MCP servers and skills: search, filter by where they run, and compare.
MCP server for measured local-LLM benchmarks from the AGmind claim registry — AMD Strix Halo (Ryzen AI Max+ 395) llama.cpp numbers today, NVIDIA DGX Spark on the bench. search_claims, get_claim, list_
Node.jsApache-2.0★ 4Few starsNo key
Benchmark harness for AI-generated 3D browser games — same brief, same tools, 8 models, 24 playable builds.
SkillMIT★ 9No key
TokenMark MCP server and CLI: measured local-LLM speeds and model picks for Strix Halo, DGX Spark and Mac
Node.jsMITFew starsNo key
An operating-agent calibration benchmark — measures whether an LLM agent makes correct operating decisions (not whether it can write code).
Node.jsMITFew starsNo key
Put your AI agent in command of a nation in a real-time world war on a 3D globe. MCP server, starter bots and an LLM agent for any model.
Node.jsMITFew starsNo key
MCP server for RealRun: independent AI model test results on everyday tasks
Node.jsMITFew starsNo key
Benchmark LLMs on your own scenarios with a multi-judge panel. Full MCP server (tools, resources, prompts, progress) plus local GUI, CLI, and desktop app. One OpenRouter key.
Node.jsMITFew starsNo key
decrease token in figma mcp by using DTF!
Node.jsMIT★ 3Few starsNo key
JavaScript MCP Server — agent/service discovery and registry
Node.jsMITFew starsNo key
perf-skills is a structured knowledge base that gives AI coding assistants deep, opinionated expertise in performance testing. It works with any AI tool that supports custom instructions, rules, or sk
SkillMIT★ 17No key
MCP server that scans Solidity repos through a 7-gate verification framework (Al-Mizaan) to cut LLM false positives, benchmarked against Slither; free pattern-search from 1,032 reconciled Sherlock fin
Node.jsMIT★ 9No key
基于 Vue 3 + Element Plus 的企业级中后台 CRUD 组件库 — 配置化驱动表单、表格、弹窗全链路联动
Node.jsMIT★ 14No key
Titan-Memory , it is a memory system that is not only for memory, but it also has built-in safety guardrails, circuit-breakers, semantic adapters, and drift protection. Everything you need to run Agen
Node.jsApache-2.0★ 5No key
An unofficial MCP server for the Artificial Analysis API
Node.jsMIT★ 9No 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
Delegate work from Claude Code to any external LLM — and benchmark which ones you can trust with what
SkillMIT★ 1Few starsNo key
Local-first, read-only profiler for AI coding agents.
Node.jsMIT★ 9No key
Benchmark local LLM models: speed, quality, and hardware fitness scoring. CLI, MCP server, and IDE plugins.
Node.jsApache-2.0★ 8No key
Lets Claude Code and Cursor drive Chrome. Blind benchmark vs agent-browser: -33% tokens, -33% cost, -24% tool calls, +48% speed, 30/30. Direct CDP, a11y-tree refs, server-side plan executor. MIT, no p
Node.jsMIT★ 19No key
A memory for coding agents: pin what you were told, journal what you did, sleep when your head is full. pi extension, Claude Code plugin, Codex/Copilot hooks, and the benchmark behind it.
SkillMIT★ 6No key
The luck-robust benchmark for trading agents.
Node.jsApache-2.0★ 6No key
Same answer, fewer tokens — KO-first LLM output-compression skill for Claude Code & Codex. A Korean-native caveman alternative, measured on real session output_tokens.
SkillMIT★ 6No key
Cross-session memory and recall for AI agents — git-synced knowledge base, hybrid semantic+TF-IDF search, auto-distillation with secrets scrubbing
Node.jsMIT★ 19No key
MCP server for German & EU law. Verified, citable legal context for any LLM. Daily updates from official sources, hosted in Germany
Node.jsMIT★ 11Needs a key
Who stands behind it
