Memary
https://github.com/kingjulio8238/Memary
Open-source long-term memory framework for autonomous agents.
At a glance
- Type
- Long-term memory for autonomous agents
- Tier
- T2
- Section
- Dedicated memory layers
- Created
- 2024-04
- Latest release
- v0.1.5 2024-10-22
- License
- MIT
- GitHub
- 2.6k★ Jupyter Notebook
- Pricing
- OSS (MIT); no commercial pricing
- Funding
- searched not found
Taxonomy
- storage
- graph
- retrieval
- graph-traversal
- persistence
- long-term
- update
- extraction
- unit
- episode
- governance
- user-controllable
- conflict
- none
When to use
Optimised for: autonomous-agent long-term memory (research-quality)
Anti-fit: no anti-fit explicitly stated
Pros & cons
Pros
Knowledge-graph autonomous memory inspired by human memory model; OSS implementation.
Cons
Smaller community; production deployment evidence is thin.
Claims & capabilities
MIT; long-term knowledge-graph memory framework for autonomous agents; 2.6k GitHub stars; v0.1.5 released 2024-10-22; bio-inspired episodic+semantic memory model; ~40/mo PyPI downloads (memary pkg)
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Self-hosted (OSS; no cloud service found)
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- not documented publicly
- A2A
- not supported
- 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)
- Neo4j depends on at runtime — adjacent-infrastructure cell: BYO LLM; Neo4j required