I'd like to switch to opencode, But "yolo mode" feels risky and manually approving every command the model runs kills the flow
ghrl 3 hours ago [-]
I've been using OpenCode V2 since it first appeared on the website, and I can only repeat the positive views on usability, the client/server model and self-awareness/ability to edit it's config and write plugins.
I'd like to mention two other impressive things about OpenCode.
First, their issue tracker on GitHub works really well. They have the OpenCode GitHub App connected, and for any bug report it reads the issue, tests on the mentioned version and latest dev branch, and comments the findings along with a reproduction script. For TUI Bugs it even records a video. And all that in less than two minutes, usually.
Another thing they are working on is opentunnel, where you can tunnel services to https on <random>.opentunnel.xyz and its subdomains. What's notable is that the subdomain is persistent and unique to you, and a wildcard ssl cert is actually generated on your machine, so the platform cannot see the traffic. Their primary use case seems to be making the OpenCode Server usable from anywhere, but it can do much more with their cli:
The opentunnel feature is probably related to the "official native apps that are in the coming" mentioned in the article
greenicon 6 minutes ago [-]
Unfortunately, opencode v2 still has mandatory remote config loading from your model provider's .well-known/opencode url, which gives your model provider remote code execution on your machine.
solarkraft 10 hours ago [-]
It's good.
Many of the annoyances from V1 are gone. Skills and plugins reload automatically (finally). Tasks can be backgrounded (though I think this doesn't happen automatically yet). There's a built-in skill for editing the configuration (finally I can retire mine). The front-end got some love. Apparently they re-architected the loop around Effect. Sub-sessions can be communicated with better. Configuration is loaded from the folder the session is created in rather than where the server was started.
In general, this update largely takes OpenCode into the current age features-wise and is a good overhaul quality-wise. Just in time to stop my early switching away efforts, which would've been a pain because I know few other harnesses with such a strong server/client model.
verdverm 9 hours ago [-]
To me, there are more annoyances in V2, so many that I've switched harnesses to Pi (for now?). I think the hot-reload is another security misalignment. An agent should not be able to modify plugins and have that immediately reloaded for availability.
gbalduzzi 3 hours ago [-]
Just curious, what other annoyances do you have with V2?
try-working 7 hours ago [-]
DeepSeek Harness allows the user/agent to build its own plug-ins and run them without restart, mostly. Pi and OpenCode were then influenced to do the same in their respective new versions. I don't know which has the better implementation.
pests 3 hours ago [-]
DeepSeek does. The entire thing is composed on plugins, using a framework called Cordis. Everything is a plugin. All the tools, the models, plan mode, file system access, everything. You can change anything anywhere, even reconfiguring active plugins deep internally. Cordis provides an effect system so everything can be rewound on uninstall time. This is how people run local models or just other major models, just by writing a new plugin to talk to whatever instead of the deepseek api. The agent loop itself is a plugin and can be swapped out.
I do not see where Pi does any automatic hot-reloading, though I believe there is a /reload command one has to run that can do this. Still new to Pi, if you have a link, I'd be appreciative.
This is all a stopgap until I have some time to go back to my personal/custom harness.
tacomagick 10 hours ago [-]
Tasks can be backgrounded by the model you are using automatically. It is not just manual fyi
solarkraft 9 hours ago [-]
Yeah, but only I can click to move a task to the background when it takes longer, which could and IMO should happen automatically. The model can’t always judge that. (I see how my comment wasn’t clear enough that I mean this)
In general, the preventable “model gets stuck” class of annoyances has not been fixed quite yet - there are also stil no timeouts for permission requests, at least by default.
andersonpico 9 hours ago [-]
> the preventable “model gets stuck” class of annoyances has not been fixed quite yet
I thought it was just me. The damn thing get sucked when standing up my applications like half the time
podocarp 3 hours ago [-]
Or when they get lazy and decide to grep the whole system instead of actually thinking about where things should be at…
Lucasoato 1 hours ago [-]
It’s great, they’re embracing even more the “everything’s a plugin” principle that has been pushed by other harnesses like Deepseek. Shoutout to all the AI model companies out there: if your subscription can’t be used on open code, I’ll buy something else.
Many of the workarounds I had to develop for the v1 now come as native features in v2 (i.e. session rebinding to other folders), now the only thing that was missing is the ability of plugins to read the response you’re writing (useful if you want to have the double-Esc feature like in claude code).
maelito 48 minutes ago [-]
All the power of LLMs in the hands but a page impossible to read on my phone...
smcleod 37 minutes ago [-]
Why? Loads fine on iOS 27 Safari.
red_trumpet 27 minutes ago [-]
Firefox on Android: scrolling is lagging, and when scrolling to far the text takes time to appear. Even text that was already there before.
andunie 5 hours ago [-]
Feels like more of the same, although I can't say because this article wasn't very readable so I couldn't bring myself to reading it.
A list of big new features and changes would have been nicer.
I hope they fixed the long delays to opening OpenCode I have been experiencing, and the huge database of old chats I don't care about anymore.
verdverm 5 hours ago [-]
It opens much faster because there is a persistent server running now
adamtulinius 5 hours ago [-]
That seems like the totally wrong solution to fixing spending minutes opening.
verdverm 5 hours ago [-]
This is not why they separated into client/server, but is a secondary effect.
dkarter 5 hours ago [-]
It's my daily driver - very easy to customize. Added a pretty solid vim plugin for it and a few more really useful plugins. Here are my dotfiles https://github.com/dkarter/dotfiles
antupis 3 hours ago [-]
Can you share that vim plugin? Now running opencode at Ghostty and looking diffs at github and rarely when need to do code changes manually I am using vscode but proper vim plugin would be godsend.
afruitpie 11 hours ago [-]
Native apps connecting to the OpenCode server is a great way to run sessions on remote hosts!
I wish Claude Code would adopt the same model. The desktop app deploys a separate engine that restarts and clobbers long-running sessions upon reconnect (Remote Control is their recommended solution but requires a Claude.ai account).
I’ve been vibe coding a native macOS Claude Code app that spawns a server that wraps Claude Code on remote hosts, but the UX and features are always lagging behind.
avereveard 10 hours ago [-]
Claude code agents have a protocol that's usable for the same purpose it just listen locally but it's usable i have my own claw-like that has options for claude, codex, and pi (my subscription, wife subscription, and i got a yearly sub on glm when it was cheap)
nijave 7 hours ago [-]
ACP?
avereveard 3 hours ago [-]
No because it doesnt get backgrounded and I would need to hold one end of the stream at all time, and feature completedness is spotty
I use the protocol claude code terminal use to talk to its server to spawn agents, opencode server protocol which is published for the same purpose, and manage pi command lines by pid
movedx01 1 hours ago [-]
The one that Claude Agent SDK uses?
dofm 9 hours ago [-]
I was experimenting with Paseo for this.
The Opencode desktop app could already connect to a remote web session; does it now talk to the server directly?
ghboo0927 5 hours ago [-]
Claude Code already has a server mode. The difference is that it connects through Anthropic rather than via a local socket.
awkii 5 hours ago [-]
I've developed something similar for personal use. A harness who's only job is to delegate to other harnesses (i.e: AntiGravity, Codex, Claude Code, Hermes) to create an opencode-web-like interface across multiple hosts.
For Claude Code, don't use remote-connections. Your best option is to look at how the closed-source VSCode plugin interfaces with Claude Code. The way it works is that it reads files directly. This API, although unofficial, is likely very stable, because an old VSCode extension still has to interact with new version of Claude Code.
If there's any interest in this sort of thing, maybe I'll open-source it. I would have to cleanup the slop though.
julesrms 1 hours ago [-]
[flagged]
janzong 53 minutes ago [-]
[flagged]
denysvitali 10 hours ago [-]
Their installer (curl | sh) was taking so long yesterday for me.
It turns out it's incredibly slow... because of the progress bar rendering. This is insane. The installer took 6 minutes to reach 10%:
Isn't that an issue with your terminal? Why is stdout so slow?
mayli 9 hours ago [-]
I think it's due to they are doing a funny business to parse the progress, that's pretty much vibed and no one care. Like instead of using curl's progress, they re-invented a progress tracking with the tracing interface (--trace-ascii), byte by byte :(
Okay nevermind this is pretty bad. Although humans do this too and I've also done this without realizing it, only noticed when I was trying to move a file bigger than few kilobytes.
everforward 7 hours ago [-]
I’m kind of surprised at the overlap in “has progress bar” and “is expected to take a few seconds max”.
I’ve never even debated it for files under hundreds of megs. It’ll show up soon, if I care I’ll do an ls in a loop to look at file sizes. Just log where the file is.
serf 10 hours ago [-]
I don't think fast gpu rendering terminals should be mandatory for this kind of thing, and if you should have an option that facilitates the need for one then might I suggest falling back to something sensible rather than stalling out for forever when the user doesn't render glyphs as fast as you want them to?
either that or fail outright; dont waste my time.
himata4113 9 hours ago [-]
My terminal has gpu acceleration disabled due to being wasteful with vram and while I don't use opencode I've ran the script and it was completely fine using minimal cpu.
rpcope1 7 hours ago [-]
If it doesn't work at least ok with something like xterm, someone really needs to reconsider some life decisions. Htop makes it work, why should a terminal emulator need to crack the engima just to render silly stuff?
devmor 9 hours ago [-]
Well, stdout is not typically implemented for the purpose of simulating graphics rendering via character manipulation.
himata4113 8 hours ago [-]
htop? btop(meh)? iotop? docker build?
...
claude code?
wetpaws 10 hours ago [-]
[dead]
neya 7 hours ago [-]
Sounds like I'm not upgrading then. My current OpenCode works perfectly and too many life experiences with "don't fix something that ain't broke" ;)
siwatanejo 6 hours ago [-]
Of course? I never ever upgrade any software unless I'm facing a bug or I want a new feature from the new release. Otherwise it's just taking risk for almost nothing in return.
I suspect heavy eyes free coding. I spent the last week helping them understand a major security regression in config loading, took two issues/pull requests. Our hunch is the Ai told them what they had was good, not enough human critical thinking.
I've switched to Pi because I do not like the direction v2 has taken UX. Nor do I trust the security posturing going forward. There is also the social media stunts of the CEO that push me away.
I'm now trying to advocate Pi adopt system level configuration for similar security reasons. If any HNers would like to add their thoughts, please do so here
Ive anecdotally never found OpenCode to have a real axis where I find it "best". But I havent tried it in a bit, mostly because I don't have a real gap in use case coverage between Codex/CC/Pi. Anything more specific in need probably gets a custom harness.
Maybe the Go plan is changing that for others?
verdverm 9 hours ago [-]
The Go plan is quite good, possibly the best deal out there. I recommend it for anyone interested in trying open weights ($10/month, very generous quota), and you can use it with any harness or direct curl. I have my Go sub configured through GoModel (no relation, my gateway of choice, also very good).
yuhond 8 hours ago [-]
[flagged]
cyanydeez 8 hours ago [-]
and they probably haven't stopped hijacking copy paste.
icelancer 1 hours ago [-]
probably my single biggest beef with their client and why i don't use it all that often outside of non-interactive mode
And they created the slowest webpage on the planet Earth. Full throttle slop.
EagleEdge 10 hours ago [-]
They need DHH!
acedTrex 9 hours ago [-]
chuckling
hi_hi 8 hours ago [-]
Took me a little while to figure out this was a llm harness for coding (also called an agent, I suppose, but that term seems overloaded and ambiguous to me)
There are many of these available, alongside the provider ones.
Are there any benchmarks which help me decide which ones I should try over the standard codex/claude?
jameshart 7 hours ago [-]
Codex and Claude should not be seen as ‘the standard’
They are vendor offerings but you don’t have to take them.
EgregiousCube 5 hours ago [-]
You kinda do have to take Claude if you want to take advantage of their subscription pricing, sadly.
hnhn34 5 hours ago [-]
this is no longer the case. If your harness handles login through the Agents SDK, you can use your sub now. That's why your Claude sub can be used in Amp and T3 Code for free now, but not in Pi (at least not without workarounds)
mathstuf 3 hours ago [-]
Does it need to be proxied through the `claude` tool still? Or is it authenticating directly? From what I can see (for Amp at least), it's all being proxied through a `claude` binary. Perhaps I'm seeing outdated info from the announcement though?
hebelehubele 1 hours ago [-]
Does OpenCode support it?
EgregiousCube 5 hours ago [-]
oo, really? And Anthropic's ok with that? Any reason pi can't be modified to use this method?
For example, consider something like SWEBench, where a test should pass. Harness or a skill can just tell the agent keep trying until the test pass. So same model can have a lot of behavior changes between the harnesses.
In my experience (i own a multi-agent IDE with 50+ supported harness) folks stick to first party, usually either openai or anthropic, grok, agy; if they are willing to pay for the subscription the value is unbeatable. And they don't risk trying different harnesses.
sroussey 7 hours ago [-]
I made a harness too, and recently added eval with opencode and pi and I sat between them. No gaming other than trying to figure out why I was really bad on some evals (I was not returning thinking tokens which broke cache, for example, and different model families do things way different here). I have yet to try my harness for coding but I do have a few terabytes for it to read. And I’d rather use a local model that’s fast and good at retention, but that run could take a year, lol.
esperent 6 hours ago [-]
The main four seem to be Pi, Opencode, Claude Code, abd Codex.
I do often see benchmarks comparing them and usually Pi comes out on top, but I think the benchmarks are generally testing one moderately sized clear task. Pi is minimal and great in that situation.
For more general usage, where tasks are not clear, you might interrupt at any moment to steer it, etc. benchmarks are harder I guess. I personally love pi because anytime there's something I don't like, I spin up a separate session and fix it.
E.g. I've found the "reply in simple technical English" hack amazing but I have to keep saying it over and over. So I had an agent write an extension in about ten minutes that appends a short hidden message saying all user and dev facing text must be in STE, apply that without talking about STE. Works amazingly well.
ghrl 3 hours ago [-]
I would state the same, but looking at commercial offerings for agents, such as MCP servers or skill instructions in the vender's own docs, opencode is often not mentioned at all.
Here is an example I encountered recently: The Figma MCP Server documents usage with Claude (Code), Codex, Cursor, Grok and Antigravity [], but notably not OpenCode. More so, their oauth registration seems to use some kind of whitelist, meaning just adding the MCP by url does not work either. To make it work, my agent edited the config entry to use "Codex" as the oauth name, which worked.
That's just one example, but something you see quite frequently.
esperent 2 hours ago [-]
> The Figma MCP Server documents usage with Claude (Code), Codex, Cursor, Grok and Antigravity [], but notably not OpenCode
In other words, big industry supporting bigger industry. I don't think that's surprising or says much about the real landscape.
thinkingemote 58 minutes ago [-]
Could opencode do the same? Thinking of trying pi because of these extensions
verdverm 5 hours ago [-]
I use "harness" for the tool which calls the llm, has the tools, interacts with the computer (filesys, bash, etc), does the session bookeeping
and "agent" as the instance which is running... this is the more overloaded term because there are "agent" definitions, this is where a combinatorial exists, because the running "agent" is a combination of agent definitions, context, tool choice where you can modify each independently to create a new "agent"
I wish they’d invest more time in performance improvements over code mods. I recently switched to pi which uses an order of magnitude less RAM (hundreds vs dozens) and noticeably less CPU on my machine… OpenCode is really nice but it’s about as heavy as antigravity and is substandard in features…
kbrannigan 10 hours ago [-]
With websites i went back to 90s styles.
Hyper dense in information. Anything clickable is a link.
A button is for Write actions.
Interactive element are distinct from text.
If webpage page is an interactive canvas , make the canvas the main thing ad text as support.
If you start mixing the two idk..
krb5 1 hours ago [-]
9 months ago I had opencode fill my 2tb storage with temp files and if I delete it’d redo it on session start. From that time onwards I have not gotten around to building my own verification pipeline to convince me that opencode won’t do it again. I guess I wanted to highlight that verification is what would sell me on opencode again.
kingds 11 hours ago [-]
it feels like a clear improvement across the board but a heads up: i got bitten by upgrading - since all tool calls now go through the background process, the sandbox that i use to wrap the TUI process quietly became useless. took me a day or two to realize that web fetches, etc. which should have been blocked were succeeding.
LeBit 9 hours ago [-]
Yeah, it is a regression IMO.
You need to run it with —standalone to properly sandbox it.
Those tools should be designed to be sandboxed.
verdverm 9 hours ago [-]
There are at least 3 security regressions (imo) in the initial v2 release
1. configuration loading (now fixed) dropped support for system level, then restored it incorrectly, now it is better, but still some issues in user space
2. hot-reloading of plugins, agents can now change them with immediate effect
3. this, which I was unaware of
I wonder how many more there are given this much has been found already
Cannabat 6 hours ago [-]
4. Tools added by plugins don’t respect your permission config! For example you can set a tool to always ask when used, but it auto allows.
verdverm 5 hours ago [-]
you should be able to deny it though, yea? (not common, I use this for certain subagents)
ideally that should look more like enforced preflight by the plugin system
techcomthanh 9 hours ago [-]
[flagged]
unrented7977 11 hours ago [-]
Wait, but OpenCode got renamed to Crush and the original dev went on to that new project. Where did this come from? Is this a fork? Who is behind it?
kzsh 10 hours ago [-]
Someone from Opencode went to Crush, but Opencode continued.
EDIT: as a rewrite, owning the name. but not code.
TIL - there was business in TUIs that actually warranted “acquisitions”. Always considered developing them a hobby…
bayindirh 10 hours ago [-]
A well written TUI, esp with keyboard shortcuts is a power multiplier. One of the biggest bus companies in my country used real terminals well into 2000s, and continued to use the same TUI inside a terminal emulator then.
It was efficient, bug free and fast after that many years of polish and refinement, it became one of the defining pillars of the experience. Imagine doing something and that thing can be reproduced reliably by muscle memory. You can trust that system.
Trading consoles are basically TUIs which can be driven with their specialized keyboards at great speeds and reproducibility, as well.
WillAdams 10 hours ago [-]
Moreover, it's a UI which should be ADA-compliant and readily used by the blind and visually disabled
hdjrudni 7 hours ago [-]
Wat? I would have thought a TUI is the least ADA compliant. Sure it has hotkeys (as does any decent GUI app) but does it have TalkBack and all the other accessibility features? I don't think ASCII-art is very accessibility friendly.
WillAdams 6 hours ago [-]
Should just be a matter of an appropriate terminal program and suitable settings:
(my wife works with several visually impaired people at her workplace)
chrysoprace 10 hours ago [-]
I don't think that's the case. This is from anomalyco, the company who made sst.dev. Crush is from Charm. I think OpenCode may have originally been written in Go but nowadays their codebase is TypeScript.
Edit: I'm missing some context others have pointed out.
10 hours ago [-]
jauntywundrkind 8 hours ago [-]
I'm really tired of this being retread time and time and time again.
It's just not interesting, it doesn't seem to matter, they are are separate projects and both doing great. The inside baseball about old history doesn't feel like it goes anywhere, adds anything. It didn't the last 5 times opencode got submitted!
vadepaysa 11 hours ago [-]
I love opencode, but not this website. so difficult to use.
paweladamczuk 5 hours ago [-]
I don't see a "performance" section. Should be the first one they mention.
Last time I tried OpenCode was on a tiny VPS which stopped responding when OpenCode tried to eat over 2GB of RAM in launch.
dormento 11 hours ago [-]
My notebook took up flight and launched itself through the window and died trying to render this site.
shafyy 16 minutes ago [-]
When I opened the site, I started hearing a sound that I never heard before: My MacBook Pro M4's fans. I checked ActivityMonitor and Firefox was using a significant CPU share. Are they mining crypto in the background or what's happening?
wy35 8 hours ago [-]
My M3 Pro noticeably stuttered when I opened it :/
LaurensBER 11 hours ago [-]
Interesting and I'll definitely give this a try, the client/server and plugin system do look very powerful.
However, I've been using OMP in combination with Tern (the terminal) lately and it's an incredibly smooth operation. It's hard to find a decent terminal on Windows (corporate device) but this is the best I've found so far.
flashblaze 4 hours ago [-]
Gave it a try as well, but the RAM consumption was pretty high. Had to move back to Ghostty.
DylanBohlender 8 hours ago [-]
There are dozens of us, dozens!
nfriedly 10 hours ago [-]
I've been using OpenCode 2.0 indirectly via OpenChamber 2.0 and I've been very happy with it.
Once I got past the initial hurdle of having to upgrade my server and clients all at once, everything has been smooth sailing.
bluerooibos 8 hours ago [-]
OpenChamber ftw! I'm surprised it's not more popular - so much nicer to use than the TUI.
I'm always confused when people at work show me their opencode or Claude code setup of 6 terminal windows open simultaneously with the same illegible walls of text. No idea how people still prefer that over a nice GUI.
threecheese 5 hours ago [-]
Once you really know your keyboard, it's like an extension of your hands. You can fly through those six terminals, and moving your hand to grab a mouse means stopping whatever you were doing. That wall of text is all familiar to me - I see an UI full of empty space and wonder what I could have used it for.
Of course there are great reasons for using pointers also. I'd say this is mostly a preference, I'm sure you are extremely effective using your own methods. I have maybe two dozen terminals open atm, and I can tell you what each of them is for - but put a phone bill or a bank statement in front of me and it might as well be Greek.
s4i 3 hours ago [-]
Reading long walls of unrendered markdown is where the TUI is not fun and the GUI can shine. Especially when illustrations come to play.
Also editing your own prompts with a normal text input is far better IMO (instead of whatever magical box Anthropic or OpenCode has shoehorned into the terminal).
marton78 2 hours ago [-]
I just use Zed and interface to agents via ACP. Works like a charm.
lifeisloving 5 hours ago [-]
At first glance it looks like an electron app, so thats probably a great reason not to use it. (But I could be wrong)
nater5000 11 hours ago [-]
Based on this post, it sounds like a ton of great improvements.
I've only used OpenCode a bit, but I found it was sufficient for the workloads I was throwing at it. It wasn't quite enough to beat out Codex or Claude Code as my go-to choice, though. Perhaps I'll give this version a shot and see if they've gotten it over the hump.
dsauerbrun 10 hours ago [-]
out of curiosity, how or what do you use codex/claude code for that beats opencode?
theplumber 2 hours ago [-]
Can someone tell me what am I missing if I just use the Claude extension via vscode instead of opencode? I use codex as well but only as mcp for reviews
ericpauley 2 hours ago [-]
I was finally forced to go CLI from the VSCode extension because its treatment of sub-agents is abysmal.
jrmg 7 hours ago [-]
Is there a way to buy tokens with a good model that makes OpenCode near as cheap as Claude Code with a Claude Pro subscription?
For personal projects, Claude Pro seems to give me a lot of tokens to use with Claude Code, and from experiments using other models with Claude Code (e.g. via Vercel) always seems way more expensive.
pornel 6 hours ago [-]
DeepSeek has very good bang for the buck if you're paying API prices.
6 hours ago [-]
ryuuseijin 6 hours ago [-]
There is opencode go [1] that gets you quite far compared to paying API prices. For example for the $10 subscription you get $80 in deepseek 4.1 flash credits.
The headline figures are $10/month for 'Go' with "Generous limits" and $40/month for 'Go Plus' with "Higher limits".
Then, in the table below, picking (at random of course) Claude Haiku 5.5, I see it listing 3,850 'requests' per 5h for 'Go', 15,380 'requests' per hour for 'Go Plus'. Then there's another column saying that the "Monthly Usage" is $15 for 'Go', and $60 for 'Go Plus'.
What are the limits?
What's a 'request' and how does it relate to a token?
Why are the 'requests' figures per '5h' (the limit resets every 5h?)
Why are there 'Monthly Usage' dollar amounts that are in no way connected to the subscription costs, and what do they mean?
All the explanations below are just repeated rewordings of the same thing: "Go costs $10/month with generous limits and Plus costs $40/month with higher limits", as if that makes everything clear.
sieve 3 hours ago [-]
The pricing is opaque for stupid reasons. All the information is actually available for you to calculate your usage exactly.
- You pay $10/mo for Go and get $10 worth of usage per month
- Now, each model they make available has a multiplier from 1.5-8x
- So, the expensive ones like Kimi K3 have a 1.5x multiplier, cheaper ones like DeepSeek 4.1 Flash have 8x
- This gives you usage of $15 and $80 per month respectively
- You can mix and match
- So, you can use 25% of your quota with K3 and 75% with DS41Flash ... usage of $3.75 and $60 respectively
- You divide the two figures by their respective multiplier ... $3.75 / 1.5 and $60 / 8 ... and you end up with $2.5 + $7.5 = $10 which is what you paid
- You should ignore the requests table and go directly to the price/M tokens table where all the actual rates are given
- They control usage at 5h/1w/1mo intervals
- You can use 25% of your monthly quota in a 5h block, 50% in a week, and 100% in a month.
- If you were only using DS41Flash, that is $20m, $40 and $80 worth of usage respectively which is $2.5, $5 and $10 of your subscription figure after accounting for the multipliers.
It would be so much simpler if they credited 1M microdollars per $1 of subscription and quoted the per M token rates for each model in this currency.
But then Claude/Codex/StepFun and all the other subscription services are far more opaque.
ghrl 3 hours ago [-]
This is quite confusing, indeed, but the limits are generous and transparent once you understand the concept.
There are two plans, OpenCode Go and Go Plus, for 10$/mo and 40$/mo.
With your plan, you get a specific monthly amount of money you can use, with separate weekly and 5-hour limits to not spend all at once.
The amount of money you can use depends on the model, but the usage percentage adds up regardless. For example, on the Haiku Model, the monthly limit is 15$/mo, as you read from the page. For other models, such as DeepSeek V4.1 Flash, the limit is now 80$/mo (the increased it from 60$ recently).
This might seem odd, but the stated purpose of OpenCode Go is "Low cost coding models for everyone", so the limits on the open models tend to be higher.
The math works like this: You use 5$ no Haiku and 20$ on a 60$ model, then your monthly limit is used 66.6%, meaning 5$ of Haiku or 20$ of a 60$ model remaining.
Another way to view this is as follows: You have 10$ flat usage per month, and the "higher usage on each model" is actually just a discount on the token price. So Haiku is discounted to 10$/15$=66.6%, DeepSeek to 12.5% and so on.
Go Plus just means you get more usage, though the rate is not always 4x.
To answer your remaining questions: The billing is based on the actual provider's api costs, so input/cached/output tokens. I suppose the "requests" number is estimated. The OpenCode TUI and your account website actually show the real session prices, which also helps with an understanding how expensive the agents are on raw (unsubsidized) api pricing.
The usage limits are rolling, so there is a 5-hour, a weekly and a monthly limit. The 5h is 20% of the monthly limit, and the weekly is 50% (not sure on the exact numbers).
I would agree that the pricing is confusing, but for the price you get surprisingly much usage, especially on the 60$ models. Give DeepSeek V4.1 a try, you get nearly unlimited usage and it's around Sonnet/Opus level.
robertlane0 3 hours ago [-]
As a Go subscriber, from my understanding the $10 is what you pay monthly, but you can use up to a certain set dollar amount of tokens supposedly at cost but that usage comes with different sets of rate limits so you can't rip through the whole thing in a matter of hours.
Mashimo 3 hours ago [-]
It's estimated requests based on average usage just to give you a better idea.
For some models your 10 Usd sub will get you 60 Usd worth of tokens per month.
But you can use any sub from other providers if you want. You can just log in with openai account and use chatgpt models.
drewfax 2 hours ago [-]
Yeah I am confused by their pricing explanation. All I get is there's some kind of throttling.
Mashimo 21 minutes ago [-]
What do you mean there is some kind of throttling?
ricericerice 4 hours ago [-]
It's not like Claude's subscription is super clear, either. All of these pricing models are a bit too opaque for my taste.
Are there any recommended sandbox patterns to use? Custom linux users or bubblewrap and managing openbao is getting to be a lot to manage each harness by themselves!
circularfoyers 9 hours ago [-]
I've been using https://nono.sh which uses landlock instead of bubblewrap. I had a look at all the similar alternatives when I started using it and everything else I could find was far too vibe coded for me to trust, especially for this.
jlkuester7 8 hours ago [-]
[dead]
Cannabat 6 hours ago [-]
Make sure to use the —standalone flag with sandbox invocations of opencode, else you will run the client in a sandbox but not the server.
eyeris 7 hours ago [-]
Microsoft has mxc which I think is neat — not sure if it’s the right level of abstraction for your needs
For me the distinguishing feature of OpenCode is the web ui/desktop app. I’m using OpenCode because it’s the only open-source agent-harness I’ve tried that runs outside of a TUI. I like terminals but not TUIs and especially not for prose-based interactions like prompting.
But that’s a shallow moat, and the rest of the features here are not particularly interesting to me. I don’t have a use for plugins or a model-server proxy (I can connect other tools directly to the model provider).
bluerooibos 8 hours ago [-]
The OpenCode UI was OK to use for the first few months but then it basically didn't improve at all in the next -insert-too-many-months-.
It's long been surpassed by better UIs like OpenChamber. Looks like I'll be trying Paseo out next.
Huh, this looks like a literal clone of OpenChamber, or maybe it's the other way around as Paseo has more stars and forks.
TLDR of the benefits over OpenChamber?
c-hendricks 5 hours ago [-]
Openchamber is a really good OpenCode client.
Paseo is a layer on top of various harnesses (aka you get to use a Claude subscription), and keeps its own database of sessions, etc.
I use Openchamber (and another client in neovim), but Paseo does have one convenient advantage where you can connect to other paseo servers
arational 2 hours ago [-]
Paseo doesn't offer as many features
circularfoyers 9 hours ago [-]
You should try dsh then. It also had a web ui.
0xbadcafebee 7 hours ago [-]
Unfortunately many subscriptions require you use their harness. In that case, I highly recommend using Termic (https://github.com/simion/termic/).
It's an incredibly useful GUI that lets you use the provider's harness, but adds extra productivity features. You can use OpenCode, Pi, Claude, Codex, whatever you want. The TUI runs in a window, but you can also pull up terminals, open tabs, keep projects, workspaces, show file diffs, give feedback on lines of code, review PRs, and way, way more. The number of features is impressive.
The devs are very quickly adding features, yet the app remains stable. And they fix bugs super fast! They fixed like three bugs and implemented two feature requests of mine within a week of asking. Best of all the whole thing is FOSS and they're not trying to make money off you. Absolutely awesome maintainers.
blahblaher 10 hours ago [-]
hermes also has desktop app.
julesrms 2 hours ago [-]
[dead]
YrRight2PushBac 8 hours ago [-]
It's a big improvement over the previous version. Currently, the Codex TUI has constant display issues for me, the most prevalent being random deviations of light/dark characters. So far no such issue in OpenCode. Since it's model agnostic, this might become my daily driver.
roytam87 4 hours ago [-]
From my limited testing, oc2.0 doesn't support sock5 proxy in HTTPS_PROXY, while v1 supports.
prtmnth 5 hours ago [-]
I had to update because the previous OpenCode 2.0.3 I had installed stopped working suddenly. I love the idea behind OpenCode but compared to managing Claude and Codex, it's such a pain and requires continuous debugging or managing.
chisleu 2 hours ago [-]
Does it still have rediculous system prompt alignment preventing use on red teams?
drybjed 16 minutes ago [-]
It's open source so... It does if you want it to. ;-)
oblongsquare69 11 hours ago [-]
I enjoy this program, and 2.0 is a great improvement.
sksduck 9 hours ago [-]
Otherwise called OpenMemoryLeak, it eats memory like a piece of cake.
nijave 7 hours ago [-]
Found out on 1.x it goes crazy with file watches. If you launch in a top level directory with lots of sub directories, iirc it can create millions of watches X2
Not sure if it's fixed in 2.x. There's some way to get it to not do that with ignore files or rules but not sure exactly how--I had Claude fix it...
figmert 5 hours ago [-]
Moved to pi after killing my computer one too many times. It's like they think memory has never been cheaper.
ChaseRensberger 4 hours ago [-]
their client server model is a fantastic idea and the core reason i started building https://wingman.actor a year ago.
unfortunately making a great harness is tricky and i often just steal with things i like from ocv2 and pi.
been using ocv2 as my daily driver for a while and had very little complaints. its a great product from a great team.
361994752 11 hours ago [-]
The background task / subagent feature and the ability to specify a model when starting a subagent are so far my favorite improvements. Small things but make huge QoL difference in everyday development.
montroser 10 hours ago [-]
OpenCode is a beast. Does it still try to take a disk snapshot of my working directory, even when it contains hundreds of millions of files? Does it still eat all of my memory? Does it still have a super-gigantic system prompt that wastes a solid percentage of my context window before I've even begun?
I switched to pi some months ago, and I have no complaints. It just does what it says, with no shenanigans. They updated the rendering approach recently so scrollback is nice and smooth now.
verdverm 9 hours ago [-]
I switched to Pi after experiencing OpenCode V2 about a week ago. Dislike the UX direction a lot. I took some effort to sift through the Pi plugin ecosystem to get my setup in a good place.
I will say OpenCode has likely improved significantly from your experience. I never experienced any of that since ~May of this year when I picked up OpenCode the first time.
cdnsteve 7 hours ago [-]
Is there azure login capability, for az login?
We are 100+ devs and claude code has this built in by default where we can host our own models in Azure Foundry. Devs don't need any keys since they can just use az login and it just works.
devmunchies 2 hours ago [-]
Yes. Their docs have a providers page. I was able to set it up pretty easily
statenjason 5 hours ago [-]
If workspaces had a way of managing separate Go subscriptions for team members, a large chunk of my org would jump in. DS and GLM are solid for a lot of tasks.
otekengineering 7 hours ago [-]
tried opencode for the first time to use the $200 in api credits that come with claude max but can't be used in claude code. it's great. the free nemotron 3 model is even decent, i love seeing agentic coding accessible to students and hobbiests and folks that can't drop $200/mo.
i used the bonus anthropic credits to get ornith 1.5 35b q8 running on a jetson. it's no opus 5, but it's usable for real coding and sys admin work, and works great in opencode. at least as good as sonnet 4. 5 token/sec is a little painful though.
VerifiedReports 5 hours ago [-]
"From the beginning OpenCode adopted a client/server model."
+1 for knowing when to use a slash, not a hyphen.
fantasizr 7 hours ago [-]
they deprecated the old layout which I very much preferred in open code desktop. I'm never in a rush so I'll wait for the early adopters to vouch for this release.
emerongi 11 hours ago [-]
I had no clue you have to scroll down.
wnmurphy 4 hours ago [-]
Good lord, me either. I thought it was a gag reading through these comments, but there was no way all of these people commenting were that locked into a joke.
mawadev 10 hours ago [-]
The site took a minute to load in completely and when I scrolled to the bottom I couldn't read the SDK text, it was literally cut off, kinda resembling the current state of coding very accurately lmao
NichoPaolucci 6 hours ago [-]
Did anyone find out what numbers trigger something on that counter box on the left?
amelius 9 hours ago [-]
I'm a Vim user and I actually like the web interface of AI better than the TUIs, which is weird perhaps.
0xbadcafebee 7 hours ago [-]
You may like pi-web-ui, it has a ton of useful functionality. Was a bit rough around the edges before but it's improved quickly. (https://pi.dev/packages/pi-web-ui)
verdverm 9 hours ago [-]
I was a Vim user that switched to VS Code (for reasons) and now the TUIs are where my Vim personalization efforts have been redirected. Pi is a good harness for vim users to consider if they want to try a TUI experience. The Pi plugin ecosystem is a slopfest though. There are vim bindings for Pi and OC (and VS Code) because I'm never going to give those up.
SV_BubbleTime 4 hours ago [-]
I basically only have eyes for Claude code. Sell me on this?
NamlchakKhandro 1 hours ago [-]
pi-mono is better
217 7 hours ago [-]
There's this amazing three letter harness that had all those features and more for many, many months already, but many aren't ready for that conversation
no-name-here 7 hours ago [-]
Why are “many aren’t ready for that conversation” about a harness?
wren6991 4 hours ago [-]
Agreed, DSH is pretty great
illusive4080 6 hours ago [-]
Then name it, because not everyone knows about it. Another commenter said it might be omp.
rpcope1 7 hours ago [-]
omp?
0xbadcafebee 11 hours ago [-]
Same OpenCode team who ignore bug reports, don't respond on their discord, don't have modern CI/CD test suites (often shipping regressions), don't have bots to triage bug reports or PRs, and have what might be the worst open model subscription service available today.
OpenCode users: switching to Pi takes about 5 minutes, and customizing it to work just like OpenCode takes another 30 minutes. Better design, better devs, better community.
mattkevan 10 hours ago [-]
What open model subscription services are there that’s better. Genuinely interested in knowing.
I thought $80 of deepseek usage for $10 was a pretty good deal, but I’d be delighted to hear of better ones.
strobe 9 hours ago [-]
ollama cloud, syntetic - they both has much more care about quality of model hosting
verdverm 9 hours ago [-]
OpenCode Go is the best deal in the market right now imo. Their quotas are so generous I often assume they are burning money, but I think they are largely thriving off of the subscription revenues and making it work, or their vendors are subsidizing things.
0xbadcafebee 8 hours ago [-]
Charm Hyper is not only a better deal ($350 of credit on all models for $20), but their models don't run at 20t/s, more like 200t/s
verdverm 6 hours ago [-]
I'm skeptical, their docs are pretty bad and the list of models there is really outdated. Not a good look
No prices on the pricing page, "credit" based systems is a non-starter for me, don't be different or "innovate" on pricing, unless it's an unlimited plan, but that is more progress and which I expect as commodification happens.
I am a user. They have the latest Qwen, DeepSeek, Moonshot, Z.AI, MiniMax, gpt-oss-120b, gemma-4-26b. They have them at the cheapest prices, very fast speeds consistently, caching works, and they're not dumbed down quants. The credit system is a substitute for dollars, like airline miles. $20 subscription is 250 credits per day covering all models. 1 credit is $0.05. Therefore you get $12.50 per day or $375 per month. You can buy more on-demand credits at $5 per 100. No complicated rate limits or per model price tiers like everyone else. I have not found a better provider yet and I've tried most of them.
verdverm 3 hours ago [-]
I'm not interested in credit abstractions and no amount of convincing will change that, same reason I have no interest in Circle CI
If you like their service and the company, tell them they are losing potential customers with their inaccurate, minimal docs and unappealing pricing abstractions
bluerooibos 8 hours ago [-]
There's an actual team? I had the same experience and figured it was basically just one guy. Their issue backlog does seem a total shambles though.
verdverm 9 hours ago [-]
While I just switched from OpenCode to Pi, I'm still unclear on which is better in terms of handling github issues/pull-requests. I do give OC credit here, especially after the last week.
Here's the Pi issue for a security feature request, derived from an opencode v2 security regression I was able to work through with the OC team. This issue links to the OpenCode ones too.
ah man, I wanted this domain but I'm pleased to see it's at least being put to use instead of squatted
markerz 11 hours ago [-]
This game is quite interestingly fun despite how basic it is.
sleep_debt 6 hours ago [-]
Is it still super bloated?
anon373839 5 hours ago [-]
What in the hell is wrong with this page? Whole blocks of content disappear and reappear on my phone as I scroll. Eventually the page just starts force reloading. It’s a blog post! What could possibly require … whatever this is?
aniceperson 11 hours ago [-]
having a daemon PID helps for web gui, but may bite in unexpected ways under extensive parallization.
Saris 8 hours ago [-]
What the heck is this website, it completely locks up the tab it's in for 15 seconds and none of the text shows up at all until it finishes.
rfgplk 10 hours ago [-]
Goes to check the repo out
> TypeScript
Considering the whole thing is LLM produced I would like an explicit answer as to why C++ or Rust weren't used to write the project in.
porkloin 6 hours ago [-]
They refactored from golang to typescript too, which is wild.
k__ 10 hours ago [-]
Probably because of Effect.
verdverm 8 hours ago [-]
Compiled languages make 3rd party plugins harder.
Also, the Rust ecosystem is annoying with demands for explicit answers to why their preferred language was not used.
metaltyphoon 8 hours ago [-]
> the Rust ecosystem is annoying with demands
One person != "the ecosystem"
verdverm 8 hours ago [-]
If you hang out on HN, you see this kind of statement a lot, it's happens so often (more than any other language right now, used to be TypeScript), it's the outside perception of the ecosystem. If they chill out on the superiority claims, that perception can change like it did for TypeScript.
suprjami 10 hours ago [-]
2.0 is a big disappointment so far.
Several basic things don't work, like hiding the sidebar.
With 3.2k open GitHub issues there's no point reporting anything.
esafak 10 hours ago [-]
Somehow I manage to get issues noticed and PRs merged. They aggressively cull old issues but if they take notice things get done. I contributed just this week.
verdverm 9 hours ago [-]
I too have been able to get several issues addressed and pull requests merged (not mine, others had noticed first).
Being the most popular open harness, they get inundated with slop and are doing their best (imo).
fg137 10 hours ago [-]
> We've built a minimal JavaScript interpreter
Huh?
platevoltage 7 hours ago [-]
I've been getting good results from OpenCode. Has anyone been able to get it to work with local models though? It doesn't seem to want to play nice with Ollama.
dv35z 4 hours ago [-]
I used OpenCode to help me install ollama, Qwen local LLM, and connect OpenCode to it.
The computer is very slow (old Dell Optiplex running Mint Debian Linux), but it worked! So cool to turn off the network, and still be able to chit-chat with Qwen model ("Tell me a joke about...").
platevoltage 4 hours ago [-]
cool, I'll have to mess around with it some more. I don't expect to be able to do any real work with my 16GB MacBook Pro, but eventually, I would like an all local setup.
anthonyIPH 6 hours ago [-]
I have an open code server running as a service on a linux desktop with the port opened up so I can use the web UI from my windows laptop. The same linux desktop is running Ollama and I'm currently using qwen3.6:35b with it.
The setup was mostly for the learning experience and I haven't done any serious work with it, but it's been great for writing bash scripts.
EddieRingle 7 hours ago [-]
I have no issues using it with llama.cpp.
tontinton 11 hours ago [-]
Everyone copies https//maki.sh. I've been the first!
arialdomartini 10 hours ago [-]
curl | sh should die
StrLght 10 hours ago [-]
The monkey's paw curls, now it's "Give your agent a link to our SKILL.md!"
ingen0s 8 hours ago [-]
oh coolio
moralestapia 10 hours ago [-]
These guys stole money from me. It amounts to like 10 US or something, so not significant, but still...
Their models have pricing published in their docs, like any other LLM provider. I measured the tokens I consumed, did the math, and it was always off, in their favor. One model (GPT Luna) was about 2x as expensive as advertised.
I joined their Discord, which is apparently how you get support from them. I filed a bug and someone from their team replied, we verified the data, and he said that something was indeed off and that he'd escalate it. Then silence. After 2–3 weeks, I followed up and was now ignored.
As I said, the amount isn't material to me, but if they do this a million times, they could make some decent money out of it. No idea if it's on purpose, I'll leave that to the reader to speculate.
Overall, their complete lack of interest after acknowledging the "bug" left a really bad taste in my mouth, so I decided to leave.
jambutters 9 hours ago [-]
Ahh. I recall their opencode go plan offered $60-$80 worth of Deepseek for $5-10 or something? I was debating if I should try it out but I think this is convincing me not to...Thanks for the heads up
andersonpico 9 hours ago [-]
Can you link to the discord thread? I'm very much interested and I'll be double check my usage vs. their rates.
moralestapia 7 hours ago [-]
Sure, shoot me an email (see profile).
I'd prefer not to share my Discord username here.
esafak 10 hours ago [-]
OC is all right -- it's my daily driver -- but it could be better. I'd like a harness to let me customize the GUI, not just add MCPs and plugins. For example, I'd like add buttons to merge a PR, and show indicators for CI. Claude Code does a lot of this out of the box. Give me UI building blocks (buttons, labels, etc.) and wire them with my own functions. Could Code Mode enable this?
The built-in browser is a most welcome feature.
PS(A): Opencode Go is a great deal and now has a $40 plan.
dizhn 9 hours ago [-]
Look at Paseo and build your own backend and UI plugins while still using opencode.
It seems to check all items on your list but of course that doesn't mean it's for you necessarily.
By the way opencode go $40 plan for 2x-3x usage vs their $10 plan is not such a good deal.
verdverm 4 hours ago [-]
I did not share my checklist, so your claim is non sequitur
I'm very happy with my OpenCode go plans, it's the best deal I have found, everyone that claims they are better is not upon my inspection
Firepass v2 (unlimited kimi-2.7 for $50/m) sounded good too, but I missed that by the time I found Fireworks, v3 is still soon (tm)
dizhn 3 hours ago [-]
I am on mobile didn't realize the author names were different. Sorry.
I agree that opencode go is great. I didn't say it wasn't. That the $40 plan is not 4 times the value of their $10 plan is just fact and that was my claim.
verdverm 3 hours ago [-]
no worries, and yeah, that $40 not being a straight up 4x is super annoying, they did just bump up deepseek ("cheapseek") to $80 credit on the $10 plan iirc
long-term I look forward to unlimited plans
julesrms 2 hours ago [-]
[dead]
keyle 11 hours ago [-]
I was annoyed that it takes just as much ram if not more than 1.0
2 hours ago [-]
ingen0s 8 hours ago [-]
Bros - that opening disk transfer interaction is peak awesomeness. I copied about 4 files and did not want to stop...Id sit there all day and do all of them just to see what happens in the end...perhaps later this weekend.
my002 11 hours ago [-]
I really hope we don't get a slew of WebGL-intensive sites.
I'd like to switch to opencode, But "yolo mode" feels risky and manually approving every command the model runs kills the flow
I'd like to mention two other impressive things about OpenCode.
First, their issue tracker on GitHub works really well. They have the OpenCode GitHub App connected, and for any bug report it reads the issue, tests on the mentioned version and latest dev branch, and comments the findings along with a reproduction script. For TUI Bugs it even records a video. And all that in less than two minutes, usually.
https://github.com/anomalyco/opencode/issues?q=is%3Aissue+st...
Another thing they are working on is opentunnel, where you can tunnel services to https on <random>.opentunnel.xyz and its subdomains. What's notable is that the subdomain is persistent and unique to you, and a wildcard ssl cert is actually generated on your machine, so the platform cannot see the traffic. Their primary use case seems to be making the OpenCode Server usable from anywhere, but it can do much more with their cli:
https://opentunnel.xyz/
Many of the annoyances from V1 are gone. Skills and plugins reload automatically (finally). Tasks can be backgrounded (though I think this doesn't happen automatically yet). There's a built-in skill for editing the configuration (finally I can retire mine). The front-end got some love. Apparently they re-architected the loop around Effect. Sub-sessions can be communicated with better. Configuration is loaded from the folder the session is created in rather than where the server was started.
In general, this update largely takes OpenCode into the current age features-wise and is a good overhaul quality-wise. Just in time to stop my early switching away efforts, which would've been a pain because I know few other harnesses with such a strong server/client model.
https://github.com/cordiverse/cordis
This is all a stopgap until I have some time to go back to my personal/custom harness.
In general, the preventable “model gets stuck” class of annoyances has not been fixed quite yet - there are also stil no timeouts for permission requests, at least by default.
I thought it was just me. The damn thing get sucked when standing up my applications like half the time
Many of the workarounds I had to develop for the v1 now come as native features in v2 (i.e. session rebinding to other folders), now the only thing that was missing is the ability of plugins to read the response you’re writing (useful if you want to have the double-Esc feature like in claude code).
A list of big new features and changes would have been nicer.
I hope they fixed the long delays to opening OpenCode I have been experiencing, and the huge database of old chats I don't care about anymore.
I wish Claude Code would adopt the same model. The desktop app deploys a separate engine that restarts and clobbers long-running sessions upon reconnect (Remote Control is their recommended solution but requires a Claude.ai account).
I’ve been vibe coding a native macOS Claude Code app that spawns a server that wraps Claude Code on remote hosts, but the UX and features are always lagging behind.
I use the protocol claude code terminal use to talk to its server to spawn agents, opencode server protocol which is published for the same purpose, and manage pi command lines by pid
The Opencode desktop app could already connect to a remote web session; does it now talk to the server directly?
For Claude Code, don't use remote-connections. Your best option is to look at how the closed-source VSCode plugin interfaces with Claude Code. The way it works is that it reads files directly. This API, although unofficial, is likely very stable, because an old VSCode extension still has to interact with new version of Claude Code.
If there's any interest in this sort of thing, maybe I'll open-source it. I would have to cleanup the slop though.
It turns out it's incredibly slow... because of the progress bar rendering. This is insane. The installer took 6 minutes to reach 10%:
curl -fsSL https://opencode.ai/v2/install | bash
Managed to fix it by running this instead:
curl -fsSL https://opencode.ai/v2/install | bash 2>&1 | cat
https://github.com/anomalyco/opencode/issues/22998 https://github.com/anomalyco/opencode/issues/53702
I’ve never even debated it for files under hundreds of megs. It’ll show up soon, if I care I’ll do an ls in a loop to look at file sizes. Just log where the file is.
either that or fail outright; dont waste my time.
...
claude code?
https://news.ycombinator.com/item?id=50075319
I've switched to Pi because I do not like the direction v2 has taken UX. Nor do I trust the security posturing going forward. There is also the social media stunts of the CEO that push me away.
I'm now trying to advocate Pi adopt system level configuration for similar security reasons. If any HNers would like to add their thoughts, please do so here
https://github.com/earendil-works/pi/issues/10895
Maybe the Go plan is changing that for others?
time curl -fsSL https://opencode.ai/v2/install | bash
real 0m24.975s user 0m9.537s sys 0m14.904s
Edit: indeed https://github.com/anomalyco/opencode/commit/d099d2cb2a0869d... / https://github.com/anomalyco/opencode/pull/55586
There are many of these available, alongside the provider ones.
Are there any benchmarks which help me decide which ones I should try over the standard codex/claude?
They are vendor offerings but you don’t have to take them.
For example, consider something like SWEBench, where a test should pass. Harness or a skill can just tell the agent keep trying until the test pass. So same model can have a lot of behavior changes between the harnesses.
In my experience (i own a multi-agent IDE with 50+ supported harness) folks stick to first party, usually either openai or anthropic, grok, agy; if they are willing to pay for the subscription the value is unbeatable. And they don't risk trying different harnesses.
I do often see benchmarks comparing them and usually Pi comes out on top, but I think the benchmarks are generally testing one moderately sized clear task. Pi is minimal and great in that situation.
For more general usage, where tasks are not clear, you might interrupt at any moment to steer it, etc. benchmarks are harder I guess. I personally love pi because anytime there's something I don't like, I spin up a separate session and fix it.
E.g. I've found the "reply in simple technical English" hack amazing but I have to keep saying it over and over. So I had an agent write an extension in about ten minutes that appends a short hidden message saying all user and dev facing text must be in STE, apply that without talking about STE. Works amazingly well.
Here is an example I encountered recently: The Figma MCP Server documents usage with Claude (Code), Codex, Cursor, Grok and Antigravity [], but notably not OpenCode. More so, their oauth registration seems to use some kind of whitelist, meaning just adding the MCP by url does not work either. To make it work, my agent edited the config entry to use "Codex" as the oauth name, which worked.
That's just one example, but something you see quite frequently.
In other words, big industry supporting bigger industry. I don't think that's surprising or says much about the real landscape.
and "agent" as the instance which is running... this is the more overloaded term because there are "agent" definitions, this is where a combinatorial exists, because the running "agent" is a combination of agent definitions, context, tool choice where you can modify each independently to create a new "agent"
I think Scion (Google's) does a decent job defining these concepts: https://googlecloudplatform.github.io/scion/concepts/
Interactive element are distinct from text.
If webpage page is an interactive canvas , make the canvas the main thing ad text as support.
If you start mixing the two idk..
You need to run it with —standalone to properly sandbox it.
Those tools should be designed to be sandboxed.
1. configuration loading (now fixed) dropped support for system level, then restored it incorrectly, now it is better, but still some issues in user space
2. hot-reloading of plugins, agents can now change them with immediate effect
3. this, which I was unaware of
I wonder how many more there are given this much has been found already
ideally that should look more like enforced preflight by the plugin system
EDIT: as a rewrite, owning the name. but not code.
https://x.com/thdxr/status/1933561254481666466
It was efficient, bug free and fast after that many years of polish and refinement, it became one of the defining pillars of the experience. Imagine doing something and that thing can be reproduced reliably by muscle memory. You can trust that system.
Trading consoles are basically TUIs which can be driven with their specialized keyboards at great speeds and reproducibility, as well.
https://support.freedomscientific.com/support/technicalsuppo...
(my wife works with several visually impaired people at her workplace)
Edit: I'm missing some context others have pointed out.
It's just not interesting, it doesn't seem to matter, they are are separate projects and both doing great. The inside baseball about old history doesn't feel like it goes anywhere, adds anything. It didn't the last 5 times opencode got submitted!
Last time I tried OpenCode was on a tiny VPS which stopped responding when OpenCode tried to eat over 2GB of RAM in launch.
However, I've been using OMP in combination with Tern (the terminal) lately and it's an incredibly smooth operation. It's hard to find a decent terminal on Windows (corporate device) but this is the best I've found so far.
Once I got past the initial hurdle of having to upgrade my server and clients all at once, everything has been smooth sailing.
I'm always confused when people at work show me their opencode or Claude code setup of 6 terminal windows open simultaneously with the same illegible walls of text. No idea how people still prefer that over a nice GUI.
Of course there are great reasons for using pointers also. I'd say this is mostly a preference, I'm sure you are extremely effective using your own methods. I have maybe two dozen terminals open atm, and I can tell you what each of them is for - but put a phone bill or a bank statement in front of me and it might as well be Greek.
Also editing your own prompts with a normal text input is far better IMO (instead of whatever magical box Anthropic or OpenCode has shoehorned into the terminal).
I've only used OpenCode a bit, but I found it was sufficient for the workloads I was throwing at it. It wasn't quite enough to beat out Codex or Claude Code as my go-to choice, though. Perhaps I'll give this version a shot and see if they've gotten it over the hump.
For personal projects, Claude Pro seems to give me a lot of tokens to use with Claude Code, and from experiments using other models with Claude Code (e.g. via Vercel) always seems way more expensive.
[1]: https://opencode.ai/go
The headline figures are $10/month for 'Go' with "Generous limits" and $40/month for 'Go Plus' with "Higher limits".
Then, in the table below, picking (at random of course) Claude Haiku 5.5, I see it listing 3,850 'requests' per 5h for 'Go', 15,380 'requests' per hour for 'Go Plus'. Then there's another column saying that the "Monthly Usage" is $15 for 'Go', and $60 for 'Go Plus'.
What are the limits?
What's a 'request' and how does it relate to a token?
Why are the 'requests' figures per '5h' (the limit resets every 5h?)
Why are there 'Monthly Usage' dollar amounts that are in no way connected to the subscription costs, and what do they mean?
All the explanations below are just repeated rewordings of the same thing: "Go costs $10/month with generous limits and Plus costs $40/month with higher limits", as if that makes everything clear.
- You pay $10/mo for Go and get $10 worth of usage per month
- Now, each model they make available has a multiplier from 1.5-8x
- So, the expensive ones like Kimi K3 have a 1.5x multiplier, cheaper ones like DeepSeek 4.1 Flash have 8x
- This gives you usage of $15 and $80 per month respectively
- You can mix and match
- So, you can use 25% of your quota with K3 and 75% with DS41Flash ... usage of $3.75 and $60 respectively
- You divide the two figures by their respective multiplier ... $3.75 / 1.5 and $60 / 8 ... and you end up with $2.5 + $7.5 = $10 which is what you paid
- You should ignore the requests table and go directly to the price/M tokens table where all the actual rates are given
- They control usage at 5h/1w/1mo intervals
- You can use 25% of your monthly quota in a 5h block, 50% in a week, and 100% in a month.
- If you were only using DS41Flash, that is $20m, $40 and $80 worth of usage respectively which is $2.5, $5 and $10 of your subscription figure after accounting for the multipliers.
It would be so much simpler if they credited 1M microdollars per $1 of subscription and quoted the per M token rates for each model in this currency.
But then Claude/Codex/StepFun and all the other subscription services are far more opaque.
There are two plans, OpenCode Go and Go Plus, for 10$/mo and 40$/mo.
With your plan, you get a specific monthly amount of money you can use, with separate weekly and 5-hour limits to not spend all at once.
The amount of money you can use depends on the model, but the usage percentage adds up regardless. For example, on the Haiku Model, the monthly limit is 15$/mo, as you read from the page. For other models, such as DeepSeek V4.1 Flash, the limit is now 80$/mo (the increased it from 60$ recently).
This might seem odd, but the stated purpose of OpenCode Go is "Low cost coding models for everyone", so the limits on the open models tend to be higher.
The math works like this: You use 5$ no Haiku and 20$ on a 60$ model, then your monthly limit is used 66.6%, meaning 5$ of Haiku or 20$ of a 60$ model remaining.
Another way to view this is as follows: You have 10$ flat usage per month, and the "higher usage on each model" is actually just a discount on the token price. So Haiku is discounted to 10$/15$=66.6%, DeepSeek to 12.5% and so on.
Go Plus just means you get more usage, though the rate is not always 4x.
To answer your remaining questions: The billing is based on the actual provider's api costs, so input/cached/output tokens. I suppose the "requests" number is estimated. The OpenCode TUI and your account website actually show the real session prices, which also helps with an understanding how expensive the agents are on raw (unsubsidized) api pricing. The usage limits are rolling, so there is a 5-hour, a weekly and a monthly limit. The 5h is 20% of the monthly limit, and the weekly is 50% (not sure on the exact numbers).
I would agree that the pricing is confusing, but for the price you get surprisingly much usage, especially on the 60$ models. Give DeepSeek V4.1 a try, you get nearly unlimited usage and it's around Sonnet/Opus level.
For some models your 10 Usd sub will get you 60 Usd worth of tokens per month.
But you can use any sub from other providers if you want. You can just log in with openai account and use chatgpt models.
Are there any recommended sandbox patterns to use? Custom linux users or bubblewrap and managing openbao is getting to be a lot to manage each harness by themselves!
https://github.com/microsoft/mxc
But that’s a shallow moat, and the rest of the features here are not particularly interesting to me. I don’t have a use for plugins or a model-server proxy (I can connect other tools directly to the model provider).
It's long been surpassed by better UIs like OpenChamber. Looks like I'll be trying Paseo out next.
TLDR of the benefits over OpenChamber?
Paseo is a layer on top of various harnesses (aka you get to use a Claude subscription), and keeps its own database of sessions, etc.
I use Openchamber (and another client in neovim), but Paseo does have one convenient advantage where you can connect to other paseo servers
It's an incredibly useful GUI that lets you use the provider's harness, but adds extra productivity features. You can use OpenCode, Pi, Claude, Codex, whatever you want. The TUI runs in a window, but you can also pull up terminals, open tabs, keep projects, workspaces, show file diffs, give feedback on lines of code, review PRs, and way, way more. The number of features is impressive.
The devs are very quickly adding features, yet the app remains stable. And they fix bugs super fast! They fixed like three bugs and implemented two feature requests of mine within a week of asking. Best of all the whole thing is FOSS and they're not trying to make money off you. Absolutely awesome maintainers.
Not sure if it's fixed in 2.x. There's some way to get it to not do that with ignore files or rules but not sure exactly how--I had Claude fix it...
unfortunately making a great harness is tricky and i often just steal with things i like from ocv2 and pi.
been using ocv2 as my daily driver for a while and had very little complaints. its a great product from a great team.
I switched to pi some months ago, and I have no complaints. It just does what it says, with no shenanigans. They updated the rendering approach recently so scrollback is nice and smooth now.
I will say OpenCode has likely improved significantly from your experience. I never experienced any of that since ~May of this year when I picked up OpenCode the first time.
i used the bonus anthropic credits to get ornith 1.5 35b q8 running on a jetson. it's no opus 5, but it's usable for real coding and sys admin work, and works great in opencode. at least as good as sonnet 4. 5 token/sec is a little painful though.
+1 for knowing when to use a slash, not a hyphen.
OpenCode users: switching to Pi takes about 5 minutes, and customizing it to work just like OpenCode takes another 30 minutes. Better design, better devs, better community.
I thought $80 of deepseek usage for $10 was a pretty good deal, but I’d be delighted to hear of better ones.
https://hyper.charm.land/docs/models.html
No prices on the pricing page, "credit" based systems is a non-starter for me, don't be different or "innovate" on pricing, unless it's an unlimited plan, but that is more progress and which I expect as commodification happens.
https://hyper.charm.land/docs/plans-billing.html
If you like their service and the company, tell them they are losing potential customers with their inaccurate, minimal docs and unappealing pricing abstractions
Here's the Pi issue for a security feature request, derived from an opencode v2 security regression I was able to work through with the OC team. This issue links to the OpenCode ones too.
https://github.com/earendil-works/pi/issues/10895
The Pi dev does not seem to grasp the issue after several back and forths.
I do really like their CONTRIBUTING.md
https://github.com/earendil-works/pi/blob/main/CONTRIBUTING....
> TypeScript
Considering the whole thing is LLM produced I would like an explicit answer as to why C++ or Rust weren't used to write the project in.
Also, the Rust ecosystem is annoying with demands for explicit answers to why their preferred language was not used.
One person != "the ecosystem"
Several basic things don't work, like hiding the sidebar.
With 3.2k open GitHub issues there's no point reporting anything.
I had one this week that, while took some effort to explain the why, was handled better than I expected. (https://github.com/anomalyco/opencode/pull/54921)
Being the most popular open harness, they get inundated with slop and are doing their best (imo).
Huh?
The computer is very slow (old Dell Optiplex running Mint Debian Linux), but it worked! So cool to turn off the network, and still be able to chit-chat with Qwen model ("Tell me a joke about...").
The setup was mostly for the learning experience and I haven't done any serious work with it, but it's been great for writing bash scripts.
Their models have pricing published in their docs, like any other LLM provider. I measured the tokens I consumed, did the math, and it was always off, in their favor. One model (GPT Luna) was about 2x as expensive as advertised.
I joined their Discord, which is apparently how you get support from them. I filed a bug and someone from their team replied, we verified the data, and he said that something was indeed off and that he'd escalate it. Then silence. After 2–3 weeks, I followed up and was now ignored.
As I said, the amount isn't material to me, but if they do this a million times, they could make some decent money out of it. No idea if it's on purpose, I'll leave that to the reader to speculate.
Overall, their complete lack of interest after acknowledging the "bug" left a really bad taste in my mouth, so I decided to leave.
I'd prefer not to share my Discord username here.
The built-in browser is a most welcome feature.
PS(A): Opencode Go is a great deal and now has a $40 plan.
Scion was the tool I'd been using for this, but haven't been doing that kind of stuff for some time.
https://googlecloudplatform.github.io/scion/overview/
By the way opencode go $40 plan for 2x-3x usage vs their $10 plan is not such a good deal.
I'm very happy with my OpenCode go plans, it's the best deal I have found, everyone that claims they are better is not upon my inspection
Firepass v2 (unlimited kimi-2.7 for $50/m) sounded good too, but I missed that by the time I found Fireworks, v3 is still soon (tm)
I agree that opencode go is great. I didn't say it wasn't. That the $40 plan is not 4 times the value of their $10 plan is just fact and that was my claim.
long-term I look forward to unlimited plans