Supermemory
Memory engine with API, app, browser extension, and MCP server. Extracts facts, tracks updates, resolves contradictions, auto-forgets expired info. Plugins for Claude Code, OpenCode, OpenClaw, Hermes.
At a glance
- Type
- Memory graph + extraction + RAG
- Tier
- T1
- Section
- Dedicated memory layers
- Created
- 2024-02
- Latest release
- no releases
- License
- MIT
- GitHub
- 22.4k★ +113/mo TypeScript
- Pricing
- OSS
- Funding
- $6M total Seed · 2025-10
Taxonomy
- storage
- graph
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- document
- governance
- opaque
- conflict
- llm-arbitrate
When to use
Optimised for: multi-channel capture (API, app, browser ext, MCP) + RAG over personal graph
Anti-fit: no anti-fit explicitly stated
Pros & cons
Pros
Simple universal API surface — wraps memory in a single SDK call without forcing extraction/retrieval choices; YC-backed.
Cons
Architectural opacity is the cost of simplicity — limited control over structure or eviction; small team.
Claims & capabilities
Reports #1 on LongMemEval, LoCoMo, and ConvoMem (self-reported, late 2025). Strong on Multi-Session (71.43%) and Temporal Reasoning (76.69%) on LongMemEval-S.
Technical surface
- API surface
- REST, SDK: Python, JS/TS
- Backend storage
- custom
- Deployment
- Both
- Embedding model
- multiple supported
- Multi-tenancy
- Enterprise: deploy in customer VPC for full tenant isolation; standard SaaS uses logical namespace per user/org
- MCP
- native (first-party) — claude-supermemory plugin + MCP
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Compare Supermemory with…
Similar systems
Other dedicated memory layers in the catalog, ranked by inbound references.
- Mem0 T1
Universal memory layer for AI agents. Three concurrent stores (vector + graph + KV); LLM-extracted facts; concurrent retrieval via ThreadPoolExecutor.
- Zep & Graphiti T1
Bi-temporal knowledge graph (event time + ingestion time). Strong on chronological reasoning and contradiction tracking. Graphiti is the open-source core.
- Cognee T1
"Extract–Cognify–Load" pipeline that turns raw input into a typed, queryable knowledge graph for agent recall.
- Hindsight (Vectorize) T1
Standalone memory service from Vectorize. Open source. Biomimetic four-network design (World, Bank, Observation, Opinion). Ships an MCP memory server.
- Memvid T2
Single-file memory layer (one .mv2 file). No DB, no server. Append-only sequence of immutable Smart Frames with timestamps + checksums. Native Rust core (rewritten from Python).
- AI Singapore SEA-LION T2
SEA-LION-Embedding (March 2026): retrieval + reranking models contrastively trained on 245M text pairs across 10 SE Asian languages. SEA-BED benchmark (169 datasets). SEA-LION v4 (Gemma-based) at 128K context with native function calling.
Related systems
Referenced by (1)
- claude-supermemory builds on — Claude Code plugin packaging Supermemory for per-project memory.