Awesome MCP Servers - A curated list of Model Context Protocol servers

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning & ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning

Democratizing AI scientists with ToolUniverse

🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.

Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

"AnyTool: Universal Tool-Use Layer for AI Agents"

Simple to install, powerful command-line based AI agent system for coding.

[ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

Paper collection on building and evaluating language model agents via executable language grounding

A working pattern for SSE-based MCP clients and servers

(NeurIPS 2024) AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning

🐔 Agentic systems explained with chickens. Workflows, agents & orchestration made simple. Mermaid diagrams included

Anthropic Claude API wrapper for Go

Chat application with multi-agents system supports multi-models and MCP

Code Mode inspired local sandboxed MCP Gateway - collapses N servers x M tools into 2 tools (~1,000 tokens)

Learn to build and customize multi-agent systems using the AutoGen. The course teaches you to implement complex AI applications through agent collaboration and advanced design patterns.

A multimodal chat interface with many tools.

Example implementation of MCP Streamable HTTP client/server in Python and TypeScript.

LLM-powered Agent Runtime with Dynamic DAG Planning & Concurrent Execution

Scalable and extensible reinforcement learning for LM agents.

The coding agent for professionals

The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".

VT.ai - multimodal AI chat app with dynamic conversation routing

Rails Engine with MCP compliant Spec.

Curated collection of tools for agentic LLMs in Emacs