Pay-per-call data agent: crypto market signal, web-content reader, and GitHub-repo SEO audit. Each skill is settled per call via x402 (USDC on Base) — no API key, no signup.
Git hosting, repos, issues and PRs.
Pay-per-call data agent: crypto market signal, web-content reader, and GitHub-repo SEO audit. Each skill is settled per call via x402 (USDC on Base) — no API key, no signup.
Read-only discovery agent for local-ydb-toolkit install guidance, workflow routing, public docs, and agent-readiness metadata. It does not execute local-ydb operations.
Governance for AI agents that you can prove — a composable suite. Witness seals and anchors decisions; C2MD turns compliance standards into governance agents can follow; ACP holds governance in git and reviews, tests and signs changes; Onboarding admits agents and issues verifiable credentials; hum…
Project management agent — workspaces, projects, issues, sprints, kanban boards, and team collaboration for software and product teams
OSC ↔ MIDI bridge — 964 synthesizers and DAWs. A MIDI MCP and OSC MCP for controlling them.
Dataify 数据采集 MCP 服务,覆盖 Amazon、Google、YouTube、TikTok 等平台的采集与搜索
Load test your app on a real server from your agent. Get p95, errors and what ran out first.
Correlate GitHub releases with Sentry issues and PagerDuty incidents.
AI marketplace for agents to find paid work and trade digital services via MCP and x402.
Measured weekly data on Claude Code and coding agents: costs, plugins, MCP registry, npm, HN, issues
8 CIPHER tools — Solana scan, breach check, Jito, FRED, Drift, repo health, more. x402-paid on Base.
Signed EOL dates, exploited CVEs and LLM prices; pay per call in USDC, no account, no daily cap.
Audit GitHub Actions workflows for script injection, unpinned actions and missing permissions.
GitLab MCP server for projects, merge requests, issues, pipelines, wiki, releases, and more.
Add MCP servers to your favorite coding agents with a single command.
The agentic meta-harness — freeze the model, evolve the harness. An open runtime that routes each query to the cost-optimal model, evolves its own harness (planner/context/reviewer/retry/tool/memory/score policy) and autonomously repairs code, then orches
MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + `npx metaharness` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM, Prime Agent.
GitHub Action for evaluating MCP server tool calls using LLM-based scoring
Reusable project context and specialist workflows for the AI tools you already use. AIWG places agents, skills, commands, and rules in provider-readable locations, with optional utilities for artifact memory, workflow orchestration, recovery, and discover
CLI and agent skills for managing GitHub PR review comments. List, filter, reply, and watch for bot findings.