10 open-source GitHub repos to build RAG pipelines for AI agents, from RAGFlow (93k stars) to Qdrant
victor_explore · x · 2026-11-01
A GitHub compilation rounds up 10 open-source repos covering the full agent context stack—parsing, vector storage, reranking:
- RAGFlow (infiniflow, 93k stars): self-hosted full RAG app combining retrieval and agent capabilities
- Docling (docling-project, 70k stars): PDFs and docs to clean Markdown
- LlamaIndex (run-llama, 52k stars): framework for connecting data to LLMs
- Milvus (milvus-io, 46k stars): vector database for huge datasets
- LightRAG (HKUDS, 40k stars): knowledge graphs from documents
- OpenViking (volcengine, 39k stars): context database for agents
- PageIndex (VectifyAI, 39k stars): reasoning-based retrieval without vectors
- Qdrant: fast vector search in Rust
- Chroma: the easy open-source vector database
- FlagEmbedding (FlagOpen, 12k stars): BGE embedding and reranker models
More from coding & agent
- Dev adds chatting AI bots to multiplayer games, doubling as server load tests — chongdashu · 2026-11-01
- OCI MCP Server lets you manage Oracle Cloud via natural language in VS Code — modelcontextprotocol · 2026-11-01
- pipeworx-io ships a Salesforce MCP connector over Streamable HTTP — modelcontextprotocol · 2026-11-01
- Building an overlanding sim game entirely in Runway Agent + App Studio — c_valenzuelab · 2026-11-01
- Adobe's EditAgent picks the right tool like a Photoshop pro, at 10x the compute cost — The Decoder · 2026-11-01
- Dev builds playable voxel survival game Wildmere with Claude Opus 5.5 + Unity + Blender MCP — TamoghnaKabi · 2026-11-01