Coding agents & developer tools

Autonomous coding agents

4,327 agents · most starred first

Autonomous coding agents, page 17 of 44

BubblesAgent★ 18

BubblesAgent: Open-source AI agent using LLMs (GPT, Gemini, Claude) for automated, large-scale code refactoring and transformation.

codera_ai★ 18

This project aims to modernize legacy codebases by transforming them into modern, efficient, and maintainable code. Through an AI-driven analysis and transformation process, legacy systems can be upgraded to meet current standards and technologies.

opencode-multiplexer★ 18

an OpenCode MultiPlexer, to allow seamless switching between parallel running session, both existing and new

opencode-vscode-ide★ 18

VS Code fork with the OpenCode AI coding agent embedded natively as a sidebar SPA via an Electron-main loopback proxy. Open source AI IDE — alternative to Cursor / Windsurf / Claude Code Desktop.

homedir★ 18

Community Platform Developed 100% with AI Agents, Agentic and AI SDLC

MandoCode★ 18

A .NET C# CLI Coding Agent powered by Ollama + MAF (Agent Framework) and RazorConsole. Run locally or in the cloud. Refactors code, proposes diffs, manage context snapshots, mcp servers and skills.

Velune-CLI★ 18

VELUNE CLI is an open-source AI engineering CLI that unifies local LLMs (Ollama), cloud AI providers, MCP servers, tools, memory, and project context into a single developer workflow. Build, code, automate, and orchestrate AI with one extensible, provider-agnostic command-line interface.

LiteEditorAI★ 18

Terminal-first Linux workspace for supervising AI coding agents (Claude Code, Codex, Gemini): live agent status, split terminals, IDE code viewer + Git graph, and 20+ built-in dev modules.

Code-Assistant★ 18

streamlit region:us

FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview-v0.1-GGUF★ 18

gguf text-generation base_model:FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview base_model:quantized:FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview licen

Qwen2.5-Coder-14B-Instruct-Uncensored-GGUF★ 18

gguf text-generation base_model:Qwen/Qwen2.5-Coder-14B-Instruct base_model:quantized:Qwen/Qwen2.5-Coder-14B-Instruct license:mit endpoints_compatible

qwen3-coder-30b-a3b-compacted-19b-256k★ 18

mlx gguf 19b 256k-context 30b agentic-coding

vycode★ 18

🚀 Modern, high-performance Terminal AI Coding Assistant built in Rust. Supports OpenAI, Gemini, Anthropic, Groq, OpenRouter, and Ollama with a premium Orange TUI.

pxx★ 18

Local-first AI coding agent runtime — your models, fail-closed safety, evidence-gated self-improvement

memcode★ 18

Open Source Coding Agent

codey★ 18

A multi-agent workbench for coding agents — orchestrate Claude Code, Codex, OpenCode & pi from a native macOS app, Telegram/Discord/iMessage, or voice. Per-project workspaces, worker teams, flow graphs, parallel runs. Local-first, MIT.

Derivative★ 18

Turns natural-language requirements into executable Python software, tests it in isolation, and packages only independently validated builds.

Hacxgent★ 18

An autonomous CLI coding agent with smart memory management and zero provider lock-in.

duo★ 18

Two peer coding agents that work as equals: shared plans, live collaboration, isolated Git worktrees, cross-review and joint sign-off. Drives Pi, agy or opencode.

branchdeck★ 17

Multi-repo agentic orchestration that learns from every run

CodeFramer★ 17

CodeFramer is a versatile code editor built to enhance your coding experience with its intuitive interface and powerful features.

AI-Senior★ 17

🤖 AI Assistant fine-tuned to provide support for coding and design questions based on the latest trends in the industry.

attocode★ 17

A series of lessons, 0 to hero ai coding agent building guide.

uira★ 17

A lightweight, secure AI agent harness for your entire development lifecycle, fully written in Rust

codeforge★ 17

🤖 CodeForge AI: An autonomous multi-agent coding system powered by LangGraph for agentic software development and automated workflows. SOTA custom agentic GraphRag, shared-state memory, auto-model routing for cost optimization, and a range of custom tooling.

vv-opencode★ 17

An opinionated agentic development layer for OpenCode — spec-first when it matters, review-driven execution, portable model roles, safer tools, and long-run safety.

Qwen2.5-Coder-7B-Instruct-abliterated★ 17

transformers safetensors qwen2 text-generation chat abliterated

Qwen3.5-9b-Sushi-Coder-RL-MLX★ 17

mlx safetensors qwen3_5 mlx-vlm apple-silicon code

pier★ 17

Pier Code is a terminal-native agentic coding tool that understands your codebase and helps you move faster by handling routine tasks, explaining complex code, and managing git workflows through simple natural language commands.

StratumCode★ 17

AI coding agent that shows its work — every step visible, every patch approved by you. Build projects brick by brick, stay in control.

codeoid★ 17

Multi-Agent Coding Harness with pluggable AI-SDLC: switch sessions across claude, codex, gemini, export/share coding sessions, save tokens, multi-frontend (TUI · web · Telegram).

SeekAnchor★ 17

Experimental DSH Minimal trajectory-steering adapters for DeepSeek V4 Pro on Pi, Oh My Pi, and OpenCode V2. 推理轨迹引导实验。

IvyClaw★ 17

A production-oriented multi-agent AI Agent system for software engineering. | 面向软件研发任务的多智能体 AI Agent 工程系统

mastra-desktop★ 17

Local-first multi-agent coding workbench built on Electron, React and the Mastra framework. 本地优先的开源桌面 AI 工作台,基于 Mastra + Electron,把一次 Agent 运行组织成可暂停、可回溯、可交接的任务。

crabcode★ 17

A Python Code Agent

swamr★ 17

One prompt → a swarm of 150+ specialist Cursor agents that plan, build, test & harden your whole project in parallel, sharing an Obsidian brain.

clud★ 17

Claude & Codex CLI but with safety 3rd and God Mode always.

Aimighty★ 16

Self-hosted Codex, Your Codex in Your Container

pygent★ 16
smith★ 16

A performant open-source AI coding agent that lives in your terminal.

autocodex★ 16

autocodex orchestrates a structured loop: ideate → plan → implement → review → test

helloam-agentic-kanban★ 16

Agentic engineering platform: Kanban-driven AI coding agents with gated state transitions, per-task git worktrees and a full audit trail.

0xClaw★ 16

[EMNLP 2026] 🦀 The first autonomous hackathon agent stop assisting and start competing (🏆 Hackathon Champion Project).

spoox★ 16

Spoox CLI - Terminal Agent - SPlit lOOp eXand agent

wiggum-cli★ 16

AI agent CLI for spec-driven feature loops with Claude Code and Codex. Scans your stack, generates specs, and runs autonomous implement-test-fix cycles.

KodaCode★ 16

Трекер ошибок и предложений по продуктам KodaCode

CLITrigger★ 16

Dockable terminals for Claude Code, Codex & Antigravity by day, an unattended task queue by night. Each task gets its own git worktree; review the diffs over coffee.

beast★ 16

Beast Agent is a TUI to an agent, much like Pi or Claude Code. But compiled. Containerized. Multi-model. Agentic. Perfect for long-horizon tasks.

Qwen2.5-Coder-7B-Q8_0-GGUF★ 16

transformers gguf code qwen qwen-coder codeqwen

Qwen2.5-Coder-14B-Instruct-GPTQ-Int4★ 16

transformers safetensors qwen2 text-generation code codeqwen

aether-agent★ 16

A coding agent that lives in your terminal. Local Ollama first, or hosted models through the Aether AI fleet.

ant★ 16

Self-hosted AI engineering platform — PRD → design → code → verification as a state machine. Declared, auditable context per job; bring your own LLM key.

INKz★ 16

Cloud IDE + autonomous AI coding agent - Kubernetes-powered instant dev sandboxes with LangChain ReAct agent that reads, writes & ships multi-file code changes in your browser.

MiniDSH★ 16

Minimal surface, complete architecture: a small, local-first coding-agent harness that re-derives the invariants of DeepSeek Harness with fewer concepts. Independent educational project, not affiliated with DeepSeek.

beecode★ 16

BeeCode — free AI coding agent for the terminal. g4f models, no API key, real tools, skills/plugins/MCP, EN+RU UI.

jupyter-studio★ 15

The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat with @cell/@file context, ghost-text completion, one-click traceback fix. BYO model: Anthropic, OpenAI, Gemini, Ollama, vLLM. Local-first, privacy-first, fully open source.

autoloom★ 15

Autonomous AI Agent built on tinyloom

nclaw★ 15
alduin★ 15

Self-guided workshop to build your own CLI coding agent like Claude Code from scratch in Python.

ClawSharp★ 15

C# port of Claude Code for .NET, with multi-provider support across Anthropic, Gemini, Codex, OpenAI, GitHub Models, and more.

tiny-coding-agent★ 15

A lightweight, extensible coding agent built in TypeScript that helps developers with coding tasks across TypeScript, React, JavaScript, Node.js, Bash, and markdown/JSON.

ikanban★ 15

iKanban 是面向 OpenCode V2 的独立前端应用。iKanban is a standalone static frontend for OpenCode V2, based directly on the upstream shared desktop/web application.

a-agent★ 15

Minimal Coding Agent for use on iPad/iOS in a-Shell Terminal

codex-agenteam★ 15

AI team for Codex — researcher, PM, architect, developer, QA, and reviewer orchestrated through a configurable pipeline.

autoloom★ 15

Autonomous AI Agent built on tinyloom

Tlamatini★ 15

Speak an idea. Build the real thing. Tlamatini brings AI to code, 3D worlds and hardware: voice, live editor tutoring, 86 workflow agents, 110 tools, Unreal Engine, Blender, STM32, ESP32 and MCP. Open source on Windows, with local control and cloud reasoning. Full experience requires Ollama Pro+

hako-code★ 15

A standalone terminal agent in a single C file. Model agnostic (14 providers + local hako), skill-driven, tool permission gated. No node, no python.

Qwable-5-27B-Coder-GGUF★ 15

gguf code agentic distillation demonstration quantized

swebench-harness★ 15

Coding agent harness, achieved SWE Bench Lite resolve rate of 52.4%

Shepherd★ 15

Shepherd is an end-to-end AI Software Engineering platform that supervises the complete software delivery lifecycle—not just code generation, but planning, execution, testing, regression, governance, deployment, and continuous knowledge growth.|Shepherd 将 AI 的一次性交付,转化为组织的长期软件工程资产。

complex_platform★ 15

Open-source agentic SDLC harness for structured requirements and application design with Codex, AI-DLC, independent review, Product Design, and human approval gates.

zlite★ 15

Lightweight CLI AI agent — chat, write code, and manage server software with natural language.

shiro-neko★ 15

An agentic coding CLI. It reads your code, edits it, runs your tests, and asks when the request is ambiguous — in a terminal UI, with every mutating action gated behind an approval prompt.

aiset★ 15

Turn your repos into a team of Claude Code agents with persistent memory, coordinated tasks, and a live dashboard.

herdr-recap★ 15

Come back to a bunch of agents and know in seconds which ones need you. For the Herdr app and the herdr TUI: per agent, where it got to (a recap written while you were away) and whose move it is, across every machine. Reply from the list, get better titles. Nothing else to install.

forge-agent★ 15

Open-source, local-first AI coding agent. Build, share, and install skills. Runs on your machine. Your keys, your data. No cloud. No subscription. Built for developers who ship.

herduck★ 15

Open-source terminal app for running many coding agents (Claude Code, Codex, OpenCode). Keeps each piece of work's goal, status, blockers & next steps across sessions. Derived from Herdr.

agentmash-cli★ 15

Your team's coding agents warn each other before they edit the same file. Claude Code, Codex, Cursor and 17 more.

pi-rust★ 15

Rust-only port of the pi coding agent harness

dev-copilot★ 14

A developer-focused chatbot agent that answers technical questions.

you★ 14

An autonomous AI agent orchestrator that coordinates an entire software company within OpenCode

claudeme★ 14

ClaudeMe - 终端里的另一个你。基于 Claude Code,支持任意 OpenAI Compatible API,多厂商多模型,零确认开干。不只是编程工具,是你的赛博分身。 | Your digital twin in the terminal. A Claude Code fork with multi-provider & zero-confirmation mode.

jules-app★ 14

self-hosted workspace for Google's Jules AI agent

clapp★ 14

CLAPP: CLASS LLM Agent for Pair Programming

SAM★ 14

SAM — Smart Agentic Model: CLI coding agent for open-source LLMs. pip install sam-agent

dhara★ 14

Dhara — The Agent Protocol Standard. Minimal, secure, language-agnostic coding agent harness. Built from India 🇮🇳 for the World 🌏

Clif-Code★ 14

AI code editor + terminal coding agent, built in Rust. Works with any LLM via OpenRouter, OpenAI, Anthropic, or Ollama. 20MB native binary, 20 themes, real terminal, git, agent sidebar with tool calling.

orbiqd-briefkit★ 14

Orchestrate multiple coding CLIs (Claude Code/Codex/Gemini) from one interface. Exposes MCP server for tool integration. Run agents locally without API keys, track all executions, resume conversations. Built for automation and scripting.

mimo-code★ 14

CLI coding agent powered by the MiMo large language model

Qwen2.5-Coder-32B-Instruct-4bit★ 14

transformers safetensors qwen2 text-generation code codeqwen

Seed-Coder-8B-Instruct-GGUF★ 14

transformers gguf llama text-generation unsloth base_model:ByteDance-Seed/Seed-Coder-8B-Instruct

Qwen2.5-Coder-0.5B-Instruct-abliterated-GGUF★ 14

gguf code codeqwen chat qwen qwen-coder

the-forge★ 14

Multi-Agent Code Evolution Platform: 4 LLMs compete, evolve, and breed code through a JIT compiler judge

wraith★ 14

潜伏在终端与桌面里的幽灵 AI 编程 agent「Wraith」· A ghost-themed AI coding agent for terminal & desktop

AnyAutomationStudio★ 14

AI-powered engineering IDE for Siemens TIA Portal and CODESYS: SCL code generation with Claude, GPT, Gemini or local Ollama, unit tests on PLCSIM Advanced, OPC UA, Git and MCP tools. TIA Portal V15-V21.

clarvis★ 14

Local-first coding agent with operator-owned prompts, memory, plans, tools, and multi-agent workflows in the terminal.

reika★ 14

Coding agent CLI for local and hosted models, designed around small local models first

Mentat★ 14

A two-layer coding agent. Your code and data never leave your machine.

kraft★ 14

A local orchestrator that takes your coding agent from spec to pull request, stopping only when a decision is yours.

toppingout★ 14

Spec-driven software factory for Claude Code that works through your tickets overnight. A planner/executor split: the foreman (planner) specs each ticket, a cheap model builds it, another model family reviews it, and you merge only what comes with proof.

More in Coding agents & developer tools