Why agents love Obelisk
Agents act on people's behalf, and the softest part of most systems is "log in". Obelisk makes identity machine-native: a discoverable contract, standards-based auth (OpenID Connect), predictable JSON, and tamper-evident receipts so an agent's actions are verifiable after the fact.
Start here
- One manifest:
GET /apidescribes every surface — method, path, auth, params — in machine-readable JSON. - The agent interface:
GET /agent(also at/.well-known/obelisk-agent) returns the deeper machine contract — capabilities, callable actions with exact body shapes, and the SDK pointer. - Standards auth: OpenID Connect discovery + JWKS. Use the authorization-code + PKCE flow to obtain tokens.
- Contract JSON: account, organization, API-manifest, and changelog surfaces negotiate JSON; editorial pages remain HTML.
Authenticating as an agent
Agents authenticate the same way apps do: the user signs in with a passkey via Obelisk; your agent receives an OIDC access token. Present it as Authorization: Bearer <token> to call protected APIs on the user's behalf. For long-running agents, opt in to DPoP (RFC 9449) at the token endpoint — the token binds to your agent's own P-256 key, so even a leaked token is inert without it.
The auth vocabulary is a small closed set an agent can branch on: none, session (cookie or body token), bearer (OIDC), owner (org admin). Errors are uniform: { ok:false, reason, message }.
Per-project memory
Each project gets a per-user profile slice it owns, scoped to its OIDC client — perfect for agent state: GET/POST /api/project-profile with the user's access token. One identity underneath; your project's data layered on top. See the contract.
Verifiable by design
Every sensitive action chains a signed receipt, so an agent's behavior is auditable and non-repudiable. Combined with passkey-first, uncopyable credentials, Obelisk gives autonomous systems a foundation they can be trusted on. See Security.
Be a good citizen
Respect rate limits, scan only sites you're authorized to, and follow the Acceptable Use Policy. Good-faith research is protected under our disclosure policy.