MCP-Universe is a comprehensive framework designed for RL training, benchmarking, and developing AI agents for general tool-use.
☆604Oct 8, 2026Updated last month
Alternatives and similar repositories for MCP-Universe
Users that are interested in MCP-Universe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers☆515Oct 7, 2025Updated last year
- MCP Atlas☆164Nov 3, 2026Updated last week
- Anemoi: A Semi-Centralized Multi-agent Systems Based on Agent-to-Agent Communication MCP server from Coral Protocol☆369Aug 27, 2025Updated last year
- [ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution☆513Aug 18, 2026Updated 2 months ago
- MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.☆472Jun 12, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [COLING25] CodeJudge Eval: Can Large Language Models be Good Judges in Code Understanding?☆12Dec 3, 2024Updated last year
- MCP-based Agent Deep Evaluation System☆155Jun 2, 2026Updated 5 months ago
- Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments☆271Dec 16, 2025Updated 10 months ago
- A simple yet powerful agent framework that delivers with open-source models☆4,634Updated this week
- Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike stat…☆579Sep 30, 2026Updated last month
- Reached #13 on Stanford's Terminal Bench leaderboard. Orchestrator, explorer & coder agents working together with intelligent context sha…☆1,473Nov 3, 2025Updated last year
- Toolathlon-Gym for testing AI agents real-world tool-use capabilities across diverse MCP servers.☆152Oct 1, 2026Updated last month
- LiveMCPBench is a benchmark for evaluating the ability of agents to navigate and utilize a large-scale MCP toolset. It provides a compreh…☆105Dec 18, 2025Updated 10 months ago
- An Open-Source Large-Scale Reinforcement Learning Project for Search Agents☆615Nov 26, 2025Updated 11 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A benchmark for LLMs on complicated tasks in the terminal☆2,616Jul 11, 2026Updated 4 months ago
- The raw UserRL repo under construction☆128Jun 2, 2026Updated 5 months ago
- On the Theoretical Limitations of Embedding-Based Retrieval☆673Sep 15, 2025Updated last year
- A Gym for Agentic LLMs☆517Jan 21, 2026Updated 9 months ago
- Code and Data for Tau-Bench☆1,497Mar 18, 2026Updated 7 months ago
- Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.☆585Sep 8, 2025Updated last year
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,023Oct 22, 2026Updated 3 weeks ago
- LIMI: Less is More for Agency☆162Oct 14, 2025Updated last year
- Democratizing Reinforcement Learning for LLMs☆5,916Oct 16, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- An MCP server exposing full Chrome DevTools Protocol debugging: breakpoints, step/run, call stacks, eval, and source maps.☆350Oct 2, 2025Updated last year
- A version of verl to support diverse tool use [TMLR 2026]☆1,055Jul 15, 2026Updated 3 months ago
- xLAM: A Family of Large Action Models to Empower AI Agent Systems☆642Jun 2, 2026Updated 5 months ago
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆408Mar 30, 2026Updated 7 months ago
- [AAAI25] Official Repo of Paper `ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates`☆14Mar 22, 2025Updated last year
- A general memory system for agents, powered by deep-research☆869Mar 14, 2026Updated 7 months ago
- [CVPR 2026] 🔥🔥 Official Repo of USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning☆1,240Sep 12, 2025Updated last year
- LangGraph template for a simple ReAct agent, with MCP tools support and robust test suites.☆561Sep 28, 2025Updated last year
- One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation t…☆558Jun 30, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- MCPToolBench++ MCP Model Context Protocol Tool Use Benchmark on AI Agent and Model Tool Use Ability☆46Mar 17, 2026Updated 7 months ago
- τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains☆2,434Updated this week
- gcloud MCP server☆949Oct 17, 2026Updated 3 weeks ago
- Agent RL framework for LLM agents: multi-turn reinforcement learning with StarPO and reasoning-collapse diagnostics☆2,841Oct 28, 2026Updated 2 weeks ago
- ☆4,699Apr 22, 2026Updated 6 months ago
- Run Claude Code/Codex within AgentFS, orchestrated by LlamaIndex Workflows☆324Dec 19, 2025Updated 10 months ago
- A multi-agent LLM system for detecting and resolving cognitive dissonance.☆282Apr 25, 2026Updated 6 months ago
Are these results useful?