AI tools · AI coding agent
OpenCode
An open-source coding agent recommended for mixing models and providers, including cheap or local ones, with a good-value Go plan; critics cite prompt privacy, security holes and bloat.
Summarized from 2593 comments.
An open-source coding agent recommended for mixing models and providers, including cheap or local ones, with a good-value Go plan; critics cite prompt privacy, security holes and bloat.
- recommend
- 1060
- criticize
- 572
- months recommended
- 13 of 13
- median owned, 41 owners said
- 0.2 years
Why people love it
Mix models and providers freely · 6
I've been experimenting with some planner-executor-reviewer setup in opencode, and I'm starting to feel like multiple smaller models working together are netting me better results
Mar 2026 · commentthere is another service that lets you upload keys for Ant/OAI, where you add one key for your company and then OpenCode enables you to budget / route across vendors
Oct 2026 · commentA harness like OpenCode will enable you to use different models in one session, or more specifically different subtasks when doing long running teams.
Oct 2026 · commentGo plan offers strong value · 5
The OpenCode Go $40 plan with DeepSeek flash is like 2x the value of the Claude max 20x plan for how much I actually get out of it, for 1/5 the price.
Oct 2026 · commentYour comparison is the research I didn't know I needed, and I will be cancelling my Copilot subscription to replace it with OpenCode Go right away.
Apr 2026 · commentOpenCode Go is a smoking deal IMO. You basically get 6x multiplier on the $10 price since you get $60 worth of usage for $10.
Jun 2026 · commentReplaces Copilot or Claude Code · 5
Your comparison is the research I didn't know I needed, and I will be cancelling my Copilot subscription to replace it with OpenCode Go right away.
Apr 2026 · commentswitch to opencode - they allegedly reverse engineered Claude Code, and so the performance you get with Claude models should be very similar
Nov 2025 · commentMy experience with Opencode using its default model, vs. Github Copilot using its default model, is night and day. One is amazing
Jan 2026 · commentWorks well with open models · 4
This is a relatively complex piece of tooling built entirely by Gemma 4 inside OpenCode where I manually intervened maybe only 4 times
May 2026 · commentIt's not particularly hard to set up OpenCode for your company and plug in one of the myriad inference providers running free models.
Jun 2026 · commentI've completely replaced GitHub Copilot using Sonnet 3.6 with OpenCode using Qwen3.6 27b, and it's been a great experience.
May 2026 · comment
What people warn about
Prompts routed through their servers · 3
Their terms and conditions allowed training on prompts, the default behavior was to route prompts to their servers for conversation summary/labeling.
Aug 2026 · commenteven when using local models in ollama or lmstudio, prompts are proxied via their domain, so never put anything sensitive even when using local setup
Mar 2026 · commentI've had opencode go + opencode work reliably, though I'm skeptical of how robust their data security claims are in practice
Sep 2026 · commentSecurity holes in local server · 3
Previous versions of OpenCode started a server which allowed any website visited in a web browser to execute arbitrary commands on the local machine.
Jan 2026 · commentthe CORS fix, while a huge improvement, is not sufficient since it doesn't protect from things like malicious code running locally or on the network
Jan 2026 · commentA permanently running buggy server on your computer instead of a screen or tmux session is not something that should be a default solution.
Oct 2026 · commentResource heavy, laggy and bloated · 4
It has a web UI, smoother UX, and less flickering. Nothing groundbreaking, but it is pretty annoying that even something as simple as tagging files with @ is still so laggy.
Jan 2026 · commentthe runtime is so resource heavy that, even though the heavy computational workload is given to AI on a remote cluster of servers, it will bring an old-ish laptop to a stall
Mar 2026 · commentWish Pi (and Opencode, DeepSeek Harness, Claude, Claude Desktop, Codex Desktop) was written in a memory and performance efficient language.
Oct 2026 · commentBuggy and needs constant fiddling · 3
I love the idea behind OpenCode but compared to managing Claude and Codex, it's such a pain and requires continuous debugging or managing.
Oct 2026 · commentOpencode (and other coding agents) have hundreds of open issues reported. It is quite discouraging when they are not being closed/fixed.
May 2026 · commentA permanently running buggy server on your computer instead of a screen or tmux session is not something that should be a default solution.
Oct 2026 · comment
What hackers pick instead
- Claude CodeAn agentic coding tool that writes, runs and tests code on its own, often replacing hand-coding entirely, though many report quality regressions after updates and broken code on complex work.4522recommend
- OpenAI CodexA coding agent many find as good as or better than Claude Code, thorough on hard problems, with generous $20-plan limits, though its output needs careful review.2474recommend
- Gemini CLIGoogle's terminal coding agent is liked for its generous free tier, polished interface and strong one-shot results, but critics cite rate limits, bugs, eager code edits and its planned discontinuation.172recommend
- ClineFree open-source VS Code agent that works with your own API key, billed per token. Critics note context loss in long sessions.63recommend
- Mistral VibeA terminal coding agent people recommend for cheap subscription value and an open-source CLI; the most common caveat is weaker models and data-use defaults on Team plans.57recommend
Every quote
The 40 most detailed of 2593 comments. Each links to the original.
I've been experimenting with some planner-executor-reviewer setup in opencode, and I'm starting to feel like multiple smaller models working together are netting me better results
Recommends · Mar 2026 · in “Anthropic Update on Session Limits”
It has a web UI, smoother UX, and less flickering. Nothing groundbreaking, but it is pretty annoying that even something as simple as tagging files with @ is still so laggy.
Mixed · Jan 2026 · in “Sisyphus Now Lives in Oh My Claude”
the runtime is so resource heavy that, even though the heavy computational workload is given to AI on a remote cluster of servers, it will bring an old-ish laptop to a stall
Mixed · Mar 2026 · in “OpenCode – The open source AI coding agent”
there is another service that lets you upload keys for Ant/OAI, where you add one key for your company and then OpenCode enables you to budget / route across vendors
Mixed · Oct 2026 · in “OpenCode Hacked: User credentials leaked”
A harness like OpenCode will enable you to use different models in one session, or more specifically different subtasks when doing long running teams.
Recommends · Oct 2026 · in “Getting the most out of Opus 5.5 in Claude and Claude Code”
The OpenCode Go $40 plan with DeepSeek flash is like 2x the value of the Claude max 20x plan for how much I actually get out of it, for 1/5 the price.
Recommends · Oct 2026 · in “MiniMax M3.1 Flash”
Their terms and conditions allowed training on prompts, the default behavior was to route prompts to their servers for conversation summary/labeling.
Mixed · Aug 2026 · in “DeepSeek V4 Pro 0813”
the CORS fix, while a huge improvement, is not sufficient since it doesn't protect from things like malicious code running locally or on the network
Mixed · Jan 2026 · in “Remote Code Execution in OpenCode, update now”
Your comparison is the research I didn't know I needed, and I will be cancelling my Copilot subscription to replace it with OpenCode Go right away.
Recommends · Apr 2026 · in “Reallocating $100/Month Claude Code Spend to Zed and OpenRouter”
switch to opencode - they allegedly reverse engineered Claude Code, and so the performance you get with Claude models should be very similar
Recommends · Nov 2025 · in “The current state of the theory that GPL propagates to AI models”
I love the idea behind OpenCode but compared to managing Claude and Codex, it's such a pain and requires continuous debugging or managing.
Mixed · Oct 2026 · in “OpenCode 2.0”
This is a relatively complex piece of tooling built entirely by Gemma 4 inside OpenCode where I manually intervened maybe only 4 times
Recommends · May 2026 · in “Running local models on an M4 with 24GB memory”
It's not particularly hard to set up OpenCode for your company and plug in one of the myriad inference providers running free models.
Mixed · Jun 2026 · in “OpenAI Losses Increased Nearly 8X in 2025, with Spending Hitting $34B”
you can use opencode with their API gateway (they call it "zen") to get access to all the most popular models using a single account
Recommends · Dec 2025 · in “Getting a Gemini API key is an exercise in frustration”
I use planning mode in opencode. It has a prompt to tell it to plan it out etc. Then I execute with a smaller model. it works well
Recommends · Jun 2026 · in “MiMo-v2.5-Pro-UltraSpeed: 1T model with 1000 tokens per second”
My experience with Opencode using its default model, vs. Github Copilot using its default model, is night and day. One is amazing
Recommends · Jan 2026 · in “Gas Town Decoded”
it does a good job on the whole at having sufficient functionality. But the release pace is blistering and it does feel bloated
Mixed · Jul 2026
OpenCode Go is a smoking deal IMO. You basically get 6x multiplier on the $10 price since you get $60 worth of usage for $10.
Recommends · Jun 2026 · in “GLM-5.2 is the step change for open agents”
I didn’t think I could have found a better solution, spawning multiple subagents with different models is such a great thing.
Recommends · Jul 2026 · in “GPT-5.6”
practically on par with Claude Code and Copilot in terms of being able to do the 80% of things that most people actually use
Recommends · Jun 2026 · in “SpaceX to buy Cursor AI coding agent operator Anysphere for $60B”
I've had opencode go + opencode work reliably, though I'm skeptical of how robust their data security claims are in practice
Mixed · Sep 2026 · in “So you want to use OpenRouter?”
You can get the most value out of a lot of these plans at their second-tier, so it makes sense to arbitrage them like this.
Recommends · Jun 2026 · in “SpaceX to buy Cursor AI coding agent operator Anysphere for $60B”
I've completely replaced GitHub Copilot using Sonnet 3.6 with OpenCode using Qwen3.6 27b, and it's been a great experience.
Recommends · May 2026 · in “Qwen 3.7 Preview”
Opencode and a smart LLM (qwen 3.8-flash-next, deepseek v4 0731 or smarter) do relatively well with this in my experience.
Recommends · Sep 2026 · in “VSCode's SSH Agent Is Bananas (2025)”
With the base usage in Go and pay as you go on cheaper models like MiniMax you can get a lot done for not a lot of coin.
Recommends · Apr 2026 · in “Claude Code refuses requests or charges extra if your commits mention "OpenClaw"”
you can get a lot done for not a lot of coin
Recommends · Apr 2026 · in “Claude Code refuses requests or charges extra if your commits mention "OpenClaw"”
Previous versions of OpenCode started a server which allowed any website visited in a web browser to execute arbitrary commands on the local machine.
Criticizes · Jan 2026 · in “Remote Code Execution in OpenCode, update now”
even when using local models in ollama or lmstudio, prompts are proxied via their domain, so never put anything sensitive even when using local setup
Criticizes · Mar 2026 · in “OpenCode – The open source AI coding agent”
Wish Pi (and Opencode, DeepSeek Harness, Claude, Claude Desktop, Codex Desktop) was written in a memory and performance efficient language.
Criticizes · Oct 2026 · in “Pi 1.0”
A permanently running buggy server on your computer instead of a screen or tmux session is not something that should be a default solution.
Criticizes · Oct 2026 · in “OpenCode 2.0”
Opencode (and other coding agents) have hundreds of open issues reported. It is quite discouraging when they are not being closed/fixed.
Criticizes · May 2026 · in “DeepSeek reasonix, engineered for low token cost during long running sessions”
Having the ability to start OpenCode, give it an issue, add a little extra context, and have the issue completed without writing a single line of code?
Recommends · Jan 2026 · in “Ask HN: Do you have any evidence that agentic coding works?”
I can have opencode discover third party APIs and generate fully working solutions that are well integrated into an existing long-lived codebase.
Recommends · May 2026 · in “The last six months in LLMs in five minutes”
I've started doing this by hand in OpenCode and it works pretty well. But there's no UI support for maintaining a tree of related session forks
Mixed · Jul 2026 · in “Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k”
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.
Recommends · Oct 2026 · in “OpenCode 2.0”
If you care about privacy at all, you can route your Opencode requests through an inference provider that does not retain any logs or data.
Recommends · Jun 2026 · in “Elevated error rate across multiple models”
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.
Recommends · Oct 2026 · in “OpenCode 2.0”
All you need is the source code for your existing project and the claude code/codex/opencode cli and boom, you are ready to ship.
Recommends · Oct 2026 · in “Personal software factories are a waste of time”
You can absolutely still use this to do some basic stuff like tell opencode to convert a video file from one format to another.
Recommends · Jun 2026 · in “Ask HN: Has anyone replaced Claude/GPT with a local model for daily coding?”
Including the date in the system prompt - at the cost of a cache invalidation at midnight - is an entirely reasonable decision.
Recommends · Jul 2026 · in “Stop Using OpenCode”
Counts from 1,795,640 Hacker News comments, Nov 2025 to Nov 2026. How we count · Report a mistake