Memory API for AI Agents

Your agents forget
everything. Fix that.

Persistent memory in 3 API calls. Store, search, and recall—with Ebbinghaus decay scoring that lets memories fade naturally, just like the real thing.

Simple by design

No SDKs to install. No schemas to define. Just REST.

POST /v1/memories POST
curl -X POST https://api.smara.io/v1/memories \
  -H "Authorization: Bearer smara_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "userId":  "user_42",
    "content": "Prefers dark mode. Uses vim keybindings.",
    "tags":    ["preferences", "editor"]
  }'
Response
{ "id": "mem_8f3a...", "decayScore": 1.0, "status": "stored" }
GET /v1/users/:userId/context GET
curl https://api.smara.io/v1/users/user_42/context \
  -H "Authorization: Bearer smara_your_key"
Response — full user context, ranked by relevance × decay
{ "userId": "user_42",
  "memoryCount": 23,
  "context": [
    { "content": "Prefers dark mode. Uses vim keybindings.", "score": 0.96 },
    { "content": "Working on a Rust CLI tool for log parsing", "score": 0.89 }
  ] }

Memory that behaves
like memory

Ebbinghaus decay

Memories lose weight over time using a decay curve modeled on human forgetting. Recent memories surface first. Old, unreinforced memories fade—but never disappear.

Contradiction detection

When a new memory contradicts an existing one (0.94–0.985 cosine similarity), the old memory is soft-deleted automatically. Your agent's knowledge stays consistent.

Vector search

1024-dimensional embeddings via Voyage AI. Semantic search that understands meaning, not just keywords. Powered by pgvector for production-grade performance.

Plain REST

No SDKs, no GraphQL, no WebSockets. Just HTTP with JSON. If you can write a curl command, you can integrate Smara in under five minutes.

Start free.
Scale when you need to.

Free
$0
For prototyping and side projects
  • 10,000 memories
  • Full API access
  • Decay scoring
  • Community support
Join waitlist
Pro
$99/mo
For teams shipping at scale
  • Unlimited memories
  • Dedicated embedding queue
  • Custom retention policies
  • Slack support + SLA
Join waitlist

Get early access

We're onboarding developers now. Drop your email and we'll send you an API key.

No spam. Just your API key when it's ready.