# Coding Agents

> AI agents that write, review, refactor, and ship code autonomously or as pair programmers.

Coding agents span in-editor pair programmers that autocomplete and refactor, terminal agents that run commands and edit files, and autonomous engineers that take a ticket and open a pull request. Pick based on where it runs — your IDE, the command line, or the cloud — how much autonomy you want it to have, and how cleanly it fits your existing codebase, tests, and review process. The most important axis is the trust boundary: an in-editor assistant keeps a human on every keystroke, while an autonomous agent needs sandboxing, guardrails, and a disciplined diff-review habit before you let it touch a real repository. Evaluate language and framework coverage on your actual stack, how well it pulls context from the wider codebase, and whether it can run your tests and iterate on failures rather than guessing once. Pricing is usually a per-seat subscription, sometimes with usage-based limits on the underlying model; a few capable options are open source and self-hostable if you want to bring your own keys and keep code in-house. Public benchmarks are a weak proxy here — the real test is a week on your own code, watching how often you accept output unedited and how much review overhead it adds. A tool that writes plausible code you can't trust is slower than no tool at all.

37 tools indexed. Sponsored placements are labeled and never ranked; open-source ordering reflects real GitHub adoption. Browse on the web: https://agentsearchengine.app/category/coding-agents

## Commercial products (alphabetical — stars don't measure commercial adoption)
- [Claude Code](https://agentsearchengine.app/agents/claude-code) — Anthropic's agentic coding tool that works in your terminal, IDE, and CI. · Paid product · Agent · best for developers who want an agentic coding tool in the terminal, ide, and ci that works against existing repositories
- [Cursor](https://agentsearchengine.app/agents/cursor) — AI-first code editor with agent mode for multi-file edits and background tasks. · Freemium · Agent · best for teams that want an ai-native ide with agent mode, multi-file edits, and background tasks in a familiar vs code feel
- [Devin](https://agentsearchengine.app/agents/devin) — Autonomous AI software engineer by Cognition that plans, codes, and ships end-to-end. · Paid product · Agent · best for delegating whole engineering tickets to a cloud agent that plans, codes, tests, and opens prs autonomously
- [GitHub Copilot](https://agentsearchengine.app/agents/github-copilot) — GitHub's AI pair programmer with an autonomous coding agent for issues and PRs. · Freemium · Agent · best for developers who live in github and want inline completion plus an autonomous agent for issues and prs
- [OpenAI Codex](https://agentsearchengine.app/agents/openai-codex) — OpenAI's cloud software engineering agent that works on many tasks in parallel. · Paid product · Agent · best for running many delegated engineering tasks in parallel in the cloud
- [Replit Agent](https://agentsearchengine.app/agents/replit-agent) — Builds and deploys full apps from natural-language prompts inside Replit. · Freemium · Agent · best for building and deploying full apps from prompts without managing a local dev environment
- [Windsurf](https://agentsearchengine.app/agents/windsurf) — Agentic IDE with Cascade flows that keep full context of your codebase. · Freemium · Agent · best for developers who want an agentic ide with strong codebase-context flows at a competitive price

## Open-source index (ranked by adoption)
1. [gemini-cli](https://agentsearchengine.app/agents/gemini-cli) — An open-source AI agent that brings the power of Gemini directly into your terminal. · Open source · Agent · 106k★ · TypeScript · Apache-2.0 · active today · best for terminal-native coding assistance with direct access to google's gemini models
2. [openinterpreter](https://agentsearchengine.app/agents/openinterpreter) — A lightweight coding agent for open models like Deepseek, Kimi, and Qwen · Open source · Agent · 68k★ · Rust · Apache-2.0 · active 1 day ago · best for running a lightweight, open-source coding agent locally with open models
3. [jcode](https://agentsearchengine.app/agents/jcode) — Coding Agent Harness · Open source · Agent · 15k★ · Rust · MIT · active today
4. [Skill_Seekers](https://agentsearchengine.app/agents/skill-seekers) — Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection · Open source · SDK / library · 15k★ · Python · MIT · active today · best for turning documentation sites into reusable claude code skills
5. [openevolve](https://agentsearchengine.app/agents/openevolve) — Open-source implementation of AlphaEvolve · Open source · Agent · 6.8k★ · Python · Apache-2.0 · active 16 days ago
6. [semble](https://agentsearchengine.app/agents/semble) — Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read · Open source · SDK / library · 5.8k★ · Python · MIT · active 2 days ago
7. [agents-cli](https://agentsearchengine.app/agents/agents-cli) — The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud. · Open source · Agent · 5.5k★ · Python · Apache-2.0 · active 11 days ago
8. [vibesdk](https://agentsearchengine.app/agents/vibesdk) — An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack · Open source · Platform · 5.2k★ · TypeScript · MIT · active 3 days ago
9. [MonkeyCode](https://agentsearchengine.app/agents/monkeycode) — AI coding platform for teams · Open source · Platform · 4.1k★ · TypeScript · AGPL-3.0 · active today
10. [command-code](https://agentsearchengine.app/agents/command-code) — Command Code AI · Open source · Agent · 3.6k★ · active 1 month ago
11. [grok-cli](https://agentsearchengine.app/agents/grok-cli) — An open-source coding agent for the Grok API · Open source · Agent · 3.4k★ · TypeScript · MIT · active 28 days ago
12. [claude_codex_bridge](https://agentsearchengine.app/agents/claude-codex-bridge) — Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents · Open source · Agent · 3.4k★ · Python · active today
13. [teaql-agent-kit](https://agentsearchengine.app/agents/teaql-agent-kit) — Deterministic execution for non-deterministic AI. · Open source · SDK / library · 2.8k★ · Python · MIT · active 1 day ago
14. [cocoindex-code](https://agentsearchengine.app/agents/cocoindex-code) — A super light-weight embedded code search engine CLI (AST based) that just works - saves 70% token and improves speed for coding agent Star if you like it! · Open source · SDK / library · 2.6k★ · Python · Apache-2.0 · active 1 day ago
15. [HolyClaude](https://agentsearchengine.app/agents/holyclaude) — AI coding workstation: Claude Code + web UI + 8 AI CLIs + headless browser + 50+ tools · Open source · Agent · 2.5k★ · JavaScript · MIT · active 1 day ago
16. [little-coder](https://agentsearchengine.app/agents/little-coder) — A harness optimized to smaller LLMs · Open source · Agent · 2.2k★ · TypeScript · Apache-2.0 · active 3 days ago
17. [ORG2](https://agentsearchengine.app/agents/org2) — Open-source Cursor-style agent IDE — but built for reviewability and control. Built-in rust harness; supports 10+ CLIs. · Open source · Agent · 2.2k★ · TypeScript · AGPL-3.0 · active today
18. [open-cowork](https://agentsearchengine.app/agents/open-cowork) — Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration. · Open source · Agent · 2.0k★ · TypeScript · MIT · active 3 days ago
19. [CoreCoder](https://agentsearchengine.app/agents/corecoder) — Minimal AI coding agent (~1,000 lines of Python) inspired by Claude Code. Works with any LLM. Think NanoGPT for coding agents. Formerly NanoCoder. · Open source · Agent · 1.6k★ · Python · MIT · active 1 month ago
20. [zerostack](https://agentsearchengine.app/agents/zerostack) — Lightweight coding agent written in Rust, optimized for memory footprint and performance · Open source · Agent · 1.5k★ · Rust · GPL-3.0 · active 1 day ago
21. [cli-continues](https://agentsearchengine.app/agents/cli-continues) — resume any AI coding session in another tool — Claude Code, Copilot, Gemini, Codex, Cursor · Open source · SDK / library · 1.4k★ · TypeScript · MIT · active 2 months ago
22. [10x](https://agentsearchengine.app/agents/10x) — 10x - Up to 20x faster AI coding with multi-step Superpowers. Open-source agent with smart model routing, BYOK, fully self-hosted. · Open source · Agent · 1.4k★ · TypeScript · MIT · active 6 months ago
23. [dao-code](https://agentsearchengine.app/agents/dao-code) — Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so · Open source · Agent · 1.3k★ · TypeScript · MIT · active 1 day ago
24. [vibecode-pro-max-kit](https://agentsearchengine.app/agents/vibecode-pro-max-kit) — Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders — self-improving context memory, 15 agents, 33 skills working with /goal, · Open source · Agent · 1.1k★ · JavaScript · MIT · active 1 month ago
25. [spec_driven_develop](https://agentsearchengine.app/agents/spec-driven-develop) — Spec-driven development workflow for AI coding agents: architecture-first planning, task decomposition, GitHub Issue/PR tracking, Deep Discuss, and adaptive control for Claude Code, Codex, Cursor, · Open source · Agent · 955★ · Python · MIT · active 8 days ago
26. [UnrealClaude](https://agentsearchengine.app/agents/unrealclaude) — Claude Code CLI integration for Unreal Engine 5.7 - Get AI coding assistance with built-in UE5.7 documentation context directly in the editor. · Open source · Agent · 875★ · C++ · active 1 month ago
27. [ai-maestro](https://agentsearchengine.app/agents/ai-maestro) — AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. · Open source · Framework · 738★ · TypeScript · MIT · active 3 days ago
28. [openyak](https://agentsearchengine.app/agents/openyak) — Open-source local-first AI agent for desktop work. No account, no telemetry: use local models with Ollama/Rapid-MLX or bring your own provider key. · Open source · Agent · 700★ · Python · Apache-2.0 · active 2 days ago
29. [ospec](https://agentsearchengine.app/agents/ospec) — Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. · Open source · Framework · 524★ · JavaScript · MIT · active 5 days ago
30. [Async](https://agentsearchengine.app/agents/async) — IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience. · Open source · Agent · 474★ · TypeScript · Apache-2.0 · active 2 months ago

## Frequently asked
**What is a coding agent?**
A coding agent is an AI that writes, edits, reviews, or ships code — either as a real-time assistant in your editor or as an autonomous agent that completes whole tasks.

**What's the best coding agent?**
It depends on your workflow: editor-integrated tools suit day-to-day pair programming, autonomous agents suit delegating self-contained tasks. Compare language support, autonomy, and review fit.

**Are there open-source coding agents?**
Yes — several capable coding agents are open source and self-hostable, alongside the commercial subscription products.

---
Source: [Agent Search Engine](https://agentsearchengine.app). Full directory in one file: https://agentsearchengine.app/llms-full.txt