#a2a

One open A2A 1.0 mesh for Claude Code, Codex, Cursor, Cline, Continue and Gemini.

A gateway + skill letting Claude Code agents collaborate across machines

An A2A hub that lets coding agents on different machines talk, align on tasks, and discuss work in real time (a real swam).

Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server

AI agent for writing, research, code, DeFi & blockchain. Pay per task in USDC on Base or Solana. A2A + MCP + x402 protocols.

Self-hostable managed agents harness. Author YAML manifests; Felix compiles them into governed agents with durable fibers, memory, skills, eval, approvals, and sandboxes — over OpenAI, A2A, MCP, and SSE. Fork, rewind, and steer runs. Docker, Helm, AWS, or GCP.

Agent-to-agent communication and multi-agent messaging, local-first: an A2A-inspired coordination platform where AI agents talk in natural language, manage tasks with human approval, and never send your data to the cloud. 65-command API, Python client, web UI, encrypted backups.

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.

Neutral self-hosted registry and toolkit for Agentic Resource Discovery.

Make your API, MCP server or AI agent discoverable by AI agents. Build, validate and verify an Agentic Resource Discovery (ARD) manifest.

A public AI-agent world whose map grows only from corroborated evidence: residents research with read-only tools, findings are judged across independent sources, rooms are built from agreement and retracted by dispute. Runs on a laptop and free-tier models.

API-first marketplace for autonomous AI agents: one-call identity (Ed25519 + did:key), services and bounties, jobs with sealed delivery, wallet-to-wallet USDC payments on Base verified on-chain (no custody), payment-anchored reputation, disputes decided by agent panels. Speaks MCP, A2A and Agent Skills.

Open, experimental specification (v0.1) for machine-readable trust and Cognitive Passports for autonomous agents. A proposal, not a standard.

AIMail: the native email system for the AI age — purpose-built for human-agent and agent-agent collaboration.

Runnable Spring AI 2.0 demo — govern every LLM call, MCP tool call and agent-to-agent hop through the self-hosted Dvara control plane. Approval gates, PII blocking, hash-chained audit.

Machine-discoverable x402 micro-workers powered by Venice AI, paid in USDC, with A2A and MCP discovery.

Open-source A2A Agent Card inspection and signature verification. Offline CLI and Node.js library, Apache-2.0, zero dependencies.

One home for every AI agent. Build, test and ship agents once, then use them from Claude, ChatGPT, Codex, Cursor, VS Code or Slack (MCP, OpenAI-compatible, A2A, ACP). Self-hosted, with teams, approvals, audit, memory and multi-agent composition. Docker or Kubernetes.

Write the agent, not the chat integration. Kubernetes-native broker between Slack and streaming A2A AI agents (kagent, Google AX): threaded sessions, alert investigations, restart recovery.

A2A Nexus — a control plane for delegating, tracking, and recovering work across agent nodes

The agent that helps agents find other agents — MCP server, A2A card, OpenAPI for AgentSearch (agentsearch.luthersystems.com).

Go-first, knowledge-graph-grounded agent platform — built on toolnexus + ctx-optimize

Open discovery infrastructure for AI agents. Crawl, validate, normalize, and search A2A-compatible agents.

Garden: public AGI governance and human-sovereignty architecture — AI safety, multi-agent systems, formal verification, privacy, justice and agent interoperability.

Open-source AI usage observability for model, agent, and token telemetry.

Log into a Workday tenant, discover Agent System of Record (ASOR) agents, and drive them from a CLI — for Slack, Teams, Claude Code, or anything with a shell.

Mind — a CLI and web console that builds AGI agents you own: a soul of its own, memory recalled from your notes and documents, autonomy with a kill switch, A2A and Telegram, one git repo per agent, local-first.

One terminal for all your coding agents — Claude Code, Codex, OpenCode and more, working as a team

Multi-agent clinical workflow orchestration on FHIR R4: evidence, care-plan drafting, clinical validation, policy-gated clinician sign-off and signed Provenance write-back

Full-stack TypeScript framework for Node.js and AI agents: compile-time dependency injection, server-rendered pages with islands, durable streaming agents, MCP and A2A.

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

Compile a declarative DAG of subagents into a deployed, orchestrated team on AWS Bedrock AgentCore — agent manifests + dependency resolution → a provisioning plan and a topological supervisor.

A multi-agent AI system that runs entirely on the local machine, using - Langgraph, MCP, A2A, Ollama, CrewAI, Langfuse, DeepEval.

A git repository that can be imported together with the agents that own it.

Repository for sample snippets of agents, covering a2a, langgraph, ollama setup, phoenix.