Agent Marketplace

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

Any research. One Claw. 🦞 From any materials to research with fully autonomous & skill-driven researcher.

First Principles Framework (FPF): Pattern language and core specification for admissible action in problematic engineering, research, and mixed human/AI work.

🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/

Agentic RAG R1 Framework via Reinforcement Learning

Llama Agents + Workflows are an event-driven, async-first, step-based way to control the execution flow of AI applications like agents.

Let's reproduce paper simulations of multi-robot systems, formation control, distributed optimization and cooperative manipulation.

An ops AI Agent that understands your infrastructure, finds the root cause, and fixes it — right from Slack, Telegram, Lark or DingTalk.

An autonomous research colleague — from a question to a compiled manuscript, while you sleep.

A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.

A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.

165 evidence-based education skills for Claude, Codex, Hermes and any Agent Skills-compatible tool.

📱 Terminal in Your Pocket — Control Claude Code, Codex, Gemini CLI & your Mac/Linux/Windows from any phone or browser. Vibe coding from anywhere. Alternative to MobileCLI, Claude Remote, vibe-remote, MuxAgent.

One task, one agent, delivered. The open-source platform for task-driven autonomous AI agents.OpenCow assigns an autonomous AI agent to every task — features, campaigns, reports, audits — and delivers them in parallel. Full context. Full control. Every department. 🐄

Practical system design, tools, and hands-on resources for building Gen-AI agents & agentic AI systems.

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with Claude Code, OpenClaw, and any CLI agent.

本书围绕 DeerFlow 2.0，从理论到源码，系统讲解如何进行二次开发。(精校)

A highly customizable agentic harness for arXiv-ready ML/AI review papers (and beyond). It drives agentic AI like Codex CLI and Claude Code through a gated LaTeX workflow with verified BibTeX citations.

[ICLR'25] OpenRCA: Can Large Language Models Locate the Root Cause of Software Failures?

(JAIR'2022) A mini-scale reproduction code of the AlphaStar program. Note: the original AlphaStar is the AI proposed by DeepMind to play StarCraft II. JAIR = Journal of Artificial Intelligence Research.

Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)

A comprehensive set of LLM benchmark scores and provider prices. (deprecated, read more in README)

Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK, no backend, no telemetry.