agent-cards
Agent Cards define the verifiable identity and capabilities of autonomous agents — binding ENS names to verbs, schemas, x402 entrypoints, and discovery metadata. Strictly validated, ERC-8004 aligned, and built for deterministic interoperability across runtimes and agent networks.
In the AI payments ecosystem
agent-cards is an early-stage JavaScript project in the AI payments / x402 ecosystem, focused on agent-discovery, agent-identity, agents, ens. It currently has 3 GitHub stars and 1 forks, and sits alongside related tools like protocol-commons, protocol-commercial, commandlayer-org, runtime, daydreams, mainnet-x402-facilitator.
Deprecated: CommandLayer Agent Cards
This repository is deprecated and should be treated as an archived historical source.
Agent card and discovery work is being consolidated around the current CLAS, Agent SDK, and public verifier direction.
Current direction
CommandLayer is consolidating around CLAS and verifiable action receipts.
Going forward:
- canonical CLAS/spec work lives in
commandlayer/clas - active SDK work lives in
commandlayer/agent-sdk - public verification/docs live in
commandlayer/commandlayer-org - public receipt verification reference lives in
commandlayer/verifyagent - private commercial/admin/payment/backend work lives in
commandlayer/commercial
Do not use this repository as the active source of truth for new CommandLayer integrations.
Why this repo is being archived
Agent Cards previously acted as discovery and binding artifacts for older Commons and Commercial schema surfaces.
Those schema mirrors and commercial/public routing surfaces are being retired from the public repo structure. The current direction is to keep the public story focused on CLAS receipts, verifier surfaces, and SDK integration.
This repository is retained only so older references and historical card/discovery work remain understandable.
Historical scope
This repository previously contained:
- agent card examples
- card manifests
- schema binding experiments
- Commons and Commercial routing assumptions
- discovery metadata for older agent namespace experiments
New integrations should not depend on this repository directly.
Recommended path
Use the current CommandLayer repos instead:
- CLAS/spec: https://github.com/commandlayer/clas
- Agent SDK: https://github.com/commandlayer/agent-sdk
- Public verifier/docs: https://github.com/commandlayer/commandlayer-org
- VerifyAgent reference: https://github.com/commandlayer/verifyagent
Status
- Repository status: deprecated / archive candidate
- New development: no
- New integrations: use CLAS + Agent SDK
- Historical purpose: card/discovery experiments for earlier CommandLayer schema surfaces
Similar projects
Protocol-Commons standardizes machine intent — canonical verbs and typed payloads that let autonomous agents interoperate reliably across chains, systems, and marketplaces. Strict schema governance, ERC-8004 aligned discovery, and native x402 execution support.
Protocol-Commercial defines economic machine intent and the associated x402 execution endpoints. It enables trustless value transfer, fulfillment, and commercial guarantees between autonomous agents — strictly validated, ERC-8004 discoverable, and aligned to Protocol-Commons semantics and Agent-Card identity.
CommandLayer — a protocol for verifiable agent execution, producing signed receipts that prove what ran.
CommandLayer Runtime: a reference HTTP runtime for CommandLayer verbs that validates schemas and issues signed, verifiable receipts using ENS key discovery and IPFS-backed schemas.
Daydreams is a set of tools for building agents for commerce
Gas-sponsored USDC transfers on Ethereum mainnet via ERC-20 permit signatures
More AI Agents projects
All AI Agents projects →
Your AI trading terminal assistant for US stocks, commodities, forex, and crypto.
The agent-native LLM router for autonomous agents. 55+ models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.
A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.
