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.

At a glance

Type
Local-geometric / privacy-first / no LLM scoring
Tier
T1
Created
searched not found
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
searched not found
Funding
searched not found

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
not documented publicly
A2A
not documented publicly
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.

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.