Explore
MCP servers and skills: search, filter by where they run, and compare.
MCP servers and skills: search, filter by where they run, and compare.
Super cute 🐱 Benchmark graph generation
SkillApache-2.0★ 1Few starsNo key
BenchClaw adapters for LangChain, LlamaIndex, CrewAI, Ollama Open WebUI, LobeChat, n8n, Dify, Continue.dev and more. Lets any agent framework submit to the P2PCLAW leaderboard.
Node.jsApache-2.0★ 4Few starsNo key
Shared engine for the benchmark-* family: runner, graders, model adapters, CLI, MCP server and HTTP API from one definition.
Hosted by authorMITFew starsNo key
MCPLink onlyFew stars
Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with DOCA_EXPERIMENTAL-marked C entry points that doca-bench loa
OfficialSkillApache-2.0★ 3.6k in collectionNo key
A developer assistant for go benchmarking and performance
SkillMIT★ 7No key
MCP server that gives AI tools visibility into connected USB hardware
SkillMITFew starsNo key
Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.
OfficialSkillMIT★ 40k in collectionNo key
A DSP workbench on the DataGrout gateway: scope, meter, spectrum, and agent-portable signal chains
SkillApache-2.0★ 1Few starsNo key
Find the agent-memory benchmark that fits your system in one offline command.
SkillMITFew starsNo key
MCP connector for BenchFleet: let AI agents use your real Android phones safely, with permissions, approvals and an audit log.
MCPLink onlyFew stars
The home for your AI agents. Live dashboard, public profiles, README badges, LLM eval, and failure insights — one line of code.
Hosted by authorMITFew starsNo key
Autonomous AI Agent Evaluation Platform for Penetration Testing
SkillMIT★ 2Few starsNo key
Rollback Recovery: Does the agent notice its own bad action, repair it and say so?
Node.jsMITFew starsNo key
Capture private, reproducible AI coding benchmark cases from real repository work.
SkillMIT★ 5No key
Agent skill for designing and red-teaming AI benchmarks and evals, with a scorer attack battery, judge meta-evaluation, and power analysis.
SkillMIT★ 2Few starsNo key
Claude Code skill: build a scientific ML benchmark per the MLCommons Science Benchmarks Ontology, then package it as a Codabench competition bundle.
SkillApache-2.0★ 5No key
BenchClaw 是面向 OpenClaw Agent 的自动化基准评测系统，包含完整的题目下发、执行、 打分、报表生成与热更新分发能力。当用户想评测 AI Agent 能力、跑基准测试、测试 Agent 完成任务的得分、验证 Agent 输出文件、生成评测报告、或自动更新客户端程序时使用。
SkillMIT★ 8No key
Self-hosted panel gateway for LLMs: ask a collection of models at once, keep every answer side by side, rotate explorer models in, and let your verdicts pick the next panel. OpenAI, Anthropic, Gemini
Node.jsMIT★ 1Few starsNo key
Benchmark-aware HAICo skill for divergent→convergent Human-AI creative workflows
SkillMIT★ 2Few starsNo key
Who stands behind it
