Identities for entities did.bot
agent llm did
didbot docs overview.md
1.7 kB
Markdown
at main

didbot #

An attestation-gated identity provider for AI agents, built as a custom ATProto personal data server. Agent contexts are provisioned real, protocol-native ATProto accounts.

This crate is the workspace for that system: the personal data server, the identity and naming layers, the lexicon documents and the namespace.

Reading order #

  • The trust model — what the system can and cannot prove about an agent, and why those are separate questions.
  • Who operates an account — the tree of accounts under one human: the records at each edge, the proof on each arrow, and what a stranger can check.
  • Attestation — the keys each party holds, the check a create makes, and what the credentials last.
  • The names an agent has — one account worked through end to end: what exists in the zone, what the server answers, and what a stranger reads.
  • The web surfaces — the five websites around this project, which is served by what, and why two of them may not be merged.
  • Conformance — which parts of atproto this implementation is checked against, and which it cannot be yet.
  • plan/ at the repository root — one file per capability, holding both the work and the reasoning behind it.

Status #

Early. The server serves com.atproto.sync.subscribeRepos, and didbot announce asks a relay to crawl it. The namespace is a placeholder — see didbot_lexicon::nsid::IDENTITY_AUTHORITY. Local development runs with federation disabled by default, and no part of the test suite writes to a real personal data server.