moorcheh-ai/

memanto

GitHub Website

Memanto is a Python tool that acts as a memory agent for AI systems, offering remember/recall/answer capabilities with local or cloud deployment options.

1.8kstars

595forks

145issues

MITlicense

2026since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

mem0ai/

mem0

▲ 565/wk

Universal memory layer for AI Agents

63k7.3kPython

langchain-ai/

langchain

▲ 595/wk

The agent engineering platform.

143k24kPython

langchain-ai/

langgraph

▲ 509/wk

Build resilient agents.

39k6.5kPython

thedotmack/

claude-mem

▲ 660/wk

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

90k7.8kJavaScript

bytedance/

deer-flow

▲ 1.2k/wk

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

79k11kPython

headroomlabs-ai/

headroom

▲ 1.7k/wk

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

65k4.9kPython

Comparememanto vs mem0 memanto vs langchain memanto vs langgraph

Reviewgenerated from repository data · Aug 5, 2026

What it is

Memanto is a memory agent. It remembers, recalls, and answers — so your agents can achieve long-term goals and avoid confusion.

How it works

Memanto provides three operations (remember, recall, answer) to manage persistent context across sessions. It can run locally via Docker or as a cloud service with a free tier, and the CLI manages either setup. Integrations connect with multiple AI agents/tools. Memory types are categorized for retrieval, and there is zero indexing delay at write time. The retrieval relies on Moorcheh as the semantic engine, with optional local Docker deployment or cloud usage managed by the memanto CLI.

Getting started

Option A — Fully local (no account, no API key):

pip install memanto
memanto           # choose "On-Prem" — guides through Docker + Ollama setup

Requires Docker. Everything runs and stays on your machine.

Option B — Free cloud (no card, ~60 seconds):

pip install memanto
memanto           # choose "Cloud" — paste your free Moorcheh API key

Get your free API from : https://console.moorcheh.ai/api-keys

Switch between local and cloud at any time with memanto config backend.

Recent releases

v0.2.13 (2026-08-04): fixes a major multi-type recall bug (filters previously AND'd rather than OR'd) and hardens session storage.
MCP server fix (v0.1.1) (2026-08-04): repairs the Memanto MCP server; writes through remember were failing.
v0.2.12 (2026-07-29): validation and correctness fixes across config management, CLI connect/skill install, MCP session isolation, and LangGraph/Her.
v0.2.11 (2026-07-28): adds real write-time contradiction detection and resolution via MemoryValidationService and batch processing.
v0.2.10 (2026-07-23): fixes memanto agent list failure with mixed timezone timestamps.

Traction

1771 stars on GitHub; 595 forks; 145 open issues.

Behind the repo

Repository owner shows a focus on Moorcheh integration and a permissive MIT license; primary language is Python.

Caveats

License: MIT
Created: 2026-03-23
Last push: 2026-08-04

SharePost on X LinkedIn