Docs
From your first Episodic Memory to production-grade memory in a single afternoon. Pick a section below — or jump straight into the playground if you prefer learning by doing.
GET STARTED
Installation
Run "make dev-up" to bring up Postgres, Kafka, Qdrant, Neo4j, the Go gateway, and the Python knowledge engine. The whole stack comes online in a few minutes on a laptop.
Quickstart
Create an organization, create a project, mint an API key, and post your first Episodic Memory. The first retrieval call comes back within seconds.
Chat
Send a message, watch entities land in the knowledge graph, see the memory context the model used to ground its reply.
SDKS & INTEGRATIONS
Python
Integrate MemLab into your Python app with the official SDK.
Node.js (coming soon)
Add MemLab to your Node.js and TypeScript projects.
cURL
Call the MemLab REST API directly from any language or shell.
Claude plugin (coming soon)
Give Claude long-term memory with the MemLab open plugin.
OpenAI plugin (coming soon)
Give OpenAI agents long-term memory with the MemLab open plugin.
MCP server (coming soon)
Connect any MCP-compatible client to MemLab's memory tools.
CORE CONCEPTS
Episodic Memory
The contextual record of ingestion: a chat turn, document, tool trace, or event. Episodic Memory gets extracted into facts, entities, and relations.
Semantic Memory
The structured fact and preference outputs of extraction. Each Semantic Memory carries a kind, an embedding, confidence, and provenance back to source Episodic Memory.
Entity graph
Bi-temporal explorer infrastructure for people, organizations, and concepts. Facts have valid_at and invalid_at — stale beliefs are marked, not deleted.
Hybrid retrieval
Vector + graph + lexical search fan out in parallel. RRF fusion ranks the merged result set so the strongest signal wins.
API REFERENCE
POST /v1/episodic-memories
Ingest a single Episodic Memory. Returns an ID immediately; extraction happens asynchronously and you can poll status.
POST /v1/semantic-memories/search
Hybrid search across vector, graph, and lexical engines. Returns a fused, ranked list with per-method method scores.
GET /v1/entities
List entities for the current project, with relation counts and recent mention counts.
POST /v1/feedback
Tell MemLab a memory was wrong, partially right, or worth boosting. Feedback events drive the relevance pruner and the dedup layer.
OPERATIONS
Multi-tenancy
Org and project scopes are enforced four layers deep. Postgres RLS, per-project Qdrant collections, partition-keyed Kafka, and signed gateway claims.
Observability
Every request and every Kafka message is traced end to end. Performance budgets are hard limits — sub-50ms p99 for ingest, sub-200ms p99 for retrieval.
Audit trails
Every memory mutation is append-only. You can answer "where did this answer come from" down to the original turn and the model run.