by CLIRank
API directory scored for CLI and AI agent use. Search 420+ APIs by capability, read integration reports, find what works headless.
https://clirank.devok 5 h ago
Evaluate model or agent outputs.
API directory scored for CLI and AI agent use. Search 420+ APIs by capability, read integration reports, find what works headless.
Eleven MCP tools for catalog discovery and autonomous Agent Arena drills. Connect over HTTPS or run the same server over stdio with 'npx -y @vibeinfra/mcp-server'.
Official public-data caches sold per pull via x402/USDC on Base.
Agent Skill ROI Registry & Benchmarking. It sells skills for log triage and repository mapping.
Sovereign AI platform for travel, luxury UHNW, and industrial wholesale B2A execution.
Turns billionaire and trillionaire fortunes into tangible, personalized, quotable comparisons.
Find shopping deals, earn cashback, and redeem rewards across retail, dining, and travel brands.
Score inbound recruiter and sales pitches on relevance, specificity, cadence and spam signals.
Read-only FalkorDB tools for cross-bank AML investigations: rings, money paths, echo-proof claims.
Read-only evidence reports on AI agents: search, fetch a report, check trust. Not a certification.
AgentX is a social network for AI agents: agents register an identity, post, message each other and build a reputation. Most features are a REST API, described for agents at https://api.agentx.social/.well-known/skill.md. MCP hosts can use the agentx-social-mcp server and OpenClaw or Hermes agents …
PrMaat — AI agent identity, multi-agent collaboration rooms, and platform-attested model claims. Any A2A agent can join rooms, exchange messages, and build verifiable reputation.
MCP server unit testing, end to end (e2e) testing, and server evals
GitHub Action for evaluating MCP server tool calls using LLM-based scoring
Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.
🦾 MONSTER ENGINEER v2 - Ultimate AI CLI with 63 Skills, 12 Superpowers, 14 Agents. Multi-Agent Orchestration, Cost-Aware, Security Scorecard, Parallel-First.
Observability and enforcement for AI agent harnesses. 40 built-in policies hooked into 12 of them — Claude Code, Codex, Cursor, Hermes, OpenClaw and more — blocking the tool call before it runs. Local dashboard included, no account needed.
Cyber-first freestyle local AI agent
Run, watch, and meter coding agents — Claude Code, OpenCode, Kiro, Codex CLI, Gemini CLI, Prime Agent — with normalized events, cost accounting, A/B experiment/variant comparison, external run sources, and replayable run artifacts.
终端编码 agent:LLM + tool-call 循环 + 流式输出(含思考)+ 27 个工具,接任意 OpenAI 兼容后端。