Discover
Every project in the index. Underrated first: good projects that haven’t been noticed yet.
- 1.9k
Video Search and Summarization
Reference architecture for AI agents that search and summarize video
- 3.4k
SIE
Self-hosted inference server running many open models behind one API
AI models and runtimesAgent frameworks and toolsServers and infrastructure
3.7k
- 4.7k
OpenRAG
Self-hosted document search and chat built on Langflow and OpenSearch
- Vitali Avagyan5.3k
Code-Graph-RAG
Maps a codebase into a knowledge graph to query and edit in plain English
- 5.7k
UltraRAG
MCP-based framework for building and evaluating RAG pipelines in YAML
- 10.4k
Octop
Self-hosted multi-user AI assistant with teams of specialist agents
- xerj-org11.6k
XERJ
Local search engine and MCP server that indexes code and docs for agents
Agent frameworks and toolsData and spreadsheetsDeveloper tools
- 11.7k
CocoIndex
Incremental data indexing framework that keeps AI agent context fresh
- 12.9k
LiteParse
Local PDF and office document parser with OCR and bounding boxes
- 13k
LEANN
Compact local vector index for private RAG over personal data
- 14.2k
Semantica
Python framework for building context and knowledge graphs with provenance
- 16.6k
Memvid
Single-file memory store for AI agents with built-in search
- Ryan Codrai17.4k
turbovec
In-process compressed vector index using TurboQuant quantization
- 23.9k
RAG-Anything
Multimodal RAG framework for documents with images, tables, and equations
- 29.8k
OpenDataLoader PDF
PDF parser that outputs Markdown, JSON and HTML, plus PDF auto-tagging
- 29.9k
Sim
Visual workspace for building, running, and monitoring AI agent workflows
- 31.3k
Supermemory
Memory and context layer that gives AI agents and assistants recall
- 32.6k
Cognee
Knowledge-graph memory layer that gives AI agents long-term recall
- 39.3k
PageIndex
Tree-based document index for RAG without vectors or chunking
- 40.2k
LightRAG
Graph-based retrieval-augmented generation library with a web UI
- 40.4k
OpenViking
Filesystem-style context store for agent memory, knowledge, and skills
- 69.2k
Docling
Python library and CLI that converts documents into structured data for AI
Agent frameworks and toolsAI models and runtimesProductivity
- 76.6k
Headroom
Local compression layer that shrinks LLM context before it is sent
