📖 MCP server for fetch deepwiki.com and get latest knowledge in Cursor and other Code Editors

Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.

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

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

A principled reduction of six benchmarks from the Open LLM Leaderboard to a single sparse benchmark.

"DeepResearch-Eval: An End-to-End Evaluation Framework for DeepResearch Systems"

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

LLM Fine Tuning Toolbox images for Ryzen AI 395+ Strix Halo

Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)

The LLM Evaluation Framework

Git Based Memory Storage for Conversational AI Agent

Roo Code gives you a whole dev team of AI agents in your code editor.

A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private conversations, form alliances, and vote to eliminate each other

[Up-to-date] Awesome Agentic Deep Research Resources

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…

Build resilient language agents as graphs.

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Sparse Inferencing for transformer based LLMs

Optimizing inference proxy for LLMs

An extremely fast Python type checker and language server, written in Rust.

Model Context Protocol Servers

💡 All-in-one open-source AI framework for semantic search, LLM orchestration and language model workflows

Streamlit — A faster way to build and share data apps.

A simple, secure MCP-to-OpenAPI proxy server

Generate impressive-looking terminal output to look busy when stakeholders walk by

🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.

Code, Data and Red Teaming for ZeroBench