- dify by langgenius, 161k stars. Platform for agentic workflows and RAG pipelines with model and tool support
- graphify by Graphify-Labs, 148k stars. Builds a queryable knowledge graph from code, docs and PDFs
- ragflow by infiniflow, 94k stars. Open source RAG engine with agent-oriented retrieval and document parsing
- ruflo by ruvnet, 82k stars. Multi-agent swarm runtime with coordination, memory and autonomous workflows
- headroom by headroomlabs-ai, 80k stars. Compresses tool outputs and RAG chunks before they reach the LLM as a library, proxy, or MCP server
- pathway by pathwaycom, 62k stars. Python stream processing framework with connectors, real-time analytics and RAG
- DeepTutor by HKUDS, 59k stars. AI tutor with multi agent research and retrieval for personalized learning
- OpenViking by volcengine, 42k stars. Context database unifying agent memory, knowledge RAG and skills
- ai-engineering-hub by patchy631, 42k stars. Tutorials on LLMs, RAG, and AI agent apps, mostly as Jupyter notebooks
- PageIndex by VectifyAI, 40k stars. Reasoning-based document index for retrieval without vector embeddings
- book-to-skill by virgiliojr94, 38k stars. Converts a technical book PDF into a Claude Code skill
- WeKnora by Tencent, 37k stars. LLM knowledge platform that turns documents into RAG, an agent and a wiki
- qdrant by qdrant, 36k stars. High-performance vector database and similarity search engine written in Rust
- onyx by onyx-dot-app, 33k stars. AI chat and enterprise search that works with many LLM providers
- Scrapegraph-ai by ScrapeGraphAI, 33k stars. Python library that uses an LLM to extract data from web pages
- TencentDB-Agent-Memory by TencentCloud, 31k stars. Team-level memory store that turns chats, docs and code into reusable agent memory
- opendataloader-pdf by opendataloader-project, 30k stars. Java PDF parser that outputs JSON, markdown and HTML with accessibility tagging
- MaxKB by 1Panel-dev, 23k stars. Open source platform for building knowledge-base chatbots and agents
- xerj by xerj-org, 19k stars. Single Rust binary for full-text, vector and hybrid search with an MCP server
- turbovec by RyanCodrai, 17k stars. Vector index in Rust with Python bindings for nearest neighbor search
- SurfSense by MODSetter, 17k stars. Private NotebookLM alternative: an agent that researches and edits documents
- awesome-ai-apps by Arindam200, 17k stars. Collection of example projects for RAG, agents, and other AI use cases
- zvec by alibaba, 16k stars. Embedded in-process vector database with HNSW indexing
- garden-skills by ConardLi, 15k stars. Collection of agent skills for web design, retrieval and image generation
- EverOS by EverMind-AI, 14k stars. Local-first memory layer shared across AI agents, stored as Markdown
- InsForge by InsForge, 13k stars. Open source backend with database, auth, storage and hosting for coding agents
- cocoindex by cocoindex-io, 12k stars. Incremental data processing engine for indexing and transforming data
- PixelRAG by StarTrail-org, 11k stars. Research code for searching web pages as images instead of parsing text
- production-agentic-rag-course by jamwithai, 10k stars. Course on building production agentic RAG systems
- utopia by deeplethe, 8.7k stars. Knowledge base and graph store with agent memory built on PostgreSQL and pgvector
- R2R by SciPhi-AI, 8.1k stars. RAG API server with agentic retrieval, document ingestion and search
- semble by MinishLab, 6.4k stars. Code search for coding agents that uses far fewer tokens than grep and read
- DigUp by ARahim3, 6.4k stars. On-device search over photos, PDFs, recordings, and code using embeddings
- helix-db by HelixDB, 6.3k stars. Graph database with built in vector and full text search, written in Rust
- hister by asciimoo, 6.3k stars. Personal search engine over your browsing history with an MCP interface
- OpenExecutive by SenteLabsAI, 5.8k stars. Virtual executive team of eight specialist agents behind one persona
- DeskcommCRM by melgarafael, 5.4k stars. Self-hosted sales CRM with AI agents and WhatsApp integration via WAHA
- code-graph-rag by vitali87, 5.4k stars. Knowledge graph RAG for querying and editing multi-language codebases
- chonkie by feyninc, 4.8k stars. Python chunking library for splitting documents in RAG pipelines
- openrag by langflow-ai, 4.7k stars. Single-package RAG platform built on Langflow, Docling and OpenSearch
New repos every two days, stars refreshed daily. Visits are counted without cookies, and the numbers are public. How it works Data RSS Newsletter