CLI coding agents
coding agent used from the terminal
anomalyco/opencode anomalyco/opencode is the clear leader by adoption and capability; before choosing an agent, decide whether you need a cloud-backed, one‑command leader or a local/self‑hosted runtime because most alternatives trade off privacy, performance, or tighter IDE/CI/PR workflows.
Which one matches your setup?
Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.
Comparison matrix
Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.
| Runs in | Models | Context | Cost to run | |||||
|---|---|---|---|---|---|---|---|---|
⭐ 203.7k +1621/7d | CLIWeb app | BYOK | Whole-repo analysis | Action gating only | ●●●●● | Cloud APIs (your key) | ●●●●● | Your API key, cloud model costs apply |
⭐ 144.0k +751/7d | PR botCLIIDE | Anthropic | Diff / file only | No noise controls | ●●●●● | Cloud service only | ●●●●● | Anthropic cloud; see docs |
⭐ 121.4k +2002/7d | CLIIDE | OpenAI | Diff/file only | None mentioned | ●●●●● | Cloud (ChatGPT/API) | ●●●●● | Sign in with a ChatGPT plan or use your OpenAI API key |
⭐ 106.8k +86/7d | CLIGitHub ActionCIPR botIDE | GeminiFixed provider | Whole-repo analysis | Config & trusted folders | ●●●●● | Cloud API (your key) | ●●●●● | Free tier (60 req/min, 1,000 req/day); usage-based billing with API key |
⭐ 101.7k +3087/7d | CLI | OpenAIAnthropicGeminiBYOK | Diff + related files | None mentioned | ●●●●● | Self-hostable | ●●●●● | Your API key for cloud models |
⭐ 68.2k +62/7d | CLIIDECoding-agent plugin | BYOKFixed provider | Diff + related files | Basic filters & hooks | ●●●●● | Cloud APIs (your key) | ●●●●● | Your API key, provider billed |
⭐ 67.5k +405/7d | CLIIDEWeb appCICoding-agent plugin | BYOKOpenAIAnthropicGeminiOllama / localFixed provider | Whole-repo analysis | Human-in-loop + rules | ●●●●● | Can run fully local | ●●●●● | Bring-your-own API key or run local models |
⭐ 40.9k +51/7d | CLIWeb appCI | BYOKOpenAIAnthropicOllama / local | Whole-repo analysis | Approvals gating | ●●●●● | Fully local | ●●●●● | Your API key or local models |
⭐ 35.8k +96/7d | CLIIDECoding-agent plugin | Fixed provider | Diff only | None mentioned | ●●●●● | Fixed cloud only | ●●●●● | Free, open-source |
⭐ 35.4k +162/7d | CLIIDECoding-agent plugin | BYOK | Diff + related files | Basic pruning & approvals | ●●●●● | Self-hostable | ●●●●● | Your API key (pay provider) |
⭐ 29.4k +1340/7d | CLIIDECoding-agent pluginPR bot | BYOKOpenAIAnthropicGemini | Whole repo | Severity gating & advisor | ●●●●● | Self-hostable | ●●●●● | Your API key; provider charges may apply |
⭐ 27.9k +146/7d | CLI | BYOKOpenAIAnthropicGeminiOllama / localFixed provider | Whole-repo access | Configurable filters | ●●●●● | Self-hostable | ●●●●● | Hyper subscription (free tier) or your API key |
Capability profiles
Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.
Open-source, installable coding agent that provides both a read-only 'plan' agent for safe exploration and a full-access 'build' agent for edits.
A terminal-first agent that executes routine coding tasks and integrates git workflows, plus @claude GitHub tagging.
A lightweight, local-first terminal coding agent that you can install and run with one command while signing in to ChatGPT or using your OpenAI API key.
Terminal-first access to Gemini 3 with multimodal models, a 1M-token context window, built-in Google Search grounding, and MCP extensibility.
An open-source, self-extensible coding agent harness that bundles a unified multi-provider LLM API, agent runtime, CLI and terminal UI in one project.
A Rust reimplementation of the Codex harness optimized for low-cost models and high-performance Kimi K3 integration.
Provides a unified, extensible SDK + CLI + editor integrations with multi-agent Kanban and real shell command execution for coordinated, project-wide edits.
A single, local-first runtime that supports 30+ hosted providers and local models (vLLM, Ollama) so the model is a component rather than a lock-in.
All repositories (139)
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you co…
An open-source AI agent that brings the power of Gemini directly into your terminal.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement…
Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement…
DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running…
An open-source AI coding agent that lives in your terminal.
Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular ope…
Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for…
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
Open source AI coding agent. Designed for large projects and real world tasks.
Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscrip…
GitHub Copilot CLI brings the power of Copilot coding agent directly to your terminal.
Universal skills loader for AI coding agents - npm i -g openskills
The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | ev…
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI age…
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make…
FuXi is a fast, self-contained AI coding agent that lives in your terminal — edit code, run commands, and driv…
A coding-agent skill for multi-phase security audits with independently verified, machine-readable findings
Agent harness to make your slop code well-engineered and beautiful.
Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~5000 行 TypeScript / Python 从零复现核心架…
AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools
ChatGPT thinks. Codex works. Use ChatGPT as the planning brain while keeping the Codex harness.
Bot that bridges Feishu/Lark messenger with a local Claude Code or Codex CLI. Streaming cards, per-chat sessio…
Antigravity CLI brings the reasoning, execution, and orchestration capabilities of Antigravity agent harness d…
AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude…
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude…
Use ChatGPT Developer Mode as a local coding agent for your repo through MCP.
(BETA) AI shouldn't have a meter. Unlimited tokens. Forever. Your machine. Your agent. Use it from anywhere. T…
Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT fo…
The coding agent that answers to you, your model, your machine, your rules.
Delegate a coding task to a separate coding agent CLI, review the diff, land the commit yourself — one per imp…
Lightweight coding agent written in Rust, optimized for memory footprint and performance
resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor
⚡️ 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, B…
AI-native agent harness for coding workflows by python: multi-model LLM orchestration, stateful sessions, tool…
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance a…
The Bloomberg Terminal for CLI Agents, its Maestro Baby!
600 行 TypeScript 写成的超级迷你版 pi，让你轻松从 0 写出属于你的 pi-agent
Minimal and readable coding agent harness implementation in Python to explain the core components of coding ag…
Empryo issue tracker + SoulForge (v2). Empryo is the graph-powered AI coding agent that edits symbols, not str…
Empryo issue tracker + SoulForge (v2). Empryo is the graph-powered AI coding agent that edits symbols, not str…
OpenCode mobile client via Telegram: run and monitor AI coding tasks from your phone while everything runs loc…
Built by DeepSeek, for DeepSeek — a Swift-native macOS coding agent
A lightweight terminal coding assistant with Claude Code-like workflow, tool loop, and TUI architecture, built…
Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-callin…
Use sidecar next to CLI agents for diffs, file trees, conversation history, and task management with td
Run Claude Code, Codex, and Gemini side by side — each in its own git worktree
Whale — blazingly fast, terminal-first AI coding agent for DeepSeek. ~98% prompt cache hit rate, 1M context, M…
Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.
A minimal autonomous code-agent CLI built with Qwen Code
CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Usin…
33 battle-tested skills + minimal .claude harness for any coding agent (Claude Code, Cursor, Codex, Gemini CLI…
Multi-device terminal server for AI coding agents. Server-side VTE, session persistence, file browser, web pre…
A minimal modern terminal for AI coding experience — Sidebar workspaces; horizontal / vertical split panes; on…
The agent harness for building analytics into your app on top of ClickHouse, Redpanda and other high-performan…
21Agent is an open-source coding agent for Robinhood Chain. Build, debug, deploy, and interact with onchain ap…
Inference-native Tokenmaxxing Agent Harness for Loop Engineering
The AI agent with a wallet — spends USDC autonomously to get real work done. Apache-2.0, TypeScript.
Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — pla…
🗿 FableCodex is a Codex-style coding agent workflow that plans like Fable.
AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verif…
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple…
Easy Code (formerly DeepV Code) — A highly customizable AI coding assistant compatible with all major AI model…
Autonomous AI dev agent in pure Go. Enforced ephemeral subagents keep context small. Getting real work done on…
The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from on…
deepseek标配coding agent、原生支持模型路由、CodeGraph代码图谱、OCR截图识别、自动上下文压缩、最佳工作模式选择，workflow等功能，从根本上节省Token
天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编…
天枢 (Tianshu) 是一个基于harness工程的终端编程智能体运行时（Tui X Gui），针对DeepSeek V4 做了前缀缓存工程优化（长会话实测稳态命中率 97–99%）和深度适配。它跳出了传统 AI 编…
AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man…
Open-source AI coding agent for the terminal. Claude Code-grade accuracy with smart model routing — uses the r…
A CLI tool for logging and analyzing Claude Code and Cursor ai-driven coding session.
OpenCode goal plugin for Codex-style goal mode, /goal slash commands, persistent objectives, and AI coding age…
Wishes in, PRs out. CLI agent that interviews you, plans the work, dispatches parallel agents in isolated work…
Autolith is a self-modifiable general purpose Lisp AI agent
UmaDev: A coding agent that works like a real dev team, commanding the Claude Code / Codex / OpenCode you alre…
Open source, terminal-first AI coding agent with fully transparent multi-model routing. Local (Ollama, LM Stud…
OpenSeek - 广度求索: open-source TUI coding agent with multi-provider routing, MCP, LSP, and Plan/Agent/YOLO modes…
Autonomous agent substrate for Claude Code CLI. Research→Plan→Implement workflows with quality gates, TDD e…
Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality cont…
Control your local Codex sessions remotely through Discord on your phone or browser.
Open-source local AI client and coding agent for DeepSeek, Qwen, ChatGPT and EconomyOS with memory, voice, bro…
Carbon Code 是一款类似 Claude Code 的代码开发工具，也是中国第一个基于 DeepSeek 的代码开发工具，Token 成本节省 90% 以上。它可以实现自动任务拆分、自动开发、MCP 测试，以及与…
FirstCoder is an open-source local coding agent that’s useful enough to run, small enough to read end to end,…
A Claude Code clone CLI - agentic coding assistant in your terminal
Agentic Engineering that actually scales. Run Claude Code, Codex, Gemini and any other CLI Agents in parallel…
Best ready-to-run DeepSeek Harness distribution: DSH desktop GUI, DSH terminal TUI, and harness integration.
Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-host…
AI-native embedded engineering agent — from natural-language requirements to code, build, flash, runtime valid…
AI website cloner for rebuilding live websites with AI coding agents
为 DeepSeek 前缀缓存定制的终端 Code Agent(纯 Go),缓存命中率 95-99%,命中输入定价为未命中的 1/30。A terminal coding agent optimized for Deep…
Cross-platform terminal grid for running Codex, Claude, Gemini, and other CLI agents side by side.
Cross-platform Claude Code desktop client by hwwn. Multi-workspace, remote mobile access, session branching, B…
An Eastern-philosophy-inspired CLI agent harness for personal research and data analysis assistance.
Commander, your AI coding commander centre for all you ai coding cli agents
Uncensored AI coding agent in your terminal. Does the work, skips the sermon. 256K context, crypto-only billin…
🚀 Xenon — Agent Harness for AI coding agents. 证据导向架构 + 7种推理范式 + 执行隔离边界 + SWE-bench 40% 通过率（+6.7pp）。可信、可验证、可评测…
A pure-Go port of pi (earendil-works/pi) — the pi-ai unified multi-provider LLM API, pi-agent-core agent loop,…
A coding-agent CLI and strongly-typed Python library -- self-mutating, hot-swapping, multi-provider, with asyn…
QodeX — a local-first LLM agent & AI coding CLI agent for your terminal. Runs local models (Qwen3-Coder via Ol…
OrbCode CLI — agentic coding in your terminal, powered by Axon models by MatterAI
Hosted alternatives
If running your own reviewer is more ops than you want, these managed services cover the same job.
The Cursor agent outside the editor: a managed terminal agent on the same subscription as the IDE, closed-source and run against Cursor's models instead of a repo you clone and wire up yourself.
Try Cursor CLI →An agentic terminal with the coding agent built into the shell. Subscription-based and managed, so there is no harness to install or model to connect.
Try Warp →Factory's hosted CLI agent aimed at real production work, with model access, tool wiring and org controls handled for you rather than assembled from config.
Try Factory Droid →