Coding agents & developer tools
Autonomous coding agents
4,327 agents · most starred first
Autonomous coding agents, page 6 of 44
AI agent that is compatible with multiple LLM models
AI agent that is compatible with multiple LLM models
Build a Claude Code–like CLI coding agent from scratch.
Empowering users.
gguf ruvltra claude-code code-generation sona adaptive-learning
Salesforce codegen with web server
An LLM-powered, autonomous coding assistant. Also offers an MCP and ACP mode.
transformers safetensors gguf stablelm text-generation causal-lm
Akari 是一个面向开发者团队的 AI Agent 并行开发管理平台。它基于 Git worktree 为每个会话创建完全隔离的工作区,让你能够同时启动多个 Agent(Claude Code、Kimi、Aider、Shell 等),通过统一界面查看状态、终端输出、代码 Diff,并在任务完成后统一 Review、合并回主干。
All your coding agents, in one place. Claude Code, Codex, Copilot and more, side by side in your terminal.
Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model, by re-engineering the agent.
A Swift reimplementation of a Claude Code-style coding agent, built stage by stage to explore what makes coding agents work
Terminal-first AI assistant for software engineering tasks (inspired by Claude Code v2.0.67)
Git worktree-based task manager with integrated terminals for CLI coding agents
Open-source AI-powered terminal agent. Built in Go.
Desktop GUI for the omp coding agent: parallel sessions, visual tool calls, model/provider management, and usage analytics.
AI-powered CLI coding agent with 20+ built-in tools, MCP support, and multi-model providers
One file. Under 200 lines. Zero dependencies. It's a coding agent.
transformers gguf unsloth qwen3 qwen text-generation
A Claude Code clone CLI - agentic coding assistant in your terminal
The older sister of Claude Code - useful for learning harness engineering
Local AI coding orchestration for repo-scale work: LLM-council planning, Ralph-loop recovery, isolated OpenCode worktrees, and human-gated PR delivery.
The native agentic development platform for the Mac: a 5 MB terminal that runs fleets of Claude Code and Codex sessions side by side, each on its own branch. Built with SwiftUI, no Electron, no telemetry.
transformers pytorch safetensors llama text-generation llama-2
A repository that ships its own code. AI workflows triage issues, implement them, review, and auto-merge with no human reading the diff. Runs on Archon. The app it maintains is a cited RAG chat over YouTube transcripts, live at chat.dynamous.ai.
Open-source terminal coding agent and SDK. Bring your own key for 25+ providers or a local model, with sandboxed subagents. Part of Directionally Local.
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.
Rust port of the pi agent harness — coding agent + LLM runtime stack
mini-claude-code: a simplified Java Claude Code agent distilling core Agent Harness mechanisms. Features: Agent Loop, tools, permission control, Hooks, Todo, Subagent, Skill Loading, context compression, memory, tasks, background tasks, scheduling, multi-agent collaboration, team protocol, autonomous claiming, MCP Plugin.
RAM efficient terminal agent harness for coding, cybersecurity, and automation.
An autonomous AI agentic harness built to code anything, automate terminals, perform cybersecurity tasks, and execute complex real-world workflows with minimal human intervention. From writing and debugging code to analyzing systems, managing files, running commands, and orchestrating tools, Agent-2 turns simple prompts into autonomous execution.
The ADE (agentic development environment) for running a team of coding agents: start a job with a chat, answer what needs you with the evidence, and build apps and dashboards over your data in a chat.
Terminal agent for coding and authorized security workflows with Anthropic, OpenAI, and Gemini support.
Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built into the app.
A conversational semi-autonomous developer assistant. AI pair programming without the copypasta.
Hatice is an autonomous coding agent orchestration system.
A goal-specification file for autonomous coding agents. Generalizes Karpathy's autoresearch to domains with constructed metrics.
One Developer. An Entire Fleet of Autonomous Coding Agents. Local-first desktop agent workbench built on Electron + pi.
Open-source VS Code AI agent that combines the best of Roo Code, Cline and kilo code, with advanced AI capabilities, multi-model support, and seamless development workflow integration.
🦊 Desktop-first code editor built with Flutter, providing GPU-accelerated rendering and a smooth editing experience.
Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.
JanusX — open-source AI-coding workspace: worktree parallel dev, split terminals for Claude/Codex/OpenCode/Pi, checkpoints with diff-restore, Blueprint+Island. Second test Oct 20 in progress (not v1.0) | 开源AI编程桌面:多分支并行、分屏终端、还原点、蓝图,10.20二测中
A local-first multi-agent app development platform, built on PenguinHarness
A local-first coding agent that works in your repository and leaves reviewable changes
A Swift reimplementation of a Claude Code-style coding agent, built stage by stage to explore what makes coding agents work
Orbit is a native desktop workbench for the pi coding agent — a chat-style GUI rendered entirely in Rust on GPUI, the GPU-accelerated UI framework Zed is built on. It speaks the pi CLI's RPC protocol directly over stdio: no browser, no webview, no Node.
Glowby lets you build production-ready software with coding agents.
用Java编写一个ai智能体,从0完整实现一个Claude Code
AI Coding assistant for large and complex codebases.
Build an AI agent harness in Rust, from a minimal loop to tools, subagents, memory, teams, worktrees, MCP, and typed tool routing.
The solo founder's AI engineering stack. Fork of gstack, rebuilt for bootstrappers, indie hackers, and people who want to quit their day job. Pieter Levels energy. Ship fast, charge money, skip the pitch deck.
Grix : Work with agents like talking to people.
Claude Code style AI agent from scratch using Python
A local-first, open-source coding agent for your desktop. Bring your own LLM key; your code stays on your machine and only ever leaves to the model provider. The AI Agent builds its own Harnes.
The best minimalist multi-agent coding harness.
Evidence-first coding agent for GitHub Copilot CLI
Open-source multi-agent coding CLI for the terminal (TypeScript, MIT). Switch models mid-session; finish goals only when your test passes.
An inspectable coding agent. Trace changes, diagnose failed runs, and share test evidence. Local-first Python, no-key demo, standalone HTML reports.
Native desktop shell for Pi Coding Agent (Tauri + Lit), extension-first and multi-session aware
Every coding agent in one desktop workspace. Run Claude Code, OpenAI Codex, Cursor Agent and Grok side by side. Bring your own CLI. Free during beta. Open source as of 21 September 2026 (MIT).
Terminal-based AI Coding Agent, similar to Claude Code, OpenAI Codex etc. but works with many more LLMs e.g. Gemini, Groq, Deepseek
Self-hosted apps you operate by watching a dashboard and talking to a coding agent that IS the runtime — it proposes, applies, and evolves the app live. Built for Claude Code and MCP.
Open-source AI coding agent for your terminal — one Rust binary, 15+ LLM providers, 1,000+ models. A self-hostable Claude Code / Codex CLI alternative (MIT).
One macOS app for Claude Code, Codex, and every agent runtime you use — scheduled runs, global hotkey launcher, per-run git worktrees, one review board.
An open-source alternative to Cursor, Windsurf (Local RAG, Bring your own LLM, Agents). Written in golang
An agentic development environment for AI coding agents
Open-source terminal agent runtime. Lean context, native speed, open all the way down — in a single Go binary.
A desktop AI coding assistant that works with your local projects. Ally helps you understand code, edit files, search a workspace, manage tasks, and complete development work through conversation.
Verification-driven AI software iteration, powered by the OpenAI Codex SDK. Self-hosted agents turn goals, GitHub Issues and PR feedback into tested, reviewable changes, with bounded execution and human control over merging and deployment.
Terminal based coding agent & harness running on your own Cloudflare account. No middleman.
An open-source, local-first AI teammate and agent operating environment for turning intent into completed work—with tools, memory, permissions, and human oversight.
🔁 Run AI coding agents as an autonomous dev team across all your GitHub repos — plan, review, fix, and ship, on a loop.
Deterministic spec-orchestration for local LLMs in the pi coding agent — drives prompts through refine→research→grill→compose→critique, with bundled web/docs/fetch worker tools.
An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qwen3.8-27B runs up to 2.6x faster than llama.cpp.
bumpgen is an AI agent that upgrades npm packages
Local GUI client for full-access multi-model coding agents
Clean-room, model-agnostic harness for Claude Code-class coding agents
Self-hosted engineering software factory: Temporal, CubeSandbox agents, deterministic verification and durable evidence. MIT-licensed Machinist fork.
AI coding agent for Visual Studio 2022/2026 — chat, inline completion, and five autonomous agents that explore, plan, patch, and verify builds. Works with the official DeepSeek API or any OpenAI-compatible endpoint.
MAGE: A Multi-Agent Engine for Automated RTL Code Generation
Our goal is to multiply model capability per dollar of inference. AgenC is an open source framework that improves how any model plans, uses tools and checks its work.
Opinionated AI coding agent and dev environment automation for macOS
Plan-then-build AI coding for Claude Code & Codex CLI — you approve the plan before the model writes a line of code. SPEC → PLAN → TEST → CODE → REVIEW → LEARN
An Autonomous AI Software Engineer
miniClaudeCode - 从50万行蒸馏到~1000行的Claude Code核心Agent架构最小复现 | Distilled Claude Code agent framework
零远程行为、子代理协同、支持自主进化的自治 Agent 编队丨 Autonomous Agent Fleet with Zero-Remote Behavior: Sub-agent Collaboration and Self-Evolution
Mission control for AI coding agents. Watch Claude Code, Codex, Gemini and a dozen more work live in one macOS terminal: live status, an editor that follows their edits, undo for any turn, approvals from your phone and local models. 20+ built-in tools, all on the site below. Built on Ghostty.
Demonstration of an agent harness with access to tools like Slack, GitHub, and Linear so it can act as your own complete software engineer.
AI coding agent with one Python core and three front-ends — headless CLI, Textual TUI, and an Electron desktop. Works with any OpenAI-compatible API, with risk-tiered permissions, event-sourced replayable sessions, and a fail-closed OS-level sandbox.
Self-Improving Agents -- A Progression Four levels of self-improving code agents, from the simplest loop to a full adversarial arena with self-modifying agents. Each level adds one key idea.
An open-source agent harness for software work.
Local-first, spec-driven SDLC workbench with governance gates, knowledge graphs, and MCP for AI coding agents.
Open-source, model-independent Agent Skill for evidence-based software reconstruction with REA. Optional integration, portable installer, and validation workflows.
transformers safetensors qwen2 text-generation code qwen
Run a team of AI coding agents. On your machine. Local-first orchestration for Claude Code, Codex, OpenCode, Antigravity, and Copilot.
Cursor Agent Tools - A Python-based AI agent that replicates Cursor's coding assistant capabilities, enabling function calling, code generation, and intelligent coding assistance with Claude, OpenAI, and locally hosted Ollama models.
A Python-based CLI coding agent, similar to Claude Code and OpenCode, but lighter and more flexible, featuring pluggable model support for DeepSeek and beyond.
The harness orchestrator — a local-first kanban for running Claude Code, Codex, and other CLI coding agents in parallel, each in its own git worktree.
AI Engineering Runtime for Professional Developers — terminal coding agent with IOSM methodology, MCP, checkpoints, orchestration, and extensions
An Open Source, Claude Code Like Tool, With RAG + Graph RAG + MCP Integration, and Supports Most LLMs (Incomplete But Functional & Usable)Autonomous LLM agent: ChromaDB semantic RAG + Neo4j knowledge-graph sync + MCP tool-call gateway.