Memory systems

Memanto (Moorcheh)

Information-theoretic agent memory + semantic search

Open sourceself-hostable

★ 2,377 on GitHub · +2 today · last commit Nov 13, 2026

What it is

Our note

Python memory system persisting agent context across sessions without an external vector DB; retrieval engine uses information-theoretic binarization (MIB/EDM/ITS) instead of HNSW cosine, claimed zero indexing latency. On-prem Docker or managed cloud; MCP server, SDKs, integrations for Claude Code, Cursor, CrewAI. Papers on arXiv/HF. 2.4k stars on memanto. Performance claims self-reported.

At a glance

Vendor
EdgeAI Innovations (Moorcheh.ai)
Business model
Open source
License
MIT (memanto); Moorcheh engine source-available Community Edition
Self-hosting
Yes, can be self-hosted

GitHub activity

This product has a public repository, so we read it nightly from the GitHub API. Stars measure developer attention, not quality or market share.

“Memory that AI Agents Love!” (repository description)

Stars
2,377
Change since last reading
+2
Forks
744
Open issues
4
Last commit
Nov 13, 2026 (1 days ago)
License (GitHub)
MIT

Last checked nov 15, 2026; last updated nov 15, 2026; facts verified nov 14, 2026; added nov 14, 2026. Vendor facts come from the vendor’s own pages; benchmark claims are self-reported unless we say otherwise.

All 62 in Memory systems · All sections