Ross ROSS = Recommend OSS · open-source software intelligence for agents

moorcheh-ai/memanto

Memory that AI Agents Love! observed · 2026-08-28

github.com/moorcheh-ai/memanto · homepage · Python · MIT (permissive) observed · 2026-08-28

Health v2 · maintenance only

81/100

  • Activity 99
  • Release rhythm 99
  • Longevity 11

Flags: young

How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 3
  • age_days: 163
  • days_rel: 9
  • days_push: 7
  • n_releases_24m: 40

Full methodology

Adoption not part of the score

1841 stars · 632 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Memanto is a companion 'memory agent' that manages long-term semantic memory for AI agents — deciding what to keep, resolving contradictions, expiring stale facts, and briefing agents at session start. It ships as a Python CLI/server with a REST API, local UI dashboard, and integrations for LangChain, LangGraph, CrewAI, LlamaIndex, n8n, Langfuse, and coding agents like Cursor and Claude Code.

Use cases

  • give my ai agents persistent memory across sessions
  • store and recall user preferences and decisions in a langchain agent
  • add long-term memory to crewai or langgraph agents
  • resolve conflicting facts my agents have learned
  • turn langfuse errors into durable agent memories
  • self-host a memory layer for coding agents like cursor
  • query agent memory semantically instead of injecting static context

When to choose

  • you run multiple agents that need shared, curated long-term memory rather than raw transcript storage
  • you want memory with temporal decay, confidence, and provenance tracking
  • you need integrations with LangChain, LangGraph, CrewAI, LlamaIndex, or n8n out of the box
  • you want local ownership with exportable Markdown and no vendor lock-in

When to avoid

  • you only need simple key-value session state or short-term conversation buffers
  • you require a fully offline solution with no external semantic service dependency
  • you need a battle-tested system with a long production track record — the project is young (v0.2.x)

Facets

library · maturity active

rag agent-framework llm-inference search-engine cli http-server sdk artificial-intelligence large-language-models developer-tools self-hosted python cli self-hosted cross-platform agent-memory semantic-memory long-term-memory memory-management llm-memory crewai langchain langgraph llamaindex n8n langfuse memory-agent stateful-agents ai-agents retrieval-augmented-generation docker

10 sources

Member repositories

RepositoryRoleHealth v2
moorcheh-ai/memantomain81

For agents

markdown · JSON · MCP: product_card(name="moorcheh-ai/memanto")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem