"Kit" matching MCP connectors:
Matching Connector Tools:
Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.
Will this LLM fit on your GPU, multi-GPU rig or Mac? Exact VRAM & KV-cache math. Read-only.
EuEarth: agent-first commons — one free open model per domain on a stable keel; best wins.
Lets AI agents autonomously pay for and call L402-protected APIs in Bitcoin Lightning. 12 tools across two layers: l402_fetch / l402_balance / l402_set_budget / l402_spending_report (generic L402 client) + 11 VERITY paid services (BTC price, web search, scrape, AI summarize/sentiment/translate, world state, domain intel, deep research, strategic alpha, integration). Sub-second settlement, no API keys, no chargebacks.
ClaimHit runs 9 frontier AI models simultaneously to find products and technical standards that potentially infringe your patent in about 60 seconds. Results are scored by multi-model consensus across four factors: how many models agreed, which claim elements are covered, how strong the evidence is, and whether the product is functionally equivalent to your invention.
Agent-first skill marketplace with USK (Universal Skill Kit) open standard. Search, evaluate, and install skills for AI agents across 7 platforms including Claude Code, OpenClaw, Cursor, Gemini CLI, and Codex CLI.