Memary
https://github.com/kingjulio8238/Memary
Open-source long-term memory framework for autonomous agents.
Inactive · Verified 2026-10-22 · fresh as of 2026-10-22 · 49 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Long-term memory for autonomous agents repo fix
- Tier
- T2
- Section
- Dedicated memory layers
- Latest release
- v0.1.5 2024-10-22 repo fix
- Pricing
- OSS (MIT); no commercial pricing repo fix
- Funding
- searched not found fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- Developer activity
- OpenRank 0.21 (12-mo avg 2.05) · 2 participants — 2026-09 third-party fix
Memory 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; 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
Alternatives to Memary → 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 (48 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 Long-term memory for autonomous agents repo
- What it does & what's distinct Open-source long-term memory framework for autonomous agents. repo
- Claims / benefits MIT; long-term knowledge-graph memory framework for autonomous agents; v0.1.5 released 2… repo
- Modalities text repo
- Created 2024-04 repo
- Latest release v0.1.5 2024-10-22 repo
- License MIT repo
- GitHub kingjulio8238/Memary — ~2.6k stars, last commit n/a repo
- Pricing OSS (MIT); no commercial pricing repo
- Compliance not applicable — not commercial (OSS research project) repo
- Data handling not applicable — not commercial (all data on user's infrastructure) repo
- Deployment Self-hosted (OSS; no cloud service found) repo
- HQ US (San Francisco — creator's location) repo
- Founders / pedigree kingjulio8238 (kingJulio; San Francisco developer; no full name publicly identified) repo
- Memory volume / scale no scale claim 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
- A2A support not supported repo
- Webhooks / events no repo
- Import / export JSON; Neo4j export repo
- Integration count 0 repo
- Orchestration single-agent repo
- Programmatic control full CRUD via lib repo
- Pricing specifics OSS only (MIT) — no hosted offering repo
- Validated verticals autonomous-agent research, agent developers repo
- Time to running <1hr (OSS pip install + Neo4j) repo
- Anti-fit no anti-fit explicitly stated repo
- Optimised for autonomous-agent long-term memory (research-quality) repo
- Adjacent infrastructure BYO LLM; Neo4j required repo
- Pros Knowledge-graph autonomous memory inspired by human memory model; OSS implementation. repo
- Cons Smaller community; production deployment evidence is thin. repo
- Project & sources GitHub kingjulio8238/Memary repo
- commit-trajectory [{"ym":"2024-02","cum":24},{"ym":"2024-03","cum":93},{"ym":"2024-04","cum":230},{"ym":"2… repo
- download-trajectory [{"ym":"2025-11","monthly":9,"cum":9},{"ym":"2025-12","monthly":22,"cum":31},{"ym":"2026… registry
- cost-input-usd-per-mtok 0 repo
- cost-output-usd-per-mtok 0 repo
- cost-tier free repo
- cost-pricing-model free-tier repo
- cost-last-verified 2026-06-29 repo
- 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":3.47,"as_of":"2026-09","openrank_12mo":2.05,"openrank_current":0.21,"partici… third-party
- sdk-languages python repo
What changed
Changes to this record's lifecycle, licence, release, pricing and hosting facts, from the catalog's git history. Subscribe (Atom)
- 2026-10-22
- Lifecycle first recorded as “unknown”
Related systems
References (1)
- Neo4j depends on at runtime — adjacent-infrastructure cell: BYO LLM; Neo4j required