Self-hostable runtime for persistent autonomous coding agents — KVM-isolated VMs (or rootless containers), A2A-protocol executor with signed AgentCard discovery, AIWG mission dispatch, web dashboard, virtiofs shared storage. Runs on your hardware; no hosted control plane.

Curated directory of AI agents, agent cards, runtime endpoints, container images, and contribution-ready metadata.

OpenClaw Skill for agent discovery, Agent Cards, ITINAI publishing, and A2A delegation

Example A2A agent implementations with security best practices and input validation

VS Code developer tool for MCP health monitoring, Debug Recorder session history, and A2A agent exploration.

apcore-a2a acts as a thin, protocol-specific layer on top of `apcore-python`. It maps A2A concepts to apcore primitives

Official CapiscIO GitHub Action to validate A2A (Agent-to-Agent) Agent Cards. Features schema validation, cryptographic verification, and live endpoint testing with 3D quality scoring.

Structured identity card (agent.json + AGENT.md) for AI agents. A draft pattern.

Free CLI to scan AI-agent readiness (12/33 signals, MIT). Bad score? Get ready-to-install ZIP fix-pack with llms.txt, schema, A2A, MCP for $1/$29/$99 at agentfix.pro.

SRAO Stage 2-3: Agent capability graph construction. Decompose SRM into atomic task DAGs, map to 6 agent categories, output Agent Cards and capability graphs.

Making agentic AI transparent, auditable and controllable — one card at a time.

Know Your Agent — An open standard for AI agent identity, compliance, and auditability

Publish your AI agent once. Any other agent can discover it, request access, and connect, without you lifting a finger.

A Postman for the Agent2Agent (A2A) protocol — validate Agent Cards (spec v0.2.5) and run live tasks against any A2A agent.

Aggregate Kinetic Gain disclosure JSON documents (Agent Cards, Tool Cards, AEO docs, Incident Cards, ...) into a /.well-known/index.json with integrity findings (duplicate ids, missing versions, broken cross-references).

End-to-end validator for A2A Protocol Agent Cards — fetches well-known endpoints, validates structure, and classifies 12 capability categories.

Audit your A2A agent card across L1-L4 trust dimensions on every PR. GitHub Action wrapping @agentlair/a2a-trust-audit.

Public CLOCKIN AI skill console kit: SKILL.md workflows, metadata, safety boundaries, and contribution notes.

Bidirectional protocol-metadata translator between Google A2A (Agent-to-Agent) and the Model Context Protocol (MCP). MCP server.json + tools/list ↔ A2A AgentCard. Pure transform; closes the lane #4 gap.

When AI agents browse a site that doesn't publish machine-readable metadata or APIs, they fall back to scraping HTML, guessing endpoints, and retrying. That burns 5-100x more tokens per session and silently inflates the cost of every agent interaction. BotVisibility runs 55 automated checks across 5 levels.