O-Mem
https://github.com/OPPO-PersonalAI/O-Mem
Omni memory system for personalised, long-horizon, self-evolving agents. From OPPO PersonalAI.
At a glance
- Type
- Omni / self-evolving memory
- Tier
- T2
- Section
- Dedicated memory layers
- Created
- 2025-12
- Latest release
- no releases
- License
- Apache-2.0
- GitHub
- 65★ Python
- Pricing
- not applicable — academic research code (no commercial pricing)
- Funding
- not applicable — corporate research lab (OPPO PersonalAI Research)
Taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- lifelong
- update
- extraction
- unit
- fact
- governance
- opaque
- conflict
- llm-arbitrate
When to use
Optimised for: self-evolving / personalised long-horizon memory
Anti-fit: searched not found
Pros & cons
Pros
Optimized memory store with low-latency reads — strong on agent loops where memory is hit per turn.
Cons
Smaller community; thin track record vs established memory layers.
Claims & capabilities
65 GitHub stars; Apache-2.0; from OPPO PersonalAI Research (corporate lab); arXiv:2511.13593 paper Nov 17 2025; targets self-evolving lifelong personal memory; 4 cites (too recent)
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Self-hosted (research code; no cloud service)
- 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.