RepoRadar
Leave a Tip
Item detail

zaydmulani09/mnemo

mnemo zaydmulani09/mnemo is an MIT-licensed local-first AI memory sidecar — a single Rust binary that extracts entities, builds a persistent knowledge graph, and injects scored context back into LLM prompts in under 50ms, with no cloud dependency and no Python runtime; POST raw text to `/ingest` (a conversation turn, a document, a note) and mnemo sends it to the configured LLM for entity extractio

Open source →Back to radar
Score7.8
Popularity225.0
Risklow
TierSilver
Score breakdown
Usefulness8.2
Novelty10.0
Momentum10.0
Maturity8.2
Open-source/build7.4
Evidence7.2
Workflow potential8.5
Setup ease6.5

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI builders who want a local-first memory layer for any LLM app (coding agents, RAG, conversational assistants) without giving up data to a cloud memory service, Rust developers who want a single static binary sidecar that ships as `mnemo-core` on crates.io and `mnemo-sdk` on PyPI, privacy-conscious teams that need the entity extraction + knowledge graph to stay on-prem with Ollama as t

Who should use it

BuildersPower users

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

Risk label needs manual review.

Evidence links

Closest alternatives / related signals

  • No close related item is available in the current public catalog.