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.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 74 cited facts, 4 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Memory graph + extraction + RAG vendor fix
- Tier
- T1
- Section
- Dedicated memory layers
- Latest release
- server-v0.0.9 (2026-10-12); Python SDK v5.0.0 (2026-10-06) repo fix
- Funding
- $6M total Seed · 2025-10 third-party fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- SDK languages
- python, rest, typescript vendor fix
- Protocols
- mcp-server repo fix
- Compliance
- gdpr, hipaa, soc2-type2 vendor fix
- Developer activity
- OpenRank 9.65 (12-mo avg 9.67) · 54 participants — 2026-09 third-party fix
Memory 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
Alternatives to Supermemory → live options ranked by shared design, licence, hosting and MCP support
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.
- Letta / MemGPT T1
Originated as MemGPT (UC Berkeley), where the model pages its own memory between context, recall and archival tiers. The product now centres on Letta Code, a stateful agent harness whose agents rewrite their own memory, skills and prompts over time.
- Memori T2
Structured, persistent memory layer for AI agents. Open source.
Sources (73 cited facts, 4 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Memory graph + extraction + RAG vendor
- What it does & what's distinct Memory engine with API, app, browser extension, and MCP server. Extracts facts, tracks u… vendor
- Claims / benefits Reports #1 on LongMemEval, LoCoMo, and ConvoMem (self-reported, late 2025). Strong on Mu… vendor
- Modalities text vendor
- Created 2024-02 vendor
- Latest release server-v0.0.9 (2026-10-12); Python SDK v5.0.0 (2026-10-06) repo
- License MIT repo
- GitHub supermemoryai/supermemory — ~31.3k stars, last commit 2026-10 repo
- Mindshare 1 inbound vendor
- Funding $6M total Seed · 2025-10 third-party
- Customers / scale 1-10 ppl a16z-backed Cluely, Montra, Scira, Composio/Rube, Rets third-party
- Pricing OSS vendor
- Compliance SOC 2; HIPAA; GDPR (per supermemory.ai security page) vendor
- Data handling Does not train models on customer data vendor
- Deployment Both repo
- HQ US repo
- Founders / pedigree 19-year-old solo founder Dhravya Shah (IIT dropout from Mumbai; built apps to 1M+ users) third-party
- Memory volume / scale no scale claim vendor
- Performance 71.43% LMES (MultiSession) 76.69% LMES (Temporal Reasoning) vendor
- Code/weights release Active — last commit 2026-05 · 22,531★ repo
- API surface REST, SDK: Python, JS/TS vendor
- Backend storage custom vendor
- Multi-tenancy Enterprise: deploy in customer VPC for full tenant isolation; standard SaaS uses logical… vendor
- Encryption AES-256 at rest, TLS in transit; SOC 2, HIPAA, and GDPR compliant; Enterprise VPC deploy… vendor
- Embedding model multiple supported vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites repo
- MCP support native (first-party) — claude-supermemory plugin + MCP repo
- Webhooks / events webhooks supported vendor
- Import / export JSON via REST; documents/URLs/raw text ingestion endpoints vendor
- Integration count 1 repo
- Orchestration both (single-agent default; multi-agent via space/container_tag) vendor
- Programmatic control full CRUD + SDK + MCP server vendor
- Vendor benchmarks LMES self-reported #1 (Multi-Session 71.43% / Temporal 76.69%); LoCoMo #1 self-reported;… vendor
- Pricing specifics per-memory + tier flat-rate: Free 100 memories; Pro $15/mo; Enterprise custom vendor
- Validated verticals consumer / individual, knowledge management, RAG agents vendor
- Time to running <10min (hosted SaaS) or <1hr (self-host) vendor
- Anti-fit no anti-fit explicitly stated vendor
- Optimised for multi-channel capture (API, app, browser ext, MCP) + RAG over personal graph vendor
- Adjacent infrastructure BYO LLM; bundled vector + graph vendor
- Pros Simple universal API surface — wraps memory in a single SDK call without forcing extract… vendor
- Cons Architectural opacity is the cost of simplicity — limited control over structure or evic… vendor
- Project & sources GitHub supermemoryai/supermemory research page org repos (26) SMFS (agent filesystem) vendor
- cost-token-budget no vendor
- cost-prompt-caching no vendor
- cost-semantic-caching no vendor
- cost-batching no vendor
- cost-model-routing no vendor
- cost-streaming-only no vendor
- cost-observability-cost-attribution no vendor
- eval-langsmith-evals no vendor
- eval-braintrust no vendor
- eval-weights-and-biases-agent no vendor
- eval-helicone-evals no vendor
- eval-custom-test-harness no vendor
- eval-human-loop no vendor
- eval-production-traffic-replay no vendor
- commit-trajectory [{"ym":"2024-07","cum":796},{"ym":"2024-08","cum":932},{"ym":"2024-09","cum":948},{"ym":… repo
- download-trajectory [{"ym":"2023-05","monthly":0,"cum":0},{"ym":"2023-06","monthly":0,"cum":0},{"ym":"2023-0… registry
- cost-input-usd-per-mtok 0 vendor
- cost-output-usd-per-mtok 0 vendor
- cost-tier free vendor
- cost-pricing-model free-tier vendor
- cost-last-verified 2026-06-29 vendor
- architecture-deployment-locus hybrid vendor
- licensing-bucket open-source repo
- positioning-platform-vs-product platform vendor
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":137.94,"as_of":"2026-09","openrank_12mo":9.67,"openrank_current":9.65,"parti… third-party
- compliance-certifications gdpr,hipaa,soc2-type2 vendor
- sdk-languages python,rest,typescript vendor
- protocol-support mcp-server repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
Related systems
Referenced by (2)
- claude-supermemory builds on — Claude Code plugin packaging Supermemory for per-project memory.
- Vercel AI SDK integrates with — AI SDK docs have a Supermemory community provider page. (verified 2026-10-29)