Competitive Analysis

The only system
with mathematical proofs.

Most agent memory systems use cosine similarity and hope for the best. SuperLocalMemory is the only one with peer-reviewed mathematical foundations, local-first architecture, and zero cloud dependency in the data path.

Feature Matrix

Head-to-head comparison.

Every claim is sourced from public documentation. SLM claims carry arXiv citations.

Feature SLM V3.6 Mem0 Zep LangMem ChatGPT Memory
Mathematical retrieval Fisher-Rao metric cosine cosine cosine proprietary
Local-first fully local Cloud + local Cloud Cloud Cloud
No telemetry
Open source AGPL v3
Peer-reviewed 3 arXiv papers
Prompt compression 60–95%
LLM cache exact + semantic partial
MCP protocol 17+ tools partial
Free tier unlimited local limited limited limited limited
LoCoMo benchmark 74.8% (local) / 87.7% (full) not published not published not published not published

Competitor data sourced from public documentation as of June 2026. See arXiv:2603.14588 for SLM methodology. ◑ = partial support. If any data is incorrect, open an issue on GitHub.

Why SLM Wins

Three things no one else has.

Not features on a roadmap. Shipped, benchmarked, and cited in peer-reviewed literature.

01 · Retrieval

Mathematical retrieval

Only SLM uses Fisher-Rao geodesics on a statistical manifold. Cosine similarity treats every memory as equally confident — it ignores the signal in your confidence scores entirely. Fisher-Rao does not.

02 · Privacy

True local-first

Zero cloud in the data path. Mem0's local mode still routes through their SDK — which can send embeddings externally. SLM's local mode runs entirely on-device. There is no network call possible. Your memories are yours.

03 · Evidence

Peer-reviewed proofs

Three arXiv papers with reproducible benchmarks. LoCoMo 74.8% local-first — the highest published score without cloud dependency. Others publish blog posts with no methodology. We publish math.

Questions

Fair questions about this comparison.