Next Generation Agentic Proxy for AI Agents and MCP servers

A research prototype of a human-centered web agent

LLM Council works together to answer your hardest questions

Agent Tool Protocol

🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.

The absolute trainer to light up AI agents.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

UI over MCP. Create next-gen UI experiences with the protocol and SDK!

The best ChatGPT that $100 can buy.

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).

Lightweight coding agent that runs in your terminal

Intelligent Router for Mixture-of-Models

CursorRIPER

A symbolic, ultra-efficient AI prompt framework for software development assistance Based off CursorRIPER

🐻 Bear necessities for state management in React

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

An open-source, no-code agent building platform.

💫 Toolkit to help you get started with Spec-Driven Development

Free and open-source API Client & Interceptor.

🎨 Vibe Design System - Official monday.com UI resources for application development in React.js

Semantic search and document parsing tools for the command line

Memory for AI Agents in 6 lines of code

AGENTS.md — a simple, open format for guiding coding agents

MCP server that enables AI agents to analyze projects, initialize vibe unified rules for AI coding across Claude Code, Cursor, GitHub Copilot, and Gemini CLI

Supercharge Your LLM Application Evaluations 🚀

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

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

"RAG-Anything: All-in-One RAG Framework"