Memobase
https://github.com/memodb-io/memobase
User-profile-based long-term memory. Per-user profile + event timeline. API + Python/Node/Go SDKs + MCP server. Profile-centric rather than fact-centric.
Active · Verified 2026-10-29 · fresh as of 2026-10-29 · 58 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- User profile + event timeline repo fix
- Tier
- T2
- Section
- Dedicated memory layers
- Latest release
- memobase Python SDK 0.0.27 (PyPI, 2025-11-08); no tagged GitHub releases registry fix
- License
- Apache-2.0 repo fix
- Pricing
- OSS self-hosted free (Apache-2.0); Memobase Cloud free and pay-as-you-go tiers advertised in the README, but memobase.io (incl. pricing and login) returns 404 and app.memobase.io is down as of 2026-10-29 repo fix
- Funding
- not applicable — not commercial fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- SDK languages
- go, python, rest, typescript repo fix
- Protocols
- mcp-server vendor fix
- Developer activity
- OpenRank 0.36 (12-mo avg 4.41) · 2 participants — 2026-09 third-party fix
Memory taxonomy
- storage
- relational
- retrieval
- injection
- persistence
- long-term
- update
- extraction
- unit
- profile
- governance
- inspectable
- conflict
- none
When to use
Optimised for: user-profile + event-timeline (companion-AI persona)
Anti-fit: not for non-Claude-Code clients (some are MCP-portable)
Pros & cons
Pros
User-profile-centric model is closer to how product teams think about user memory than fact-extraction approaches; cross-tool memory passport via MCP.
Cons
Smaller community than Mem0/Letta; profile-centric framing doesn't fit purely conversational use cases as well.
Claims & capabilities
Sub-100ms retrieval. Cross-tool memory passport for Claude / Cursor / MCP-compatible agents.
Technical surface
- API surface
- REST, SDK: Python, JS/TS
- Backend storage
- Postgres + pgvector
- Deployment
- Both (self-hosted Docker + Memobase Cloud managed)
- Embedding model
- multiple supported
- Multi-tenancy
- namespace (user_id)
- MCP
- native (first-party) — memobase MCP
- A2A
- not supported
- OpenTelemetry
- no
Alternatives to Memobase → 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 (57 cited facts, 1 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is User profile + event timeline repo
- What it does & what's distinct User-profile-based long-term memory. Per-user profile + event timeline. API + Python/Nod… repo
- Claims / benefits Sub-100ms retrieval. Cross-tool memory passport for Claude / Cursor / MCP-compatible age… repo
- Modalities text repo
- Created 2024-09 repo
- Latest release memobase Python SDK 0.0.27 (PyPI, 2025-11-08); no tagged GitHub releases registry
- License Apache-2.0 repo
- GitHub memodb-io/memobase — ~2.8k stars, last commit ~2026-01 repo
- Mindshare 1 inbound repo
- Pricing OSS self-hosted free (Apache-2.0); Memobase Cloud free and pay-as-you-go tiers advertise… repo
- Deployment Both (self-hosted Docker + Memobase Cloud managed) vendor
- Founders / pedigree Memobase (open-source; no institutional affiliation found) repo
- Memory volume / scale no scale claim repo
- Code/weights release Active — last commit 2026-01 · 2,718★ repo
- API surface REST, SDK: Python, JS/TS vendor
- Backend storage Postgres + pgvector repo
- Multi-tenancy namespace (user_id) vendor
- Encryption at-rest + in-transit vendor
- Embedding model multiple supported vendor
- Versioning immutable append-log repo
- Tombstoning append-only no delete repo
- Schema evolution schema with migration repo
- Namespace primitives per-user repo
- Contradiction handling LLM resolves and overwrites repo
- Forgetting policy none (permanent) repo
- MCP support native (first-party) — memobase MCP repo
- A2A support not supported repo
- OTel no repo
- Webhooks / events no repo
- Import / export JSON via REST; Python/Node SDK insert/retrieve vendor
- Integration count 1 repo
- Orchestration both (user-scoped memory; multi-agent sharing via user_id) vendor
- Programmatic control full CRUD + SDK (Python/Node/Go) + MCP vendor
- Pricing specifics tier flat-rate + pay-as-you-go: Free for testing; production paid (price not detailed) vendor
- Validated verticals consumer / individual companion AI, voice agents vendor
- Time to running <10min (hosted SaaS sign-up) vendor
- Anti-fit not for non-Claude-Code clients (some are MCP-portable) repo
- Optimised for user-profile + event-timeline (companion-AI persona) vendor
- Adjacent infrastructure BYO LLM; bundled storage vendor
- Pros User-profile-centric model is closer to how product teams think about user memory than f… repo
- Cons Smaller community than Mem0/Letta; profile-centric framing doesn't fit purely conversati… repo
- Project & sources GitHub memodb-io/memobase MCP server (Playbooks) repo
- commit-trajectory [{"ym":"2024-10","cum":1},{"ym":"2025-01","cum":127},{"ym":"2025-02","cum":177},{"ym":"2… repo
- download-trajectory [{"ym":"2025-11","monthly":2153,"cum":2153},{"ym":"2025-12","monthly":3881,"cum":6034},{… 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 repo
- licensing-bucket open-source repo
- positioning-platform-vs-product platform repo
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":3.76,"as_of":"2026-09","openrank_12mo":4.41,"openrank_current":0.36,"partici… third-party
- sdk-languages go,python,rest,typescript repo
- protocol-support mcp-server vendor
- maturity ga repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-29
- Latest release “no releases (no tagged releases on GitHub as of research date)” → “memobase Python SDK 0.0.27 (PyPI, 2025-11-08); no tagged GitHub releases” source
- Pricing “Free + paid (Memobase Cloud free tier for testing; pay-as-you-go for production)” → “OSS self-hosted free (Apache-2.0); Memobase Cloud free and pay-as-you-go tiers advertised in the README, but memobase.io (incl. pricing and login) returns 404 and app.memobase.io is down as of 2026-10-29” source
Related systems
References (2)
- Model Context Protocol (MCP spec) depends on at runtime — Cross-tool memory passport for Claude / Cursor / MCP-compatible agents.
- pgvector depends on at runtime — backend-storage cell: Postgres + pgvector
Referenced by (1)
- Acontext (memodb) same team as — Same GitHub organisation `memodb` publishes both repos.