HYSEN LABS DIRECTORY

#RAG

Capability tag · curated repositories and deep analysis.

740 curated open-source projects
★ 404

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

Python45 forks5 min read
★ 403

Serverless Modal + FastAPI + React + ColPali + Qdrant + GPT4o Vision RAG (V-RAG) Demo

TypeScript52 forks5 min read

A ReAct agent based on LangChain/LangGraph, combining RAG, tool calling, and a Streamlit UI, for intelligent customer-service and report-generation scenarios.

Python70 forks8 min read
labsai

EDDI

★ 394

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

Java132 forks5 min read
★ 393

Agent Framework Samples - showcasing ways in which agent framework can be utilized.

Jupyter Notebook152 forks4 min read
agenticloops-ai

agentic-ai-engineering

★ 393

Hands-on tutorials for building AI agents from scratch. Learn LLM APIs, prompt engineering, tool calling, and the agent loop through practical examples.

Python80 forks5 min read
wangtunan

blog

★ 391

Personal blog documenting a journey of growth. https://wangtunan.github.io/blog/

Shell66 forks5 min read
★ 386

A local-first AI knowledge-base system (RAG) that connects local documents into a tutoring search and LLM chat workflow. Currently supports md, txt, pdf (text), xlsx, and csv files, with MCP server support.

Go63 forks9 min read
buildingjoshbetter

TrueMemory

★ 385

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

Python52 forks6 min read
mrmps

pdf2md

★ 385

Browser based tool to convert PDFs to Markdown

TypeScript53 forks5 min read
spitfireuptown

datalinkx

★ 379

DatalinkX is a data-synchronization system between heterogeneous data sources, supporting incremental or full sync at scale. It moves data between HTTP, Oracle, MySQL, Elasticsearch, and other sources, with built-in transform operators such as SQL and LLM operators, running on the Flink and SeaTunnel engines. Includes sync-task management, cascading task configuration, and task log collection.

Java50 forks8 min read
ModelEngine-Group

DataMate

★ 375

DataMate is an enterprise-level data processing platform designed for model fine-tuning and RAG retrieval.

TypeScript48 forks7 min read
iLearn-Lab

NovelClaw

★ 375

Dynamic-memory-first collaborative AI framework for long-form story generation, chapter planning, and coherent narrative writing

Python54 forks6 min read
mine-ai-xyz

mine-ai

★ 375

Open-source reference implementations for AI-enabled payment security, blockchain fraud detection, and AML/CFT compliance reasoning.

Python2 forks7 min read
★ 372

Program that lets you ask questions about your documents, audio, and video files.

Python48 forks6 min read
feyninc

chonkiejs

★ 370

🦛 CHONK your texts with Chonkie ✨ Type-friendly, light-weight, fast and super-simple chunking library

TypeScript16 forks6 min read
★ 368

Reference implementation of a RAG-based documentation helper using LangChain, Pinecone, and Tavily..

Jupyter Notebook404 forks7 min read
csml-rpi

Foam-Agent

★ 368

Foam-Agent: An end-to-end, composable multi-agent framework for automating CFD simulations in OpenFOAM. NeurIPS 2025 Machine Learning and the Physical Sciences Workshop.

Python78 forks6 min read
Socialpranker

deepdive

★ 368

Deepdive skill for Claude Code — 12-phase research pipeline: plan-review gate, parallel sub-agent search, claims-ledger triangulation with dissent protection, relevance × authority evidence filter, multi-angle red team, four-layer citation verification. 105 blocks, 29 channels, 460+ stat sources, 47 APIs, 1072 verified endpoints.

Python6 forks5 min read
rush-db

rushdb

★ 367

RushDB is a graph + vector database and memory layer for AI agents. Push any JSON, get typed, searchable, relationship-aware records back — no schema, no migrations. Built on Neo4j.

TypeScript33 forks7 min read