Vibe Coding Discovermemanto
View on GitHubMemory that AI Agents Love!
Memanto is a Python memory agent that runs alongside your AI agents to curate, consolidate, reconcile and expire their long-term memory, with point-in-time recall, policy-based forgetting and portable OKF export. Ships as a CLI plus local REST API and dashboard, and can run fully on-prem with Docker and Ollama.
Use Cases
Give AI agents persistent long-term memory across sessionsShare one memory estate across Claude Code, Cursor, Codex and custom agentsDetect and reconcile contradictory beliefs between multiple agentsPoint-in-time recall of what the fleet believed at a past datePolicy-based memory expiry, decay and restorationExtract durable knowledge from ephemeral agent conversationsExport/migrate agent memory as portable Markdown (OKF) from Mem0, Letta or SupermemoryRun a fully on-prem, air-gapped memory service with Docker and OllamaBrief agents with relevant memory slices before they actAudit memory provenance, confidence and source per belief
Built With
- Language
- Python
- Frameworks
- FastAPI · Pydantic · Typer · Uvicorn · LangChain · CrewAI · Ollama · Docker · Moorcheh SDK · Langfuse
Tags
agent-memory · long-term-memory · semantic-memory · memory-management · stateful-ai · knowledge-consolidation · conflict-resolution · memory-decay · temporal-recall · multi-agent · cli · self-hosted · docker · mit-license · knowledge-export