Navid MoazzezNavid Moazzez

14 best coding agents GitHub repos to use

Agents that write and ship code. These are the repos behind the terminal and editor agents developers use every day, and the harnesses people build their own on.

Navid Moazzezby Navid Moazzez·Updated Sept 30, 2026·10 min read

Find GitHub repos worth using by topic, language, license and how active they are. Navid's picks come first, and each one opens its own page.

This is a list of the best coding agents GitHub repos.

In fact, it has 14 of them, with Navid's picks first.

So if you want coding agents GitHub repos worth your time, you'll love this list.

Agents that write and ship code. These are the repos behind the terminal and editor agents developers use every day, and the harnesses people build their own on.

Here's what's inside:

Each one comes with what it covers and who it's for.

What are the best coding agents GitHub repos?

Here's the list at a glance.

Owner
Anthropic
Stars
★ 148k
Owner
OpenAI
Stars
★ 127k
Owner
nexu-io
Stars
★ 98k
Owner
rtk-ai
Stars
★ 82k
Owner
openinterpreter
Stars
★ 68k
Owner
aider-ai
Stars
★ 49k
Owner
sickn33
Stars
★ 47k
Owner
esengine
Stars
★ 36k
Owner
alirezarezvani
Stars
★ 26k
Owner
pingdotgg
Stars
★ 24k
Owner
1jehuang
Stars
★ 20k
Owner
agavra
Stars
★ 3.2k
Owner
git-ai-project
Stars
★ 2.8k
Owner
Agent-Field
Stars
★ 640

Top 14 coding agents GitHub repos

1. Claude Code by Anthropic

[![npm]](https://www.npmjs.com/package/@anthropic-ai/claude-code)

[npm]: https://img.shields.io/npm/v/@anthropic-ai/claude-code.svg?style=flat-square

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows, all through natural language commands. Use it in your terminal, IDE, or tag @claude on Github.

Stars: 148k

Language: TypeScript

Install:

bash curl -fsSL https://claude.ai/install.sh | bash 

View Claude Code on GitHub · More about Claude Code

2. Codex by OpenAI

Codex CLI is a coding agent from OpenAI that runs locally on your computer.

If you want Codex in your code editor (VS Code, Cursor, Windsurf), install in your IDE. If you want the desktop app experience, run codex app or visit the Codex App page. If you are looking for the cloud-based agent from OpenAI, Codex Web, go to chatgpt.com/codex.

The standalone installers download from https://releases.openai.com/codex by default and fall back to GitHub Releases if a metadata or asset download is unavailable. To force GitHub Releases, set CODEXINSTALLERUSERELEASESOPENAICOM to false (0 and no are also accepted):

Stars: 127k

Language: Rust

License: Apache-2.0

Install:

bash curl -fsSL https://chatgpt.com/codex/install.sh | sh 

View Codex on GitHub · More about Codex

3. Open Design by nexu-io

Open Design Cloud, the official model service. One recharge to use GPT, Claude, Gemini, and DeepSeek inside Open Design: 20+ flagship models, zero config, billed by real token usage. Try Open Design Cloud

The Open Design Fellow program is now open. If you also believe design should be open, become an Open Design Fellow, shape the product alongside the core team, and help more people take part in defining the future of design. Details MAINTAINERS.md and Discord.

The open-source Claude Design alternative.   Local-first native desktop app for macOS and Windows.   Composable skills, brand-grade DESIGN.md design systems, and ready-to-use plugins.   Generates web · desktop · mobile prototypes, live dashboards / artifacts, decks, images, video, plus HyperFrames motion graphics. Sandboxed iframe preview · HTML / PDF / PPTX / MP4 export.   Runs on Claude Code · OpenClaw · Codex · Cursor · OpenCode · Qwen · Copilot · Amp · Hermes · Kimi · Antigravity and 25 distinct local CLI executables, or any OpenAI-compatible endpoint via BYOK.

Stars: 98k

Language: TypeScript

License: Apache-2.0

Install:

bash curl -fsSL https://open-design.ai/install.sh | sh -s <agent> 

View Open Design on GitHub · More about Open Design

4. Rtk by rtk-ai

rtk filters and compresses command outputs before they reach your LLM context. Single Rust binary, 100+ supported commands, Full explanation: How RTK Savings Work

Download from releases: macOS: rtk-x8664-apple-darwin.tar.gz / rtk-aarch64-apple-darwin.tar.gz Linux: rtk-x8664-unknown-linux-musl.tar.gz / rtk-aarch64-unknown-linux-gnu.tar.gz Windows: rtk-x8664-pc-windows-msvc.zip

Windows users: Extract the zip and place rtk.exe somewhere in your PATH (e.g. C:\Users\\.local\bin). Run RTK from Command Prompt, PowerShell, or Windows Terminal, do not double-click the.exe (it will flash and close). The full hook system works natively on Windows (and in WSL). See Windows setup below for details.

Stars: 82k

Language: Rust

License: Apache-2.0

Install:

bash brew install rtk 

View Rtk on GitHub · More about Rtk

5. Openinterpreter by openinterpreter

Today: Kimi K3 is here. We have reimplemented the provider-recommended Kimi Code harness in Rust, giving you maximum K3 performance with a Codex-like interface. Kimi Docs

Then type i or interpreter in your terminal to start a session.

Open Interpreter is a fork of OpenAI's Codex, with a focus on emulating the agent harness that gets the best performance out of low-cost models.

Stars: 68k

Language: Rust

License: Apache-2.0

Install:

bash curl -fsSL https://www.openinterpreter.com/install | sh 

View Openinterpreter on GitHub · More about Openinterpreter

6. Aider by aider-ai

Aider lets you pair program with LLMs to start a new project or build on your existing codebase.

Aider works best with Claude 3.7 Sonnet, DeepSeek R1 & Chat V3, OpenAI o1, o3-mini & GPT-4o, but can connect to almost any LLM, including local models.

Aider makes a map of your entire codebase, which helps it work well in larger projects.

Stars: 49k

Language: Python

License: Apache-2.0

View Aider on GitHub · More about Aider

7. Agentic Awesome Skills by sickn33

Local, agent-owned skill stacks for coding agents, from complete catalog access to a reproducible, reviewable plan.

Current release: V15.13.0. This release includes AAS Core for complete local catalog search, agent-owned selection, manifest validation, planning, and diagnosis. Apply and recovery remain experimental and outside the supported preview path.

Codex or Claude inspects your project and chooses exact skills from the complete local AAS catalog. AAS Core does not rank or recommend them: its read-only composestack tool validates the agent-owned selection in memory, and a client or the aas CLI can persist it as aas-stack.json and produce an immutable plan before any target change.

Stars: 47k

Language: Python

License: MIT

Install:

bash npx agentic-awesome-skills --agy 

View Agentic Awesome Skills on GitHub · More about Agentic Awesome Skills

8. DeepSeek Reasonix by esengine

Open source · MIT · a single Go binary A coding agent you can leave running. One local engine, four ways in, terminal, desktop app, browser, or your editor over ACP. Plan mode, permissions, a workspace sandbox and per-turn checkpoints keep a long autonomous run something you can still read and undo.

[!IMPORTANT] Community · 加入社区, bilingual Discord for setup help (#help / #求助), workflow showcases, and feature ideas. Config-driven. Providers, the agent, enabled tools, and plugins are all declared in reasonix.toml. No hardcoded models. Multi-model & composable. DeepSeek ships as a preset; any OpenAI-compatible endpoint is a config entry, not new code. Optionally run two models together (executor + planner) in separate, cache-stable sessions. Plugin-driven. MCP servers contribute tools, prompts, and resources; Extension Protocol v1 sidecars can also intercept runtime events, contribute Providers and structured UI, and ship versioned plugin packages. Cache-aware context maintenance. Startup injects a small stable environment summary, stale tool output is snipped/pruned before summary compaction, and the built-in tool schema contract is documented for regression review. Zero-friction distribution. CGOENABLED=0 single binary; cross-compile to six targets with one command. The result is a fully self-contained static binary, nothing to install on the target machine beyond the binary itself.

Choose the path that matches how you want to use Reasonix. The CLI/TUI, desktop app, and VS Code extension all use the same local Reasonix engine.

Stars: 36k

Language: Go

License: MIT

Install:

bash npm i -g reasonix # any OS; pulls the prebuilt native binary 

View DeepSeek Reasonix on GitHub · More about DeepSeek Reasonix

9. Claude Skills by alirezarezvani

362 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools.

5,200+ GitHub stars, the most comprehensive open-source Claude Code skills & agent plugins library.

Claude Code skills (also called agent skills or coding agent plugins) are modular instruction packages that give AI coding agents domain expertise they don't have out of the box. Each skill includes: SKILL.md, structured instructions, workflows, and decision frameworks Python tools, 644 CLI scripts (all stdlib-only, zero pip installs) Reference docs, 741 templates, checklists, and domain-specific knowledge files

Stars: 26k

Language: Python

License: MIT

Install:

bash git clone https://github.com/alirezarezvani/claude-skills.git

View Claude Skills on GitHub · More about Claude Skills

10. T3 Code by pingdotgg

T3 Code is an "agent harness control surface". It enables control of the agents on your machine with a best-in-class mobile app (iOS, Android), web app and Electron-based desktop app.

Works with your subscriptions on Claude Code, Codex, Cursor, Grok Build, and OpenCode. If they're set up on your computer, T3 Code can control them.

Nothing. We built T3 Code because we wanted the best possible development experience with agents. We were inspired by existing solutions like the Codex desktop app, Conductor, Claude Desktop and Cursor Glass, but none met our bar.

Stars: 24k

Language: TypeScript

License: MIT

Install:

bash npx t3@latest 

View T3 Code on GitHub · More about T3 Code

11. jcode by 1jehuang

Need Homebrew, source builds, provider setup, or want an agent to set it up for you? Jump to detailed installation.

jcode is built to be as performant and resource efficient as possible. Every metric is optimized to the bone, which is important for scaling multi-session workflows. Here we sample a few metrics to show the difference: RAM usage and boot up.

Tool Time to first frame Range Comparison ------:---:---: jcode 14.0 ms 10.1, 19.3 ms baseline Antigravity CLI 383.5 ms 363.1, 415.4 ms 27.4× slower pi 590.7 ms 369.6, 934.8 ms 42.2× slower Codex CLI 882.8 ms 742.3, 1640.9 ms 63.1× slower OpenCode 1035.9 ms 922.5, 1104.4 ms 74.0× slower GitHub Copilot CLI 1518.6 ms 1357.4, 1826.8 ms 108.5× slower Cursor Agent 1949.7 ms 1711.0, 2104.8 ms 139.3× slower Claude Code 3436.9 ms 2032.7, 8927.2 ms 245.5× slower

Stars: 20k

Language: Rust

License: MIT

Install:

bash brew tap 1jehuang/jcode 

View jcode on GitHub · More about jcode

12. tuicr by agavra

A code review TUI with vim keybindings. Export to GitHub, GitLab, Bitbucket, or clipboard.

[!TIP] Pronounced "tweaker". GitHub-style continuous diff in the terminal. Scroll through every changed file in one stream. PR-style comments at the line, range, file, and review level. Review tracking at file or hunk granularity, persisted across sessions. Three export targets: push a real review to GitHub, GitLab, or Bitbucket, copy structured markdown to your clipboard, or pipe to stdout. Works with git, jj, and mercurial. Reviews uncommitted changes, commit ranges, or any GitHub PR, GitLab MR, or Bitbucket PR.

tuicr update uses Homebrew, Cargo, Mise, or a Nix profile when that manager owns the executable. Install-script and manually downloaded binaries update in place from the matching GitHub release asset after SHA-256 verification. Exact-version installs support Cargo and direct binaries; use the package manager's pinning workflow for Homebrew, Mise, or Nix. A nix run invocation is temporary rather than installed; rerun it to use the current flake, or use nix profile install github:agavra/tuicr for an installation that tuicr update can upgrade.

Stars: 3.2k

Language: Rust

License: MIT

Install:

bash curl -fsSL tuicr.dev/install.sh | sh 

View tuicr on GitHub · More about tuicr

13. Git AI by git-ai-project

Git AI is an open source git extension that tracks the AI-generated code in your repositories. After installing the extension, every line of AI code is linked to the agent, model, and prompts that generated it, so you never lose the intent, requirements, and architecture decisions behind your code.

No per-repo setup or git hooks required. Commit with the Agent, git, or your favorite git client. Attribution will be linked to commits automatically.

The Git AI standard is supported by: Add an Agent Transparent, Git AI requires no workflow changes. Just prompt and commit as you normally would and Git AI automatically attaches attribution metadata to every commit. No performance overhead, Git AI does not rely on Git Hooks (slow + difficult to set up in every repo) and it does not wrap the Git binary. Your Git operations are just as fast as they were before Git AI was installed. Local-first, Works offline, no login required. Secure Prompt Storage, Git AI links each line of AI-code back to the prompt that generated it. These sessions are scanned and redacted, and saved outside of Git -- keeping repos lean, enabling fine-grained access control, and preventing PII or secrets from leaking. Git native and open standard, Git AI built the open standard for tracking AI-generated code with Git Notes.

Stars: 2.8k

Language: Rust

License: Apache-2.0

Install:

bash curl -sSL https://usegitai.com/install.sh | bash 

View Git AI on GitHub · More about Git AI

14. Pr Af by Agent-Field

PR-AF is the #1 open-source code reviewer on Martian Code-Review-Bench. It is built for deep code review, not shallow diff summaries: turn each PR into a task-specific review plan, spawn focused reviewer agents, ground findings in code evidence, challenge the results, and squeeze more useful review intelligence out of cheaper models. Run DeepSeek-class models for routine PRs, GLM-5.2 for deep open-model reviews, or Opus-class frontier models for major PRs, where PR-AF tops the benchmark by a wide margin.

On the 38 runnable Martian Code-Review-Bench PRs, PR-AF with GLM-5.2 is the #1 open-source reviewer in golden recall: 0.706 across 42 compared tools. It is ahead of cubic-v2 and every qodo, coderabbit, greptile, copilot, and devin variant in this snapshot.

strength result ------ Known bug recall 0.706 golden recall, #1 open source across 42 compared tools. More real issues found 595 independently valid findings, ~3× more than the leading commercial tools in the adjusted comparison. Open + reproducible Single open model (GLM-5.2), public results, per-PR judge verdicts, and reproduction scripts. Self-hosted API Run locally with Docker; trigger reviews by CLI, curl, CI, or other agents. Model-flexible Use cheaper models for regular PRs, GLM-5.2 for open-model CI gates, and Opus-class frontier models for highest-stakes reviews. Frontier ceiling With Opus-class commercial models, PR-AF tops the benchmark by a wide margin. Cost position About 10× cheaper per review than closed-source tools.

Stars: 640

Language: Go

Install:

bash git clone https://github.com/Agent-Field/pr-af

View Pr Af on GitHub · More about Pr Af

Final thoughts on coding agents GitHub repos

The best coding agents repo is the one you come back to. Pick 2 or 3 from this list, give them a month, and keep the ones you look forward to.

Navid Moazzez

AI business strategist & AI OS builder

Navid Moazzez helps creators and founders master AI and build their own AI Operating System (AI OS) to automate their business and life.

Navid.me is reader-supported. When you buy through links on this site, I may earn an affiliate commission. Learn more.

More GitHub repos

More free tools

Related MCP servers & CLIs

Free AI newsletter

The most actionable AI newsletter for founders

Every week, get proven AI strategies, curated tools, and step-by-step systems to grow your audience, create better content, and build a profitable creator business.

No fluff, no filler, no BS. Just five minutes each week that might level up your online business and life.

P.S. Sign up now to get free access to my ultimate AI tools guide for creators.

Loved by 10,000+ readers