memU (NevaMind)
https://github.com/NevaMind-AI/memU
Lightweight agent memory system that builds a shared, file-like 'memory wiki' across sessions, agents and devices and can extract reusable skills from agent history; also offered as a hosted service (memu.pro). #9 on GitHub agent-memory topic
Active · Verified 2026-10-23 · fresh as of 2026-10-23 · 17 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Tier
- T3
- Section
- Dedicated memory layers
- Created
- 2025-07-29 repo fix
- Latest release
- last commit 2026-10-16 repo fix
- License
- Apache-2.0 repo fix
- GitHub
- https://github.com/NevaMind-AI/memU (14556★) repo fix
- Pricing
- searched not found fix
- Funding
- searched not found fix
- Freshness
- 2026-10-23 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- Developer activity
- OpenRank 2.85 (12-mo avg 5.39) · 12 participants — 2026-09 third-party fix
Memory taxonomy
- storage
- file
- retrieval
- similarity
- persistence
- long-term
- update
- agent-controlled
- unit
- document
- governance
- editable
- conflict
- agent
When to use
Optimised for: searched not found
Anti-fit: searched not found
Pros & cons
Pros
searched not found
Cons
searched not found
Claims & capabilities
Across Sessions. Across Agents. Across Devices.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- searched not found
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- searched not found
- A2A
- searched not found
- OpenTelemetry
- searched not found
Alternatives to memU (NevaMind) → 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 (16 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 Framework repo
- What it does & what's distinct Lightweight agent memory system that builds a shared, file-like 'memory wiki' across ses… repo
- Claims / benefits Across Sessions. Across Agents. Across Devices. repo
- Created 2025-07-29 repo
- Latest release last commit 2026-10-16 repo
- License Apache-2.0 repo
- GitHub https://github.com/NevaMind-AI/memU (14556★) repo
- Mindshare 14556 GitHub stars repo
- Project & sources https://github.com/NevaMind-AI/memU repo
- architecture-deployment-locus hybrid repo
- licensing-bucket open-source repo
- positioning-platform-vs-product product repo
- taxonomy-three-layer-rollup agent-infra repo
- developer-activity-opendigger {"activity":28.46,"as_of":"2026-09","openrank_12mo":5.39,"openrank_current":2.85,"partic… third-party
- sdk-languages python repo
- maturity beta registry
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 Added to the catalog #222