HYSEN LABS DIRECTORY

#RAG

Capability tag · curated repositories and deep analysis.

Largest Star gains over the past seven days, from our daily GitHub snapshots.

  1. Graphify-Labs/graphify+3,987 this week
  2. thedotmack/claude-mem+2,493 this week
  3. Renhuai123/ziwei-doushu+1,395 this week
  4. Tencent/WeKnora+640 this week
  5. headroomlabs-ai/headroom+585 this week

New here

Repositories we started tracking most recently.

  1. terrier-org/pyterrierAdded Oct 20 · ★ 519
  2. ritik-prog/n8n-automation-templates-5000Added Oct 20 · ★ 531
  3. jerryjliu/liteparse_samplesAdded Oct 20 · ★ 527
  4. junkai-li/NetCoreKevinAdded Oct 20 · ★ 556
  5. DemonDamon/AgenticXAdded Oct 20 · ★ 1,088

Latest discussions

Posts on Hacker News, dev.to and Lobsters that link to a project listed here.

  1. AI Agent Sessions Are a Data Store Nobody Designeddev.to · Nov 11 · 10 points · genkit
  2. Show HN: We Build Shareable Context Layer for Agent TeamsHacker News · Nov 8 · 2 points · OpenViking
  3. Building an AI for hard conversations: five agents, one safety regex, and a supervisor who graded us blinddev.to · Nov 6 · 6 points · graphiti
  4. OpenTelemetry Collector Custom Builds: 6.5x Smaller, and What Resource Detectors Cost at Startupdev.to · Nov 5 · 5 points · google-cloud-go
  5. Does Graph RAG Actually Help? I Measured It on Postgres and TypeScriptdev.to · Nov 5 · 2 points · LightRAG
740 curated open-source projects
Graphify-Labs

graphify

★ 148,353

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

PythonAI & Machine Learning14,236 forks5 min read
thedotmack

claude-mem

★ 117,327

Persistent Context Across Sessions for Every Agent, Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More.

JavaScriptAI & Machine Learning10,193 forks5 min read
infiniflow

ragflow

★ 94,194

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses reliable RAG with Agent capabilities to create a superior context layer for LLMs.

GoAI & Machine Learning11,326 forks4 min read
PaddlePaddle

PaddleOCR

★ 92,721

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

PythonAI & Machine Learning11,659 forks4 min read
bytedance

deer-flow

★ 85,367

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

PythonAI & Machine Learning12,030 forks5 min read
headroomlabs-ai

headroom

★ 79,741

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

PythonAI & Machine Learning6,244 forks5 min read
pathwaycom

llm-app

★ 58,704

Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. Docker-friendly.Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.

Jupyter NotebookAI & Machine Learning1,550 forks3 min read
milvus-io

milvus

★ 46,668

Milvus is a cloud-native vector database in Go and C++ for scalable ANN search over billions of vectors, with CPU/GPU acceleration and real-time streaming updates.

GoDatabases & Storage4,332 forks5 min read
HeyPuter

puter

★ 44,177

The Internet Computer! Free, Open-Source, and Self-Hostable. From AI to Cloud Storage and Database to Serverless Workers, Puter has you covered.

TypeScriptDatabases & Storage4,159 forks6 min read
VectifyAI

PageIndex

★ 40,445

PageIndex: Document Index for Vectorless, Reasoning-based RAG. Inspired by AlphaGo, we propose **PageIndex**, a **vectorless**, **reasoning-based RAG** system that builds a **hierarchical tree index** from long documents, and uses LLMs to **reason** *over that index* for **agentic, context-aware retrieval**.

PythonAI & Machine Learning3,477 forks5 min read
khoj-ai

khoj

★ 38,137

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.

PythonAI & Machine Learning2,552 forks6 min read
Tencent

WeKnora

★ 37,472

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

Go5,196 forks6 min read