SuperLocalMemory
https://www.superlocalmemory.com/
Cloud-free agent memory using information-geometric retrieval (Fisher-Rao distance + BM25 + entity graph + temporal fusion via 4-channel RRF) instead of LLM calls for scoring and lifecycle. Mode A is the only system to cross 70% LoCoMo with zero API dependency.
Active · Verified 2026-10-22 · fresh as of 2026-10-22 · 39 cited facts, 1 with a third-party source · 1 recorded change · Suggest a correction
At a glance
- Type
- Local-geometric / privacy-first / no LLM scoring vendor fix
- Tier
- T1
- Section
- Dedicated memory layers
- Created
- searched not found fix
- Latest release
- v4.2.10 (2026-10-17) repo fix
- License
- AGPL-3.0-or-later (commercial licence available) registry fix
- Funding
- searched not found fix
- Freshness
- 2026-10-22 fix
- Layer
- agent-infra repo fix
- Licensing
- open-source repo fix
- Protocols
- mcp-server repo fix
Memory taxonomy
- storage
- vector
- retrieval
- similarity
- persistence
- long-term
- update
- extraction
- unit
- fact
- governance
- user-controllable
- conflict
- none
When to use
Optimised for: privacy / no LLM calls / Fisher-Rao+BM25+graph fusion
Anti-fit: not for use cases that require LLM-based scoring or generation in the memory layer
Pros & cons
Pros
Local-first by default keeps PII out of the cloud; lightweight footprint suits on-device agents.
Cons
Local-only constraint limits scale and cross-device sync; smaller ecosystem than cloud-first peers.
Claims & capabilities
74.8% LoCoMo (Mode A, zero LLM), 87.7% (Mode C). AGPL v3. EU AI Act compliance framing. arxiv 2603.14588.
Technical surface
- API surface
- searched not found
- Backend storage
- searched not found
- Deployment
- Local-only (no Docker; no graph DB; no API keys; CPU-only; Mode A zero-LLM)
- Embedding model
- searched not found
- Multi-tenancy
- searched not found
- MCP
- yes — stdio server (slm mcp) and local HTTP /mcp endpoint, configurable tool profiles
- A2A
- not documented publicly
- OpenTelemetry
- not documented publicly
Alternatives to SuperLocalMemory → 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 (38 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 Local-geometric / privacy-first / no LLM scoring vendor
- What it does & what's distinct Cloud-free agent memory using information-geometric retrieval (Fisher-Rao distance + BM2… vendor
- Claims / benefits 74.8% LoCoMo (Mode A, zero LLM), 87.7% (Mode C). AGPL v3. EU AI Act compliance framing. … vendor
- Modalities text vendor
- Latest release v4.2.10 (2026-10-17) repo
- License AGPL-3.0-or-later (commercial licence available) registry
- GitHub qualixar/superlocalmemory — ~227 stars, last commit 2026-10 repo
- Pricing free / open source (AGPL-3.0); commercial licence terms unpriced repo
- Compliance EU AI Act compliant framing (explicitly stated) vendor
- Data handling All data stays on user's machine; no cloud; no API dependency vendor
- Deployment Local-only (no Docker; no graph DB; no API keys; CPU-only; Mode A zero-LLM) vendor
- Founders / pedigree Varun Pratap Bhardwaj (creator; researcher; Qualixar initiative) third-party
- Memory volume / scale no scale claim vendor
- Performance 74.8% LoCoMo (Mode A — zero LLM) 87.7% LoCoMo (Mode C — LLM-assisted) vendor
- Tombstoning hard-delete supported vendor
- Schema evolution schema with migration vendor
- Namespace primitives per-tenant vendor
- Contradiction handling LLM resolves and overwrites vendor
- Forgetting policy user-controlled forget vendor
- MCP support yes — stdio server (slm mcp) and local HTTP /mcp endpoint, configurable tool profiles repo
- Integration count 0 vendor
- Orchestration agnostic vendor
- Programmatic control full CRUD via lib (zero-LLM mode) vendor
- Vendor benchmarks LoCoMo 74.8% Mode A (zero LLM); 87.7% Mode C (vendor; arxiv 2603.14588) paper
- Validated verticals privacy-sensitive agent developers (consumer + regulated horizontal) repo
- Time to running <10min (pip install, no LLM keys required) repo
- Anti-fit not for use cases that require LLM-based scoring or generation in the memory layer repo
- Optimised for privacy / no LLM calls / Fisher-Rao+BM25+graph fusion repo
- Adjacent infrastructure fully self-contained — bring nothing repo
- Pros Local-first by default keeps PII out of the cloud; lightweight footprint suits on-device… vendor
- Cons Local-only constraint limits scale and cross-device sync; smaller ecosystem than cloud-f… vendor
- Project & sources superlocalmemory.com vendor
- architecture-deployment-locus local vendor
- licensing-bucket open-source repo
- positioning-platform-vs-product product vendor
- taxonomy-three-layer-rollup agent-infra repo
- sdk-languages python repo
- protocol-support mcp-server 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
- License “not applicable — not OSS” → “AGPL-3.0-or-later (commercial licence available)” source
- Latest release “not applicable — not OSS” → “v4.2.10 (2026-10-17)” source
- Pricing first recorded as “free / open source (AGPL-3.0); commercial licence terms unpriced” source
- MCP support first recorded as “yes — stdio server (slm mcp) and local HTTP /mcp endpoint, configurable tool profiles” source
Related systems
Referenced by (1)
- LangChain (framework) integrates with — LangChain's all-providers integrations page lists SuperLocalMemory: "Local-first chat message history stored in SQLite with no cloud dependencies". (verified 2026-10-29)