OMEGA
Local context/memory engine for coding agents: stores decisions, docs and agent history on-machine (SQLite + local ONNX embeddings) and serves a ranked slice per task over MCP. Open-core Apache-2.0 core with paid Pro tier.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 33 cited facts, 2 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Memory engine + 50ms retrieval vendor fix
- Tier
- T2
- Section
- Dedicated memory layers
- Created
- searched not found fix
- Latest release
- v1.5.20 (2026-10-08) registry fix
- License
- Apache-2.0 registry fix
- GitHub
- omega-memory/omega-memory — ~224 stars repo fix
- Pricing
- Core free (Apache-2.0); Pro $19/mo (multi-agent coordination, LLM routing, knowledge base, encrypted sync) vendor fix
- Funding
- searched not found fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Protocols
- mcp-server repo fix
Memory taxonomy
- storage
- hybrid
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- fact
- governance
- user-controllable
- conflict
- none
When to use
Optimised for: latency (50ms retrieval) over consistency
Anti-fit: searched not found
Pros & cons
Pros
Open-memory framework with explicit semantic reasoning over stored memory rather than pure retrieval.
Cons
Smaller community; less production track record than Mem0 / Letta / Zep.
Claims & capabilities
Reports 95.4% (466/500) on LongMemEval at 50ms retrieval — claimed highest published score on the leaderboard.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Local-only (local ONNX embeddings + SQLite; macOS + Linux; Windows via WSL)
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- yes — runs as MCP server subprocess; works with Claude Code, Cursor, Windsurf, Cline etc.
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Alternatives to OMEGA → 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 (32 cited facts, 2 third-party)
Each fact links to the page it came from; the badge says who published it (how to read sources).
- What it is Memory engine + 50ms retrieval vendor
- What it does & what's distinct Local context/memory engine for coding agents: stores decisions, docs and agent history … vendor
- Claims / benefits Reports 95.4% (466/500) on LongMemEval at 50ms retrieval — claimed highest published sco… vendor
- Modalities text vendor
- Latest release v1.5.20 (2026-10-08) registry
- License Apache-2.0 registry
- GitHub omega-memory/omega-memory — ~224 stars repo
- Pricing Core free (Apache-2.0); Pro $19/mo (multi-agent coordination, LLM routing, knowledge bas… vendor
- Compliance not applicable — local-only (AES-256-GCM encryption at rest; no cloud) vendor
- Data handling All data stays on user's machine; zero cloud dependency; zero external calls vendor
- Deployment Local-only (local ONNX embeddings + SQLite; macOS + Linux; Windows via WSL) vendor
- HQ US (no city specified) vendor
- Founders / pedigree Jason Sosa (builder; no further background publicly identified) third-party
- Memory volume / scale no scale claim vendor
- Performance 95.4% LMES (vendor self-reported) vendor
- MCP support yes — runs as MCP server subprocess; works with Claude Code, Cursor, Windsurf, Cline etc. vendor
- Integration count 0 vendor
- Orchestration both vendor
- Programmatic control full CRUD + SDK vendor
- Vendor benchmarks LMES 95.4% (466/500) at 50ms (vendor) — claimed highest published vendor
- Pricing specifics open-core: Core free (Apache-2.0); Graph $249/mo; Pro multi-agent additional vendor
- Optimised for latency (50ms retrieval) over consistency third-party
- Pros Open-memory framework with explicit semantic reasoning over stored memory rather than pu… vendor
- Cons Smaller community; less production track record than Mem0 / Letta / Zep. vendor
- Project & sources omegamax.co benchmarks vendor
- architecture-deployment-locus local vendor
- licensing-bucket open-core vendor
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
- sdk-languages python registry
- protocol-support mcp-server 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)
- 2026-10-22
- License “not applicable — not OSS” → “Apache-2.0” source
- Latest release “not applicable — not OSS” → “v1.5.20 (2026-10-08)” source
- Pricing “Open-core: Core tier free (Apache-2.0); Graph tier $249/mo; Pro tier (multi-agent) additional” → “Core free (Apache-2.0); Pro $19/mo (multi-agent coordination, LLM routing, knowledge base, encrypted sync)” source
- MCP support first recorded as “yes — runs as MCP server subprocess; works with Claude Code, Cursor, Windsurf, Cline etc.” source