OpenMemory
https://github.com/CaviraOSS/OpenMemory
Open-source cognitive memory engine for LLMs and agents.
At a glance
- Type
- Cognitive memory engine
- Tier
- T2
- Section
- Dedicated memory layers
- Created
- 2025-10
- Latest release
- v1.2.3 2025-12-12
- License
- Apache-2.0
- GitHub
- 4.1k★ +165/mo TypeScript
- Pricing
- OSS (Apache-2.0 self-hosted); self-hosted cost ~$5-8/mo for 100k memories vs $60-120 for SaaS
- Funding
- searched not found
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
4.1k GitHub stars; +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
- native (first-party) — OpenMemory MCP
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
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).
- Supermemory T1
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.
Related systems
References (1)
- Qdrant depends on at runtime — adjacent-infrastructure cell: BYO LLM; self-hosted Postgres + Qdrant