OpenCode – Open source AI coding agent

OpenCode was the first open source agent I used, and my main workhorse after experimenting briefly with Claude Code and realizing the potential of agentic coding. Due to that, and because it's a popular an open source alternative, I want to be able to recommend it and be enthusiastic about it. The problem for me is that the development practices of the people that are working on it are suboptimal at best; they're constantly releasing at an extremely high cadence, where they don't even spend the time to test or fix things (or even build a proper list of changes for each release), and they add, remove, refine, change, fix, and break features constantly at that accelerated pace.

More than that, it's an extremely large and complex TypeScript code base — probably larger and more complex than it needs to be — and (partly as a result) it's fairly resource inefficient (often uses 1GB of RAM or more. For a TUI).

On top of that, at least I personally find the TUI to be overbearing and a little bit buggy, and the agent to be so full of features that I don't really need — also mildly buggy — that it sort of becomes hard to use and remember how everything is supposed to work and interact.

By default OpenCode sends all of your prompts to Grok's free tier to come up with chat summaries for the UI.

To change that, you need to set a custom "small model" in the settings.

I found out about OpenCode through the Anthropic feud. I now spend most of my AI time in it, both at work and at home. It turns out to be pretty great for general chat too, with the ability to easily integrate various tools you might need (search being the top one of course).

I have things to criticize about it, their approach to security and pulling in code being my main one, but over all it’s the most complete solution I’ve found.

They have a server/client architecture, a client SDK, a pretty good web UI and use pretty standard technologies.

The extensibility story is good and just seems like the right paradigms mostly, with agents, skills, plugins and providers.

They also ship very fast, both for good and bad, I’ve personally enjoyed the rapid improvements (~2 days from criticizing not being able to disable the default provider in the web ui to being able to).

I think OpenCode has a pretty bright future and so far I think that my issues with it should be pretty fixable. The amount of tasteful choices they’ve made dwarfs the few untasteful ones for me so far.

The team also is not breathlessly talking about how coding is dead. They have pretty sane takes on AI coding including trying to help people who care about code quality.

The Agent that is blacklisted from Anthropic AI, soon more to come.

I really like how their subagents work, as a bonus I get to choose which model is in which agent. Sadly I have to resort to the mess that Anthropic calls Claude Code

opencode stands out as one of the few agents with a proper client server architecture that allows something like openchambers great vscode extension so its possible to seamlessly switch between tui, vscode, webapp, desktop app. i think there is hardly a usable alternative for most coding agent usecases (assuming agents from model providers are a no go, they cannot be allowed to own the tools AND the models). But its also far from perfect: the webui is secretly served from their servers instead of locally for no reason. worse the fallback route gets also sent to their servers so any unknown request to opencode api ends up being sent to opencode servers potentially leaking data. the security defaults are horrific, its impossible to use it safely outside a controlled container. it will just serve your whole hard drive via rest endpoint and not constrain to project folders. the share feature uploading your conversations to their servers is also so weirdly communicated and implemented that it leaves a bad taste. I dont think this will become much better until the agent ecosystem is more modular and less monolith, acp, a2a and mcp need to become good enough so tools, prompts, skills, subagent setups and workflow engines and UIs are completely swappable and the agent core has to only focus on the essentials like runtime and glue architecture. i really hope we dont see all of these grow into full agent oses with artificial lock in effects and big effort buy in.

I'm a https://pi.dev man myself.

I love OpenCode! I wrote a plugin that adds two tools: prune and retrieve. Prune lets the LLM select messages to remove from the conversation and replace with a summary and key terms. The retrieve tool lets it get those original messages back in case they're needed. I've been livestreaming the development and using it on side projects to make sure it's actually effective... And it turns out it really is! It feels like working with an infinite context window.

https://www.youtube.com/live/z0JYVTAqeQM?si=oLvyLlZiFLTxL7p0

I’ve been extraordinarily productive with this, their $10 Go plan, and a rigorous spec-driven workflow. Haven’t touched Claude in 2 months.

I sprinkle in some billed API usage to power my task-planner and reviewer subagents (both use GPT 5.4 now).

The ability to switch models is very useful and a great learning experience. GLM, Kimi and their free models surprised me. Not the best, not perfect, but still very productive. I would be a wary shareholder if I owned a stake in the frontier labs… that moat seems to be shrinking fast.

I do like OpenCode, and have been using it in and off since last July. But I feel like they’re trying to stuff too much GUI into a TUI? Due to this I find myself using Codex and Pi more often. But am still glad OpenCode and their Zen product exist.

I don't use it for coding but as an agent backend. Maybe opencode was thought for coding mainly, but for me, it's incredibly good as an agent, especially when paired with skills, a fastapi server, and opencode go(minimax) is just so much intelligence at an incredibly cheap price. Plus, you can talk to it via channels if you use a claw.

I'd really like to get more clarification on offline mode and privacy. The github issues related to privacy did not leave a good feeling, despite being initially excited. Is offline mode a thing yet? I want to use this, but I don't want my code to leave my device.

The only thing I'm wondering is if they have eval frameworks (for lack of a better word). Their prompts don't seem to have changed for a while and I find greater success after testing and writing my own system prompts + modification to the harness to have the smallest most concise system prompt + dynamic prompt snippets per project.

I feel that if you want to build a coding agent / harness the first thing you should do is to build an evaluation framework to track performance for coding by having your internal metrics and task performance, instead I see most coding agents just fiddle with adding features that don't improve the core ability of a coding agent.

i've been using this as my primary harness for llama.cpp models, Claude, and Gemini for a few months now. the LSP integration is great. i also built a plugin to enable a very minimal OpenClaw alternative as a self modifying hook system over IPC as a plugin for OpenCode: https://github.com/khimaros/opencode-evolve -- and here's a deployment ready example making use of it which runs in an Incus container/VM: https://github.com/khimaros/persona

I wish the team would be more responsive to popular issues - like inability to provide a dynamic api key helper like claude has. This one even has a PR open: https://github.com/anomalyco/opencode/issues/1302

I've used both. I stuck with Claude Code, the ergonomics are better and the internals are clearly optimized for Opus which I use daily, you can feel it. That said OpenCode is still a very good alternative, well above Codex, Gemini CLI or Mistral Vibe in my experience.

Dax post on x:

"we see occasional complaints about memory issues in opencode

if you have this can you press ctrl+p and then "Write heap snapshot"

Upload here: https://romulus.warg-snake.ts.net/upload

Original post:https://x.com/i/status/2035333823173447885

What would be the advantage using this over say VSCode with Copilot or Roo Code? I need to make some time to compare, but just curious if others have a good insight on things.

Stupid question, but are there models worth using that specialize in a particular programming language? For instance, I'd love to be able to run a local model on my GPU that is specific to C/C++ or Python. If such a thing exists, is it worth it vs one of the cloud-based frontier models?

I'm guessing that a model which only covers a single language might be more compact and efficient vs a model trained across many languages and non-programming data.

OpenCode works awesome for me. The BigPickle model is all I want. I do not throw some large work at the agent that requires lot of reasoning, thinking or decision making. It's my role to chop the work down to bite-size and ask the fantastic BigPickle to just do the damn coding or bit of explaining. It works very well with interactive sessions with small tasks. Not giving something to work over night.

I used Claude with paid subscription and codex as well and settled to OpenCode with free models.

Can someone explain how Claude Code can instantly determine what file I have open and what lines I have selected in VS Code even if it's just running in a VS Code terminal instance, yet I cannot for the life of me get OpenCode to come anywhere close to that same experience?

The OpenCode docs suggest its possible, but it only works with their extension (not in an already open VS Code terminal) with a very specific keyboard shortcut and only barely at that.

I started my own fully containerized coding agent 100% in Go recently. Looking for testers: https://github.com/aduermael/herm

Since this is blowing up, gonna plug my opencode/claude-code plugin that allows you to annotate LLMs plans like a Google doc with strikethroughs, comments, etc. and loop with your agent until you're happy with the plan.

https://github.com/ndom91/open-plan-annotator

OpenCode is the almost good IDE I need.

What does well: helps context switching by using one window to control many repos with many worktrees each.

What can do better? It's putting AI too much in control? What if I want to edit a function myself in the workspace I'm working on? or select a snippet and refer that in the promp? without that I feel it's missing a non-negotiable feature.

The decision to build this as a TUI rather than a web app is interesting. Terminal-native tools tend to get out of the way and let you stay in flow -- curious how the context management works when you have a large codebase, do you chunk by file or do something smarter?

This replaced Aider for me a couple months back.

I use it with Qwen 3.5 running locally when my daily limits run out on my other subscriptions.

The harness is great. Local models are just slow enough that the subscription models are easier to use. For most of my tasks these days, the model's capability is sufficient; it is just not as snappy.

That's my favorite CLI agent, over codex, claude, copilot and qwen-code.

It has beautified markdown output, much more subagents, and access to free models. Unlike claude and codex. Best is opencode with GitHub opus 4.6, but the fun only lasts for a day, then you're out of tokens for a month.

The security concerns here are real but not unique to OpenCode. Most AI coding agents have the same fundamental problem: they need broad file system access to be useful, but that access surface is also the attack surface. The config-from-web issue is particularly bad because it's essentially remote code execution through prompt injection.

What I'd want to see from any of these tools is a clear permissions model — which files the agent can read vs write, whether it can execute commands, and an audit log of what it actually did. Claude Code's hooks system at least gives you deterministic guardrails before/after agent actions, but it's still early days for this whole category.

I‘m a big fan of OpenCode. I’m mostly using it via https://github.com/prokube/pk-opencode-webui which I built with my colleague (using OpenCode).

Open Code has been the backbone of our entire operation (we used Claude Code before it, and Cursor before that).

Hugely grateful for what they do.

I've used it but recently moved back to plain claude code. We use claude at the company and weirdly the experience has become less and less productive using opencode. I'm a bit sad about it as it was the first experience that really clicked and got great results out of. I'm actually curious if Anthropic knows which client is used and if they negatively influence the experience on purpose. It's very difficult to prove because nothing about this is exact science.

I tried to use it but OpenCode won't even open for me on Wayland (Ubuntu 24.04), whichever terminal emulator I use. I wasn't even aware TUI could have compatibility issues with Wayland

I've been using opencode for a few months and really like it, both from a UX and a results perspective.

It started getting increasingly flaky with Anthropic's API recently, so I switched back to Claude Code for a couple of days. Oh my, what a night and day difference. Tokens, MCP use, everything.

For anyone reading at OpenAI, your support for OpenCode is the reason I now pay you 200 bucks a month instead.

Have they "squatted" the name? It's the same name for the digital Sovereignty initiative in Germany

https://opencode.de/

I wish they would add back support for anthropic max/pro plans via calling the claude cli in -p mode. As I understand thats still very much allowed usage of claude code cli (as you are still using claude cli as it was intended anyway and fixes the issue of cache hits which I believe were the primary reason anthropic sent them the c&d). I love the UX from OpenCode (I loved setting it up in web mode on my home server and code from the web browser vs doing claude code over ssh) but until I can use my pro/max subscription I can't go back, the API pricing is way too much for my third world country wallet.

I'd love for all these tools to standardise on the structure of plugins / skills / commands / hooks etc., so I can swap between them to compare without feeling handicapped!

Anecdotal pros and one annoyance:

- GH copilot API is a first class citizen with access to multiple providers’ models at a very good price with a pro plan - no terminal flicker - it seems really good with subagents - I can’t see any terminal history inside my emacs vterm :(

Is there any initiative to port it to rust (or preferably golang) and remove weird tracking/telemetry?

I guess golang is better since we need goroutines that will basically wait for i/o and api calls.

https://github.com/charmbracelet/crush ?

Question: How do we use Agents to Schedule and Orchestrate Farming and Agricultural production, or Manufacturing assembly machines, or Train rail transportation, or mineral and energy deposit discovery and extraction or interplanetary terraforming and mining, or nuclear reactor modulation, or water desalination automation, or plutonium electric fuel cell production with a 24,000 year half-life radiation decay, or interplanetary colonization, or physics equation creation and solving for faster-than-light travel?

- With love The Official Pink Eye #ThereIsNoOther

I don’t know why people use opencode. I mean it’s better than copilot but it’s pretty terrible in general when there are better options available.

Interested if these TUI agent systems have any unique features. They all seem to be shipping the standard agent swarm/bg agent approach.

I’ve been having a very good experience with OpenCode and Kimi 2.5. It’s fast enough and smart enough that I can stay in a state of flow.

The reason I'm switching again next month, from Claude back to OpenAI.

OpenCode is an awesome tool.

Many folks from other tools are only getting exposed to the same functionality they got used to, but it offers much more than other harnesses, especially for remote coding.

You can start a service via `opencode serve`, it can be accessed from anywhere and has great experience on mobile except a few bugs. It's a really good way to work with your agents remotely, goes really well with TailScale.

The WebUI that they have can connect to multiple OpenCode backends at once, so you may use multiple VPS-es for various projects you have and control all of them from a single place.

Lastly, there's a desktop app, but TBH I find it redundant when WebUI has everything needed.

Make no mistakes though, it's not a perfect tool, my gripes with it:

- There are random bugs with loading/restoring state of the session

- Model/Provider selection switch across sessions/projects is often annoying

- I had a bug making Sonnet/Opus unusable from mobile phone because phone's clock was 150ms ahead of laptop's (ID generation)

- Sometimes agent get randomly stuck. It especially sucks for long/nested sessions

- WebUI on laptop just completely forgot all the projects at one day

- `opencode serve` doesn't pick up new skills automatically, it needs to be restarted

Interesting timing — I've been building on Cloudflare Workers with edge-first constraints, and the resource footprint of most AI coding tools is striking by comparison. A TypeScript agent that uses 1GB+ RAM for a TUI feels like the wrong abstraction. The edge computing model forces you to think differently about state, memory, and execution — maybe that's where lighter agentic tools will emerge.

aider.chat was my entry to agentic coding. OpenCode followed. Not looking back.

Can anyone clarify how this compares with Aider?

Being able to assign different models to subagents is the feature I've been wanting. I use Claude Code daily and burning the same expensive model on simple file lookups hurts. Any way to set default model routing rules, or is it manual per task?

If you are doing data engineering, there is a specific fork of Open Code with an agentic harness for data tasks: https://github.com/AltimateAI/altimate-code

The maintaining team is incredibly petty though. Tantrums when they weren't allowed to abuse Claude subscriptions and had to use the API instead. They just removed API support entirely.

For some reason opencode does not have option to disable streaming http client, which renders some inference providers unavailable...

There's also a request and a PR to add such option but it was closed due to "not adhering to community standards"

I had been using open code and admire they effort to create something huge and help a lot of developers around the world, connecting LLM our daily work without use a browser!

The MCP (Model Context Protocol) support is what makes this interesting to me. Most coding agents treat the file system and shell as the only surfaces — MCP opens up the possibility of connecting to any structured data source or API as a first-class tool without custom integration work each time.

Curious how the context window management works in practice. With large repos, the "what files to include" problem tends to dominate — does it have a strategy beyond embedding-based retrieval, or is that the main approach here?

Why is this upvoted again on hacker news this is an old thing

why is this trending, we've been using it since its beta

I haven't been able to successfully get their CLI to reliably edit files when using local models, anybody else having the same problem?

Does it support hybrid models, for e.g deep research by Model 1 vs faster response from Model2

I want to love this, but the "just install it globally, what could go wrong?" is simply not happening for an AI-written codebase. Open Source was never truly "you can trust it because everyone can vet it", so you had to do your due diligence. Now with AI code bases, that's "it might be open source, but no one actually knows how it works and only other AIs can check if it's safe because no one can read the code". Who's getting the data? No idea. How would you find out? I guess you can wireshark your network? This is not a great feeling.

Use it with zed

I've been using opencode for months with codex. best combo I've tried so far

I reach for OpenCode + Kimi to save tokens on lower priority stuff and because it's quite fast on Fireworks AI.

OpenX is becoming a bit like that hindu symbol associated with well being..

Geminis cli is clearly a fork of it btw

easily the best one

Claude Code subscription is still usable, but requires plugin like https://github.com/griffinmartin/opencode-claude-auth

Things that make an an OpenCode fanboy 1. OpenCode source code is even more awesome. I have learned so much from the way they have organized tools, agents, settings and prompts. 2. models.dev is an amazing free resource of LLM endpoints these guys have put together 3. OpenCode Zen almost always has a FREE coding model that you can use for all kinds of work. I recently used the free tier to organize and rename all my documents.

I personally like this better than claude code

What is this pervasive use of yield*? I've been writing Typescript for quiet some time and I've never seen yield* used in this way: https://github.com/anomalyco/opencode/blob/dev/packages/open...

Do they have any sandbox out of the box?

I’m happy with the one I built. (ZDX)

Honestly I was a Claude code only guy for a while. I switched to opencode and I’m not going back.

IMO, the web UI is a killer feature - it’s got just enough to be an agent manager - without any fluff. I run it on my remote VMs and connect over HTTP.

I feel like Anthropic really need to fork this for Claude Code or something. The render bugs in Claude Code drive me nuts.

OpenCode feels like the “open-source Copilot agent” moment the more control, hackability, and no black-box lock-in.

opus/sonnet 4.6 can be used in opencode with a github copilot subscription

OpenCode vs Aider vs Crush?

isn't this the one with default-on need code change to turn off telemetry?

For open models with limited context, Swival works really well: https://swival.dev

If I wanted to switch from Claude Code to this - what openai model is comparable to opus 4.6? And is it the same speed or slower/faster? Thank you!

Love opencode!

I see it uses massive resources for TUI interfaces like 1GB+ of RAM.

I wonder why did they use Typescript and not a more resource efficient language like C, C++, Rust, Zig?

Since their code is generated by AI human preferences shouldn't matter much and AI is happy to work with any language.

I use this. I run it in a sandbox[0]. I run it inside Emacs vterm so it's really quick for me to jump back and forth between this and magit, which I use to review what it's done.

I really should look into more "native" Emacs options as I find using vterm a bit of a clunky hack. But I'm just not that excited about this stuff right now. I use it because I'm lazy, that's all. Right now I'm actually getting into woodwork.

[0] https://blog.gpkb.org/posts/ai-agent-sandbox/

The fact that I wasn’t able to link llama.cpp server locally without fuss kinda beats the whole open point. Open for proprietary APIs only?

I started with Codex, then switched to OpenCode, then switched to Codex.

OpenCode just has more bugs, it's incredibly derivative so it doesn't really do anything else than Codex.

The advantage of OpenCode is that it can use any underlying model, but that's a disadvantage because it breaks the native integration. If you use Opus + Claude Code, or Gpt-Codex + Codex App, you are using it the way it was designed to be used.

If you don't actually use different models, or plan to switch, or somehow value vendor neutrality strategically, you are paying a large cost without much reward.

This is in general a rule, vendor neutrality is often seen as a generic positive, but it is actually a tradeoff. If you just build on top of AWS for example, you make use of it's features and build much faster and simpler than if you use Terraform.

You do not "write" code. Stop these euphemisms. It is an intellectual prosthetic for feeble minded people that plagiarizes code by written by others. And it connects to the currently "free" providers who own the means of plagiarizing.

There is nothing open about it. Please do not abuse the term "open" like in OpenBSD.

Codex is 15MB of memory per process. Just sayin'

minus Claude login

nice

If you have to post something like this line already loser the plot

I only boot my windows 11 gaming machine for drm games that don’t work with proton. Otherwise it’s hot garbage

I fucking love OpenCode.

[dead]

[dead]

[dead]

[dead]

[dead]

What I don't understand is that, if coding agents are making coding obsolete, why do these vibe coders not choose a language that doesn't set their users' compute resources on fire? Just vibe rust or golang for their cli tools, no one reviews code slop nowadays anyway /s.

I do not understand the insistence on using JavaScript for command line tools. I don't use rust at all, but if I'm making a vibe coded cli I'm picking rust or golang. Not zig because coding agents can't handle the breaking changes. What better test of agentic coders' conviction in their belief in AI than to vibe a language they can't read.

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[flagged]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[dead]

[flagged]

[flagged]

[flagged]

[flagged]

Just remember, OpenCode is sending telemetry to their own servers, even when you're using your own locally hosted models. There are no environment variables, flags, or other configuration options to disable this behavior.¹

At least you can easily turn off telemetry in Claude Code - just set CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC to 1.

You can use Claude Code with llama.cpp and vLLM, too right out of the box with no additional software necessary, just point ANTHROPIC_BASE_URL at your inference server of choice, with any value in ANTHROPIC_API_KEY.

Some people think that Anthropic could disable this at any time, but that's not really true - you can disable automatic updates and back up and reuse native Claude Code binaries, ensuring Anthropic cannot change your existing local Claude Code binary's behavior.

With that said, I like the idea of an open source TUI agent that won't spy on me without my consent and no way to disable it much better than a closed source TUI agent that I can effectively neuter telemetry on, but sadly, OpenCode is not the former. It's just another piece of VC-funded spyware that's destined for enshittification.

¹https://github.com/anomalyco/opencode/blob/4d7cbdcbef92bb696...

Sadly Antropic have blocked the usage of claude on it.

This is extremely cool; will download now and check it out. Thank you!