OpenMemory (now LongMemory)
https://github.com/CaviraOSS/LongMemory
Renamed LongMemory (repo CaviraOSS/LongMemory; packages longmemory / longmemory-sdk, with openmemory-js@2 / openmemory-py@2 as forwarding bridges). Open-source cognitive memory engine for LLMs and agents.
Renamed · Verified 2026-10-29 · fresh as of 2026-10-29 · 48 cited facts, 6 with a third-party source · 2 recorded changes · Suggest a correction
At a glance
- Type
- Cognitive memory engine repo fix
- Tier
- T2
- Section
- Dedicated memory layers
- Latest release
- v1.2.3 (2025-12-12); v1.3.0 beta pre-release (2025-12-20) repo fix
- License
- Apache-2.0 repo fix
- Pricing
- OSS (Apache-2.0 self-hosted); self-hosted cost ~$5-8/mo for 100k memories vs $60-120 for SaaS third-party fix
- Funding
- searched not found fix
- Freshness
- 2026-10-29 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- SDK languages
- python, typescript repo fix
- Protocols
- mcp-server repo fix
- Developer activity
- OpenRank 0.66 (12-mo avg 3.43) · 6 participants — 2026-09 third-party fix
Memory taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- fact
- governance
- user-controllable
- conflict
- none
When to use
Optimised for: local-first / privacy-preserving
Anti-fit: no anti-fit explicitly stated
Pros & cons
Pros
Cross-tool memory protocol — designed to make memory portable between agents that today silo it.
Cons
Protocol adoption is early; ecosystem support outside Mem0 is thin.
Claims & capabilities
+165/mo; Apache-2.0; OpenMemory MCP first-party MCP server; v1.2.3 released 2025-12-12; self-hosted ~$5-8/mo for 100k memories vs $60-120 for SaaS
Technical surface
- API surface
- REST; OpenAI-compatible chat endpoint with embedded memory ops
- Backend storage
- hybrid (vector + graph)
- Deployment
- Self-hosted (local + Docker; no cloud service found)
- Embedding model
- multiple supported
- Multi-tenancy
- namespace
- MCP
- yes — built-in stdio MCP (longmemory mcp) and authenticated Streamable HTTP MCP
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Alternatives to OpenMemory (now LongMemory) → 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 (47 cited facts, 6 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Cognitive memory engine repo
- What it does & what's distinct Renamed LongMemory (repo CaviraOSS/LongMemory; packages longmemory / longmemory-sdk, wit… repo
- Claims / benefits +165/mo; Apache-2.0; OpenMemory MCP first-party MCP server; v1.2.3 released 2025-12-12; … repo
- Modalities text repo
- Created 2025-10 repo
- Latest release v1.2.3 (2025-12-12); v1.3.0 beta pre-release (2025-12-20) repo
- License Apache-2.0 repo
- GitHub CaviraOSS/LongMemory (formerly OpenMemory) — ~4.5k stars, last commit 2026-10 repo
- Mindshare 4.1k GitHub stars; +165/mo growth; below detection threshold for HN/press; OSS community… repo
- Pricing OSS (Apache-2.0 self-hosted); self-hosted cost ~$5-8/mo for 100k memories vs $60-120 for… third-party
- Data handling not applicable — self-hosted OSS (all data stays on user's infrastructure) repo
- Deployment Self-hosted (local + Docker; no cloud service found) third-party
- Founders / pedigree Contributors include Morven, Muhammad Fiaz, Peter Chung, Brett Ammeson, Joseph Goksu; no… repo
- Memory volume / scale no scale claim repo
- API surface REST; OpenAI-compatible chat endpoint with embedded memory ops repo
- Backend storage hybrid (vector + graph) repo
- Multi-tenancy namespace repo
- Embedding model multiple supported repo
- Tombstoning hard-delete supported repo
- Schema evolution schema with migration repo
- Namespace primitives per-tenant repo
- Contradiction handling LLM resolves and overwrites repo
- Forgetting policy user-controlled forget repo
- MCP support yes — built-in stdio MCP (longmemory mcp) and authenticated Streamable HTTP MCP repo
- Webhooks / events no repo
- Import / export JSON local store repo
- Integration count 0 repo
- Orchestration agnostic third-party
- Programmatic control full CRUD via lib third-party
- Pricing specifics OSS only (Apache-2.0); self-hosted ~$5-8/mo for 100k memories third-party
- Validated verticals consumer / individual, OSS agent developers repo
- Time to running <1hr (Docker compose, OSS) repo
- Anti-fit no anti-fit explicitly stated repo
- Optimised for local-first / privacy-preserving repo
- Adjacent infrastructure BYO LLM; self-hosted Postgres + Qdrant repo
- Pros Cross-tool memory protocol — designed to make memory portable between agents that today … repo
- Cons Protocol adoption is early; ecosystem support outside Mem0 is thin. repo
- Project & sources GitHub CaviraOSS/OpenMemory repo
- commit-trajectory [{"ym":"2025-10","cum":80},{"ym":"2025-11","cum":195},{"ym":"2025-12","cum":242},{"ym":"… repo
- download-trajectory [{"ym":"2025-11","monthly":77,"cum":77},{"ym":"2025-12","monthly":129,"cum":206},{"ym":"… registry
- architecture-deployment-locus local repo
- licensing-bucket open-source repo
- positioning-platform-vs-product platform repo
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":8.48,"as_of":"2026-09","openrank_12mo":3.43,"openrank_current":0.66,"partici… third-party
- sdk-languages python,typescript repo
- 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)
- 2026-10-23
- Name “OpenMemory” → “OpenMemory (now LongMemory)”
- Homepage “https://github.com/CaviraOSS/OpenMemory” → “https://github.com/CaviraOSS/LongMemory”
- 2026-10-22
- Latest release “v1.2.3 2025-12-12” → “v1.2.3 (2025-12-12); v1.3.0 beta pre-release (2025-12-20)” source
- MCP support “native (first-party) — OpenMemory MCP” → “yes — built-in stdio MCP (longmemory mcp) and authenticated Streamable HTTP MCP” source
Related systems
References (1)
- Qdrant depends on at runtime — adjacent-infrastructure cell: BYO LLM; self-hosted Postgres + Qdrant