MemMachine
https://github.com/MemMachine/MemMachine
Multi-layered open-source memory system for AI agents.
At a glance
- Type
- Multi-layered memory system
- Tier
- T2
- Section
- Dedicated memory layers
- Created
- 2025-08
- Latest release
- v0.3.7 2026-05-01
- License
- Apache-2.0
- GitHub
- 3.1k★ +30/mo Python
- Pricing
- OSS free; Enterprise version coming soon (no public price)
- Funding
- searched not found
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- episode
- governance
- inspectable
- conflict
- none
When to use
Optimised for: multi-layer memory architecture
Anti-fit: no anti-fit explicitly stated
Pros & cons
Pros
OSS framework for personalized memory across agents; multi-LLM support and clean SDK.
Cons
Distinct from the MemMachine paper above — naming overlap can confuse comparison.
Claims & capabilities
3.1k GitHub stars; Apache-2.0; multi-layered memory architecture; v0.3.7 released 2026-05-01; first-party MemMachine MCP; 0.9169 LoCoMo (paper); paper arXiv:2604.04853 also titled MemMachine; Enterprise version forthcoming
Technical surface
- API surface
- REST, SDK: Python
- Backend storage
- hybrid
- Deployment
- Self-hosted (private cloud or on-premises); Enterprise managed forthcoming
- Embedding model
- multiple supported
- Multi-tenancy
- namespace
- MCP
- native (first-party) — MemMachine 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.