@vicky_grok: You're paying $20/month for a coding agent that runs one model. Here's a free one that runs any of them. The coding-age…
Summary
An open-source coding agent called opencode has rapidly gained popularity as a free alternative to paid AI coding tools, offering support for multiple models and a strong community-driven development.
View Cached Full Text
Cached at: 08/24/26, 01:46 AM
You’re paying $20/month for a coding agent that runs one model. Here’s a free one that runs any of them.
The coding-agent space consolidated fast in 2025, and most of the winners are closed source. GitHub Copilot, Cursor, Claude Code, Zed’s AI — all subscription products.
Meanwhile a fork of an abandoned MIT-licensed project quietly crossed 200,000 stars.
anomalyco/opencode — the open source coding agent — is 14.6× the size of the project it forked from (opencode-ai/opencode, archived at 13.7k stars in September 2025). It’s shipping a release every 2-3 days. Latest is v1.18.21 from two days ago.
Three things about it are worth attention if you’re evaluating tooling for your team:
-
Two agents, one keybinding. opencode ships with two built-in agents: build (full file access, can edit and run commands) and plan (read-only, asks permission before touching anything). Tab swaps between them mid-session with no context loss. In practice this means you can plan a refactor in read-only mode, then flip to build mode to execute — same conversation, same working memory, no re-prompting. I haven’t seen another agent implement this pattern cleanly.
-
Provider-agnostic by default. 75+ model providers supported. Local Ollama, Claude, GPT-5, DeepSeek V3, Qwen3-Coder, all first-class. Your model choice is a config line, not a lock-in. For teams that already have a preferred provider or a compliance requirement, this matters.
-
Community depth is real. The README ships in 22 languages — Bengali, Ukrainian, Bosnian, Thai, Norwegian, all community PRs. Discord has active daily contributors. 25,897 forks. This is the kind of adoption curve that predicts long-term maintenance, not short-term hype.
Tradeoffs worth naming honestly:
Terminal-first. If your workflow is deep in VS Code or JetBrains, Cline or Continue may fit better. No official SLA — it’s a community project. Enterprise teams should factor that in. The docs are catching up to the shipping cadence. Some newer flags land in the release notes before the docs page. The benchmark ask: If you or your team have run opencode against Claude Code, Aider, or Cursor on real workloads — same tasks, same models where possible — I’d like to hear how the numbers actually shook out. Reply or DM. Not looking for opinions; looking for latency, token-per-task, and success-rate deltas on tasks that matter to you.
Repo: http://github.com/anomalyco/opencode… Install: npm i -g opencode-ai
anomalyco/opencode
Source: https://github.com/anomalyco/opencode
The open source AI coding agent.
English | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Dansk | 日本語 | Polski | Русский | Bosanski | العربية | Norsk | Português (Brasil) | ไทย | Türkçe | Українська | বাংলা | Ελληνικά | Tiếng Việt
Installation
# YOLO
curl -fsSL https://opencode.ai/install | bash
# Package managers
npm i -g opencode-ai@latest # or bun/pnpm/yarn
scoop install opencode # Windows
choco install opencode # Windows
brew install anomalyco/tap/opencode # macOS and Linux (recommended, always up to date)
brew install opencode # macOS and Linux (official brew formula, updated less)
sudo pacman -S opencode # Arch Linux (Stable)
paru -S opencode-bin # Arch Linux (Latest from AUR)
mise use -g opencode # Any OS
nix run nixpkgs#opencode # or github:anomalyco/opencode for latest dev branch
Remove versions older than 0.1.x before installing.
Desktop App (BETA)
OpenCode is also available as a desktop application. Download directly from the releases page or opencode.ai/download.
| Platform | Download |
|---|---|
| macOS (Apple Silicon) | opencode-desktop-mac-arm64.dmg |
| macOS (Intel) | opencode-desktop-mac-x64.dmg |
| Windows | opencode-desktop-windows-x64.exe |
| Linux | .deb, .rpm, or .AppImage |
# macOS (Homebrew)
brew install --cask opencode-desktop
# Windows (Scoop)
scoop bucket add extras; scoop install extras/opencode-desktop
Installation Directory
The install script respects the following priority order for the installation path:
$OPENCODE_INSTALL_DIR- Custom installation directory$XDG_BIN_DIR- XDG Base Directory Specification compliant path$HOME/bin- Standard user binary directory (if it exists or can be created)$HOME/.opencode/bin- Default fallback
# Examples
OPENCODE_INSTALL_DIR=/usr/local/bin curl -fsSL https://opencode.ai/install | bash
XDG_BIN_DIR=$HOME/.local/bin curl -fsSL https://opencode.ai/install | bash
Agents
OpenCode includes two built-in agents you can switch between with the Tab key.
- build - Default, full-access agent for development work
- plan - Read-only agent for analysis and code exploration
- Denies file edits by default
- Asks permission before running bash commands
- Ideal for exploring unfamiliar codebases or planning changes
Also included is a general subagent for complex searches and multistep tasks.
This is used internally and can be invoked using @general in messages.
Learn more about agents.
Documentation
For more info on how to configure OpenCode, head over to our docs.
Contributing
If you’re interested in contributing to OpenCode, please read our contributing docs before submitting a pull request.
Building on OpenCode
If you are working on a project that’s related to OpenCode and is using “opencode” as part of its name, for example “opencode-dashboard” or “opencode-mobile”, please add a note to your README to clarify that it is not built by the OpenCode team and is not affiliated with us in any way.
Similar Articles
@KevinNaughtonJr: it says opencode - the best open source AI coding agent it says opencode - a product with 7.5M monthly users it says op…
OpenCode is promoted as the best open-source AI coding agent with 7.5 million monthly users, 165,000 GitHub stars, and a company with a single bald employee.
I benchmarked 8 AI coding agents on the same project. Results: one production-ready out of four, total cost $1.94.
A benchmark of 8 AI coding agents on building a VPS management toolkit found that only one of four implementations was production-ready, with a total cost of $1.94 and a 1:28 ratio between planning and code costs.
@jahooma: Introducing a 100% free coding agent with DeepSeek v4 Pro Choose any model, all free: - DeepSeek v4 Pro/Flash - Kimi K2…
Introducing a free coding agent tool called 'freebuff' that provides access to multiple AI models like DeepSeek v4 Pro and Kimi K2.6 via an npm package.
Coding agents are quietly shifting from "pick our model, use our cloud" to "bring any model, run it yourself" and it feels like a real inflection
An analysis of the shift in AI coding tools from vendor-locked, cloud-dependent models (e.g., Cursor, Copilot) to provider-agnostic, local-first alternatives (e.g., Zero), suggesting inference is becoming a commodity similar to storage or compute.
@vista8: The AI coding tool I use most often right now is Codex. But its front-end design taste is awful. I found an OpenCodex project that lets you switch your Codex to non-OpenAI models anytime — like Kimi K3 (OAuth), Grok 4.5 (OAuth), GLM 5.…
Introducing the OpenCodex project, which allows the AI coding tool Codex to switch to non-OpenAI models (such as Kimi K3, Grok 4.5, GLM 5.2, etc.) at any time, improving front-end design flexibility.
