Runs on: Windows WSL2 macOS Linux Docker
| # | Shot | Project | Stars | Plugs into | What it does |
|---|---|---|---|---|---|
| 1 | Bolt.diystackblitz-labs/bolt.diy | 20,022 | Local / Ollama | Open-source version of Bolt.new with Electron desktop apps, 19+ AI providers, and local model support via Ollama git clone https://github.com/stackblitz-labs/bolt.diy.git | |
| 2 | aichatsigoden/aichat | 10,537 | Claude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | All-in-one LLM CLI tool featuring shell assistant, REPL mode, RAG, AI tools and agents, supporting 20+ providers scoop install aichat | |
| 3 | CodeCompanion.nvimolimorris/codecompanion.nvim | 6,919 | Claude / AnthropicCodex / OpenAIGemini / GoogleGitHub CopilotLocal / Ollama | Neovim plugin for AI-assisted coding with agents, slash commands, and multiple LLM support git clone https://github.com/olimorris/codecompanion.nvim.git | |
| 4 | Atomic AgentAtomicBot-ai/atomic-agent | 3,490 | MCPLocal / Ollama | Local-first CLI and TUI coding agent that runs open-weight models entirely on your machine through a llama.cpp fork. No account or API key required. 56 built-in tools (browser, filesystem, git, memory, vision), MCP support, five-layer local memory, macOS/Linux/Windows irm https://atomicagent.io/install.ps1 | iex | |
| 5 | Devonentropy-research/Devon | 3,449 | Claude / AnthropicCodex / OpenAILocal / Ollama | Devon, not Devin, aims to perfect code correction for fill-in-the-middle, bug spotting, and completion tasks, using JSON for metadata in edits, and incorporates looping until user termination in function updates github npx devon-ui | |
| 6 | Claude Code Localnicedreamzapp/claude-code-local | 3,402 | Claude CodeClaude / AnthropicLocal / Ollama | by Matt Macosko - Runs Claude Code fully on-device on Apple Silicon: a native MLX server speaks the Anthropic Messages API, so the unmodified claude CLI works against local Qwen, Gemma and Llama models with no cloud calls. Includes RAM-based model selection, a tool-call parser for local models' output formats, and a verified-offline mode irm https://raw.githubusercontent.com/nicedreamzapp/claude-code-local/main/install.ps1 | iex | |
| 7 | little-coderitayinbarr/little-coder | 2,711 | Local / Ollama | A harness optimized to smaller LLMs npm install -g little-coder | |
| 8 | NanocoderNano-Collective/nanocoder | 2,544 | Codex / OpenAILocal / Ollama | Local-first CLI coding agent built with React and Ink npm install -g @nanocollective/nanocoder | |
| 9 | Codelsemanser/codel | 2,474 | Codex / OpenAILocal / Ollama | Autonomous AI agent, inspired by Devin, designed for complex task execution with features like a secure sandboxed Docker environment, integrated browser for real-time web information, text editor, and PostgreSQL database for history tracking, highlighting its relevance to agentic AI through its ability to autonomously navigate and perform actions across terminal, browser, and editor interfaces git git clone https://github.com/semanser/codel.git | |
| 10 | Gentleman-Programming/gentleman-guardian-angelGentleman-Programming/gentleman-guardian-angel | 1,194 | Claude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | Provider-agnostic code review using AI. Use Claude, Gemini, Codex, Ollama to enforce your coding standards brew install gentleman-programming/tap/gga | |
| 11 | Spark-X2.6XHToken/Spark-X2.6 | 877 | Local / Ollama | Spark-x2.6 open model series. Pushing the Limits of Agentic Capabilities in On-Device Models git clone https://github.com/XHToken/Spark-plugin.git | |
| 12 | SwarmClawswarmclawai/swarmclaw | 703 | Claude CodeClaude / AnthropicopencodeMCPCodex / OpenAIGemini / GoogleGitHub CopilotCursorLangChain / LangGraphLocal / Ollama | Self-hosted AI runtime that orchestrates Claude Code, Codex, Gemini CLI, OpenCode, Copilot CLI, Cursor Agent, Goose, Qwen Code, and Droid with heartbeats, schedules, delegation, runtime skills, and an org chart view. Ships as a desktop app (Electron) and CLI. MIT licensed, TypeScript npm i -g @swarmclawai/swarmclaw | |
| 13 | agenttyagentty-org/agentty | 619 | Claude CodeClaude / AnthropicCodex / OpenAILocal / Ollama | Native C++26 terminal coding agent and drop-in claude-code alternative. Single static binary, sub-millisecond cold start, sandboxed by default, and model-agnostic (Claude, OpenAI, Groq, OpenRouter, Ollama). Runs inside Zed over ACP and drives air-gapped hosts over SSH. MIT winget install agentty.agentty | |
| 14 | alphacodedragonked2/alphacode | 525 | Claude / AnthropicGemini / GoogleLocal / Ollama | Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & desktop automation, built in Rust. irm https://raw.githubusercontent.com/dragonked2/alphacode/main/scripts/install.ps1 | iex | |
| 15 | langchain-codezamalali/langchain-code | 439 | Claude CodeClaude / AnthropicCodex / OpenAIGemini / GoogleLangChain / LangGraphLocal / Ollama | LangChain-based coding agent for AI-assisted development. Supports Gemini, Anthropic, OpenAI, and Ollama pip install langchain-code | |
| 16 | DvalinCodearthurpanhku/dvalincode | 118 | Claude / AnthropicMCPCodex / OpenAICursorLocal / Ollama | Provider-neutral, local-first CLI coding agent (Chat/Cowork/Code modes) built for governance: org policy engine, enforced network egress, and a verifiable hash-chained audit trail. Works with any OpenAI-compatible endpoint (DeepSeek, OpenAI, Claude via OpenRouter, Groq, Ollama). Zero runtime deps. MIT npx dvalincode mcp-install cursor # .cursor/mcp.json | |
| 17 | Gokinginkida/gokin | 108 | Gemini / GoogleLocal / Ollama | Open-source terminal AI coding agent that works with local models via Ollama or providers like DeepSeek and Kimi, with no telemetry and secret redaction curl -fsSL https://raw.githubusercontent.com/ginkida/gokin/main/install.sh | sh | |
| 18 | BBARITbbarit/terminal | 40 | Claude CodeClaude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | Free native all-in-one AI coding IDE (Tauri/Rust) with multi-agent terminals, office editing, and an embedded agent-driven browser; bring any model or run locally with Ollama git clone https://github.com/bbarit/terminal.git | |
| 19 | AGXramarlina/agx | 33 | Claude CodeClaude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | Checkpoint-based execution engine for AI coding agents; durable Wake→Work→Sleep loops that resume across sessions. Supports Claude Code, Codex, Gemini CLI, and Ollama npm install -g @mndrk/agx | |
| 20 | VoltLeulAria/volt | 17 | Claude CodeClaude / AnthropicopencodeMCPCodex / OpenAIGemini / GoogleCursorLocal / Ollama | Open-source agentic workspace on the VS Code core that runs agent chats side by side, each optionally in its own Git worktree, with subagents, hunk-level keep or undo of agent edits, and a Git checkpoint per turn. Claude Code, Codex, OpenCode, Cursor, Grok, Antigravity, Kimi, and any ACP agent, plus local models through Ollama. git clone https://github.com/LeulAria/volt.git | |
| 21 | RelayImBIOS/relay | 10 | Claude CodeClaude / AnthropicopencodeCodex / OpenAIGitHub CopilotCline / RooAiderLocal / Ollama | Universal AI API proxy — hot-switch between 14+ LLM providers (GitHub Copilot, OpenAI, Anthropic, DeepSeek, Groq, Ollama, and more) from any AI coding agent without restarting sessions. Local proxy with automatic Anthropic OpenAI protocol translation, account rotation, and real-time usage tracking pnpm install -g github:ImBIOS/relay | |
| 22 | Alchemist CoderAlekla0126/alchemist-coder | 8 | Claude CodeClaude / AnthropicCodex / OpenAIGemini / GoogleLocal / Ollama | Open-source desktop app for Windows, macOS and Linux that indexes your Gemini CLI chats, together with Claude Code, Codex and Grok Build sessions, into one local, read-only full-text search. Running Gemini CLI over ACP inside the app is planned for its upcoming Pro edition; the free edition runs Claude Code and Codex on local models git clone https://github.com/Alekla0126/alchemist-coder.git | |
| 23 | Lifeboatnoah-thing/lifeboat | — | Claude CodeClaude / AnthropicopencodeAiderLocal / Ollama | Failover for coding agents: when Claude Code hits a rate limit, ban, or outage, hands the task to Aider, OpenCode, or a local Ollama model, carrying context. Multi-provider and local resilience, not account evasion. Open-source (MIT) git clone https://github.com/noah-thing/lifeboat |