Web browsing superpowers for AI agents - one MCP server to scrape, crawl, extract, map, search, batch, research & monitor the web. Self-host...
Best Open Source AI Tools
Open-source AI gives you portable models, local runtimes, and auditable stacks. Explore popular GitHub projects here (ranked by stars), then compare licenses and use cases in the guide.
Popular on GitHub (by stars)
2,079 projects · ranked by GitHub stars, not a quality score
Open-source agent reliability platform for discovering, investigating, and fixing production agent failures
Self-hosted AI memory and MCP coordination for coding agents. Persistent context across repositories and sessions, with knowledge graphs, hy...
Open-source local policy, recovery, and audit layer for explicit Codex execution.
AgentWorks: AI agents that own the work. Goals that chase a metric, and Crews your team asks from Claude, ChatGPT or Cursor. Open source.
Self-hosted MCP server that makes your Obsidian/markdown vault searchable — text, PDFs, Office docs, images, audio — from any MCP client. Hy...
Mobile-first web UI for managing AI coding sessions (Claude Code, Codex, Aider, Gemini CLI, Amp, Pi). Self-hosted with multi-pane terminals,...
Deterministic open-source model router — right-sized LLMs per workload. Agent hooks, catalog policy, shadow mode, outcome benchmarks.
Agent work that compounds. Turn Claude Code and Codex into repeatable workflows: GitHub-triggered, fully observable, every run scored with e...
The open-source content agent — create on-brand videos, images and posts, then review and publish.
帧取 Framefetch · 自托管视频与剧本工作台:素材导入、任务追踪、AI 分镜分析与 Markdown/DOCX 报告。Self-hosted video & screenplay workspace wit...
Atlas — self-hosted, source-configurable, multi-disciplinary engineering platform for gen-AI, ML, and data work. 30+ OSS Docker Compose serv...
Fast local LLM / VLM inference engine for Apple Silicon (MLX). OpenAI- and Anthropic-compatible, lossless speculative decoding (DFlash2 / MT...
Open-source AI coding agent in V with a native backend, multi-provider API, and terminal UI.
Experimental local LLM router for OpenAI Codex CLI and Claude Code. Automatically selects models per task using TypeSafe Jev. Free, MIT-lice...
An open-source coding agent focused on reducing token usage and unnecessary model calls.
An open-source platform for building, fine-tuning, evaluating, and deploying AI models.
Long-running autonomous hierarchical multi-agent software development engine for terminal, web, and Android. Local-first, multi-provider, op...
Your files, your project — humans and AI working together without mistaking a guess for a fact. Local-first, open-source research.
ADHD planning assistant — FastAPI + Claude pipeline: kanban, day-planner timeline, ADHD nudge loop, GLaDOS-voiced. Self-hosted.
Open-source core and daemon for a Decentralized Intelligent Cooperative Network (DICN). Designed to provide applications with private multip...
Open-source, multi-tenant RAG and agents platform: teams, sources, knowledge bases, agents with verified citations. Go + React, Kubernetes-r...
One web UI for all your AI agent harnesses (pi, Claude Code, DeepSeek Harness, Hermes). Dockable tabs, real terminals, an LLM trajectory vie...
Free trial: A specialized 7-billion-parameter language…