Browse: RAG & Memory
PyTorch Lightning is the lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate.
A prompt programming language
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5Ã faster than industry leaders, 100% pass rate on 3,830 PDFs.
Ultralytics YOLO đ for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
The official Python SDK for Model Context Protocol servers and clients
Curated list of the best truly open-source AI projects, models, tools, and infrastructure.
Second Brain is a desktop application that acts as a personal knowledge base, using retrieval-augmented generation (RAG), multimodal AI models, and a hybrid lexical/semantic search algorithm to intera
Biologically-inspired memory for AI agents. Decay, retrieval strengthening, consolidation. Zero dependencies.
A Claude Code skill that turns your Obsidian vault into a living second brain â autonomous writes, thinking tools, knowledge ingestion, scheduled agents, and _CLAUDE.md for cross-surface context.
21 Lessons, Get Started Building with Generative AI
Freely available tools for computational molecular biology.
Efficient, Flexible and Portable Structured Generation
AI Agent Collaboration System for Content Creation - Based on oh-my-opencode
Universal memory layer for AI Agents
A portable accelerated SQL query, search, and LLM-inference engine, written in Rust, for data-grounded AI apps and agents.
đŠđģâđŗ A collection of example notebooks using Haystack
Tools to manipulate font files
The official Rust SDK for the Model Context Protocol
A python client for the GitHub API
The official PHP SDK for Model Context Protocol servers and clients. Maintained in collaboration with The PHP Foundation.
A repository of servers and clients from the Model Context Protocol tutorials
Microsoft Azure Cognitive Search Client Library for Python
EdegQuake đ High-performance GraphRAG inspired from LightRag written in Rust; Transform documents into intelligent knowledge graphs for superior retrieval and generation
The official Ruby SDK for the Model Context Protocol.
Recipes and resources for building, deploying, and fine-tuning generative AI with Fireworks.
A high-throughput and memory-efficient inference and serving engine for LLMs
CuPy: NumPy & SciPy for GPU
The official Java SDK for Model Context Protocol servers and clients. Maintained in collaboration with Spring AI
The official Python SDK for the xAI API
An abstract syntax tree for Python with inference support.
The operational layer for coding agents. Memory, validation, and feedback loops that compound between sessions.
Internationalized Domain Names in Applications (IDNA)
Persistent memory for AI coding agents
Run coverage and linting reports on diffs
A Python implement of Agent Client Protocol (ACP, by Zed Industries)
Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.
Natural Language Toolkit
Official Firecrawl nodes for n8n - scrape, crawl, map, search, and extract data from websites. Supports AI Agent tool usage.
RAGElo is a set of tools that helps you selecting the best RAG-based LLM agents by using an Elo ranker
Shared memory for AI agents
Paper-first SPY options validation platform with broker-backed scorecards, hard risk gates, paired-trade accounting, and live dashboards.
A thin cython wrapper around llama.cpp, whisper.cpp and stable-diffusion.cpp
tvm ffi
RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generat
HippocampAI â Autonomous Memory Engine for LLM Agents
Package for applying ao techniques to GPU models
Specification and documentation for the Model Context Protocol
The official TypeScript SDK for Model Context Protocol servers and clients
A community-driven collection of RAG (Retrieval-Augmented Generation) frameworks, projects, and resources. Contribute and explore the evolving RAG ecosystem.
Docling simplifies document processing, parsing diverse formats â including advanced PDF understanding â and providing seamless integrations with the gen AI ecosystem
Comprehensive paid advertising audit & optimization skill for Claude Code. 225+ checks across Google, Meta, YouTube, LinkedIn, TikTok, Microsoft & Apple Search Ads with weighted scoring, parallel agen
Open-source RAG platform with multi-LLM support. Build AI agents that connect to your data, tools, and workflows - no code required.
No description
A tool to determine the content type of a file with deep learning
Google OR-Tools python libraries and modules
Scapy: interactive packet manipulation tool
A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym).
List processing tools and functional utilities
A refreshing functional take on deep learning, compatible with your favorite libraries
PyMuPDF Utilities for LLM/RAG
A development tool to measure, monitor and analyze the memory behavior of Python objects.
Cython implementation of Toolz: High performance functional utilities
Modern high-performance serialization utilities for Python
Manage calls to calloc/free through Cython
Structured Text Generation in Rust
A Lucene query parser generating ElasticSearch queries and more !
The sweetest config system for Python
Super lightweight function registries for your library
client libraries for humans
The Sovereign AI Platformâ â Local AI models, agents, skills, and automations â on your own infrastructure, connected to your data
Ready Player One - stop prompting; start shipping
Cython hash table that trusts the keys are pre-hashed
DeepV-Ki â Instantly turn your code repository into a beautiful, interactive Wiki. An AI-powered documentation generator with RAG-based code Q&A, automatic architecture diagram generation, and multi-m
distributed and parallel Python
Buddhist Digital Text Platform â 9,200+ texts, 500+ sources, 8 UI languages, AI Q&A (RAG), knowledge graph, full-text search
Audit trail and search engine for AI agent sessions
Agent Skill CLI. Search, install, review, and manage AI agent skills from agentskill.sh.
Agentic memory built on Postgres
Extract tables precisely from PDFs and convert them to clean HTML for RAG pipelines, running fast on CPU without external dependencies.
Coordinate your AI agent team. Shared tasks, memory, reflections, and presence. Self-host for free.
Stream responses from OpenAI and Anthropic models with lightweight C++ tools for efficient large language model integration.
Provide free, open access to comprehensive AI tools, guides, reviews, and resources to reduce knowledge gaps and empower users.
Capture and summarize Claude Code sessions into searchable, browsable engineering journals with a web UI and automated daily entries.
Search and analyze medical literature across PubMed, ClinicalTrials.gov, and Europe PMC using AI to support clinical and research decisions.
Fast, streaming indexing, query, and agentic LLM applications in Rust
Autonomous AI agent memory system with CLAUDE.md protocol enforcement
Autonomous AI agent memory system with CLAUDE.md protocol enforcement
YouTubeGPT is an LLM-based web-app that can be run locally and allows you to summarize and chat (Q&A) with YouTube videos.
CLI tool for managing AI Agent skills - search, install, and update skills for Claude, Codex, Copilot, and more
Event transport, replay, and durable transcripts for AI agent conversations
AI Agent for Telegram & TON Blockchain
Persistent structured memory for AI agent systems â pluggable SQLite or Postgres backend, LLM context bridge
đ§ Enhance visual search with Mini-o3, providing state-of-the-art multi-turn reasoning and easy-to-use training code for advanced AI applications.
Explore alternatives to Discord with a curated list of early-stage apps, evaluating features, hosting, and encryption to guide your choice.
Showcase delivers a modern developer portfolio built with TypeScript and React, focusing on interactivity and clean architecture for a seamless user experience.
Reference Implementations for the RAG bootcamp
Broken RAG For The Broken Souls
Visual workspace manager for Squad SDK â create, manage, and collaborate with AI agent teams
Microsoft Corporation Azure AI Projects Client Library for Python
llama-index indices llama-cloud integration
Python client library and utilities for communicating with Triton Inference Server
Parse files into RAG-Optimized formats.
CUDA profiling tools runtime libs.
Databricks SDK for Python (Beta)
Local-first AI agent runtime. One command, your machine, your data.
Local AI agent with chat, tool use, persistent memory, and vision
Context window auto-manager for free AI agent users. Your 200K context, maximized.
Scaffold production-ready AI agent workspaces â SOUL.md, AGENTS.md, memory structure, heartbeat config, and more
An AI agent skill for real-time web and X search with xAI Grok.
AI agent dispatcher with adaptation loop for Mahoraga
SkillsHub CLI â publish, search, and install AI agent skills
Long-term memory system for OpenClaw AI Agent
Create a new Schift AI agent project
12 native protocol layers for AI-agent systems. No wrappers. No SDK dependencies.
Folder-as-neuron brain for any AI agent. mkdir replaces system prompts.
A better AI Agent node for n8n with improved memory management and modern AI SDK integration