Generate and verify Ed25519-signed receipts for every AI agent action with local-first verification. Built for developers who need cryptographic proof of agent decisions without external dependencies.
io.github.webaesbyamin/agent-receipts
Local install
STDIO
No auth required
How models use it and what it is built for.
Generate and verify Ed25519-signed receipts for every AI agent action with local-first verification. Built for developers who need cryptographic proof of agent decisions without external dependencies.
Local install — runs as a subprocess.
Where to find authoritative docs and source for Webaesbyamin Agent Receipts.
Paste any of these into Agent Studio after connecting Webaesbyamin Agent Receipts.
Common questions about connecting and running Webaesbyamin Agent Receipts.
What is an agent receipt and why would I need one?
An agent receipt is a cryptographically signed record of an AI agent action, proving what the agent did and when. You need it for audit trails, compliance, or verifying agent behavior hasn't been tampered with.
Do I need a server or external service to verify receipts?
No. Agent Receipts is local-first—verification happens entirely on your machine using Ed25519 public keys. No external dependencies or server calls required.
How do I set up the MCP server?
Install via `npx @agent-receipts/mcp-server@0.2.11` and connect it to your MCP client over stdio. You'll need to manage your own Ed25519 keypairs for signing.
Can I use this with any AI agent framework?
Yes, as long as your framework supports MCP servers over stdio transport. The server provides signing and verification tools that any agent can call.
What happens if a receipt signature doesn't verify?
A failed verification means the receipt or its data has been modified after signing. You should treat it as invalid and investigate the source of the tampering.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams