Documentation
Four steps to a first call.
Smara is a REST API. There is no SDK you have to adopt and no agent framework you have to move to — if it can send an HTTP request with a bearer token, it can use Smara.
Quickstart
Create an account
Sign up with email or Google. Your first sign-in creates a tenant and makes you its owner.
Sign upIssue an API key
From the portal, create a key and copy the secret. It is shown exactly once and stored only as a hash.
API keysAssemble your first context
Call POST /v1/context with an agent id and a query. On a fresh tenant it returns an empty set — that is the correct answer, and it means auth works.
ReferenceWrite what happens
Append turns, tool calls and outcomes to POST /v1/episodes. Consolidation picks them up from there — no further wiring.
How consolidation worksAuthentication
Two callers, two credentials.
Agents call the data plane with a per-tenant API key: Authorization: Bearer smara_live_…. A key resolves to exactly one tenant and carries scopes such as memory:read and memory:write.
People call the control plane — tenants, members, keys — with a Firebase ID token from the portal session. Control-plane endpoints will not accept an API key, and data-plane endpoints will not accept an ID token.
Secrets are shown once at creation and stored only as a SHA-256 hash. There is no endpoint that returns a key secret, including to the person who created it. Lose it and you revoke and reissue.
export SMARA_API_URL="https://<your-memory-api-host>"
export SMARA_API_KEY="smara_live_…"
curl "$SMARA_API_URL/v1/context" \
-H "Authorization: Bearer $SMARA_API_KEY" \
-H "Content-Type: application/json" \
-d '{"agent_id":"support-copilot","query":"hello","token_budget":1000}'curl "$SMARA_API_URL/v1/episodes" \
-H "Authorization: Bearer $SMARA_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"session_id": "sess_9f21",
"agent_id": "support-copilot",
"kind": "tool_call",
"payload": { "tool": "crm.lookup", "args": { "org": "acme" } }
}'What is here today
The interactive API reference is live and generated from the service itself. Long-form guides — consolidation tuning, graph modelling, retention policy — are still being written. Until they land, the reference plus the architecture page are the complete picture.