Explore
MCP servers and skills: search, filter by where they run, and compare.
rigbase-datagetrigbase
Hosted
MCP servers and skills: search, filter by where they run, and compare.
Measured local-LLM tok/s on home hardware (CC BY 4.0) - from getrigbase.com
Hosted by authorCC-BY-4.0Few starsNo key
MCP server for RealRun: independent AI model test results on everyday tasks
Node.jsMITFew starsNo key
Chaos engineering for MCP agents: a stdio proxy that injects timeouts, errors, malformed JSON, schema drift and stale results, plus a benchmark that measures how agents recover.
PythonMITFew starsNo key
🛡️ BLA (Blind LLM Agents) — Adversarial defense shield that protects binaries, Electron apps, JS bundles, Python, and WebAssembly against AI reverse-engineering agents like REA. Poison -> Exhaust ->
Node.jsMIT★ 4.1kNo key
🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more.
SkillApache-2.0★ 594No key
Measure and safely cut the token cost of LLM tool and MCP schemas, with equivalence checking and a CI gate.
PythonMIT★ 50No key
High-performance, memory-efficient Rust web crawler & content extraction engine for AI agents and RAG. Adaptive crawling, clean Markdown, structured data, PDF/RSS parsing, browser rendering, Firecrawl
SkillAGPL-3.0★ 124No key
Open source GEO/AEO audit engine. Track brand visibility, citations & share-of-voice across ChatGPT, Perplexity, Claude & Gemini. Built-in CLI & MCP.
Node.jsMIT★ 35No key
Index a video once, query it cheaply with any LLM. Open model-free video context format (.vctx) + MCP server + accuracy-per-dollar benchmark.
PythonApache-2.0★ 1Few starsNo key
A drawing duel game for AI agents. Paste one line into your agent and it plays a free practice match.
Hosted by authorMITFew starsNo key
Official SDKs for the AI Stupid Level Smart Router (benchmark-driven LLM router) and Data API: TypeScript, Python, Vercel AI SDK provider, MCP server, LangChain, n8n.
Node.jsMITFew starsNo key
Find where your agent breaks before your users do. Seeded tool-use tasks checked by code, on your own tools.
PythonMIT★ 2Few starsNo key
Cut browser use cost by about 25% in Claude Code: fresh runner subagent, bulk reads, three guards and a token meter. One npx command
Node.jsMIT★ 5No key
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation. Reproduction code.
SkillMIT★ 6No key
Rollback Recovery: Does the agent notice its own bad action, repair it and say so?
Node.jsMITFew starsNo key
SkillMIT★ 6No key
Independent tests of agent skills (SKILL.md): does it trigger, does it help, is it safe. Reproducible data and an npx CLI.
SkillApache-2.0★ 2Few starsNo key
Stop flooding your agent's prompt with MCP tools: MCPtoCodeMode puts every MCP server behind 3 tools and a sandbox, for Codex, Claude Code, Cursor, Grok, OpenCode, Pi, or any MCP client.
Node.jsMIT★ 9No key
Convergent deliberation loop for coding agents: multi-pass, coverage-gated, append-only ledger review and planning. Claude Code, Codex, OpenClaw.
SkillMIT★ 2Few 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
Universal JIT Skills & Hierarchical Context Tiering Optimizer (L1/L2/L3) for AI Coding Agents
SkillMIT★ 2Few starsNo key
Cache-, quota- and capability-aware LLM router (Auto Router behind decision-models-router on AntSeed)
SkillMIT★ 2Few starsNo key
Same catalog via agents-over-MCP vs today's DOM scraping: 79% fewer bytes, 42% fewer tokens on a 150-product benchmark
Hosted by authorMITFew starsNo key
Who stands behind it
