The database of free AI tools on GitHub
22,947 open-source AI repos. Find a free alternative to any paid AI tool, or see what developers are talking about.
327 repos · showing 301–327
Personal AI agent that remembers and learns locally.
一站式AI自媒体工作台，从选题到发布全流程自动化
A personal AI agent and memory hub for cross-agent task continuity.
模拟一个由AI驱动的修仙世界，观察和干预修士的决策与互动。
Build modular, asynchronous AI pipelines for generative AI.
Organize and manage AI skills and agents on macOS.
Build stateful, multi-agent applications with LLMs in Java.
Prototype and debug AI agents in one desktop app.
Persistent memory service for AI agents to share knowledge and context.
AI research workbench for scientists with local-first, model-agnostic capabilities.
Self-contained Rust agent for coding and AI assistance.
Desktop AI assistant with chat, agents, and various AI features.
Deep research agent to help you find the best GitHub repositories 🕵️!
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs
Ontology-Augmented Generation for AI agents.
A free, self-paced 24-week AI engineering course: Python, machine learning, LLMs, RAG, fine-tuning, agents and MCP, Azure and Vertex and Bedrock, and Databricks. 43 runnable notebooks, one continuous
MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.
Learn to build from scratch an AI PR reviewer integrated with GitHub, Slack and Asana that scales within your organization.
Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can explore it.
A self-contained browser engine that fetches, renders, and extracts web content as Markdown, JSON, or screenshots — no Chromium, no API key, no setup.
An open-source research system for autonomous investigation, recursive self-improvement, and human–AI collaboration. Run experiments, refine methods through evidence and feedback, and turn traceable r
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-b
Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.
A lightweight persistent-memory companion for OpenCode & Claude
One interface to nine genomic deep-learning oracles — variant effect prediction, calibrated per-track percentiles, and plain-English analysis through MCP.
Helix-AGI is an Agentic AI memory and action system that runs on a continuous daemon pulse with a fully dynamic module context window compilation system. Bicameral release utilizes dual pipelines for
An AI-native OS. Models run on your own hardware, nodes federate peer-to-peer with no broker, and the API is OpenAI-compatible. Boots, has its own Wayland compositor, and runs on 8GB. Apache 2.0.