HYSEN LABS DIRECTORY

#RAG

Capability tag · curated repositories and deep analysis.

740 curated open-source projects
StarlightSearch

EmbedAnything

★ 1,324

Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

Rust140 forks8 min read
★ 1,321

Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything into structured, cross-referenced knowledge articles - inspired by Karpathy's LLM Knowledge Base architecture.

Python332 forks8 min read
apecloud

ApeRAG

★ 1,319

ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment

Python147 forks6 min read
SmythOS

sre

★ 1,304

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.

TypeScript204 forks7 min read
stair-lab

kg-gen

★ 1,294

[NeurIPS '25] Knowledge Graph Generation from Any Text

Python201 forks6 min read
CommandCodeAI

BaseAI

★ 1,293

BaseAI — The Web AI Framework. The easiest way to build serverless autonomous AI agents with memory. Start building local-first, agentic pipes, tools, and memory. Deploy serverless with one command.

TypeScript115 forks5 min read
endee-io

endee

★ 1,290

Endee.io – A high-performance vector database, designed to handle up to 1B vectors on a single node, delivering significant performance gains through optimized indexing and execution. Also available in cloud https://endee.io/

C++1,648 forks7 min read
ongridio

ongrid

★ 1,279

An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.

Go280 forks7 min read
★ 1,258

Reliability layer for multi-agent setups — keep agents coordinating without an orchestrator. Cross-dialog contracts + drift detection + black-box memory (no LLM extraction).

Python35 forks7 min read
zjunlp

LightMem

★ 1,223

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Python118 forks8 min read
★ 1,219

SQLite-Vector is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database.

C53 forks10 min read
superlinear-ai

raglite

★ 1,212

🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL

Python117 forks5 min read
0xSojalSec

LLMs-local

★ 1,206

list of awesome platforms, tools, and resources run for LLMs locally

Unknown141 forks6 min read
Azure

GPT-RAG

★ 1,204

Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

Python331 forks6 min read
★ 1,203

A modular RAG (Retrieval-Augmented Generation) system with MCP Server architecture. Using Skill to make AI follow each step of the spec and complete the code 100% by AI.

Python275 forks7 min read
★ 1,195

A complete, structured hub for learning Artificial Intelligence — covering AI, Machine Learning, Deep Learning, and Data Science with books, roadmaps, and curated resources from beginner to advanced.

Unknown138 forks5 min read
volcengine

SearchCLI

★ 1,193

Open CLI for integrating AI search, recommendation, and conversational retrieval into agent systems and business systems

TypeScript40 forks5 min read
★ 1,192

A practical lab for building, testing, and evaluating apps with Apple's Foundation Models framework.

Swift70 forks6 min read
yfedoseev

pdf_oxide

★ 1,192

The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.

Rust152 forks10 min read

A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.

Python648 forks7 min read