Memanto

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/moorcheh-ai-memanto

About

Use cases: agent-memory, knowledge-base

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

7 read · 2 write · 1 delete · 1 not yet classified

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (11)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• answer

  Ask a natural-language question and get an LLM-generated answer grounded ONLY in the agent's stored memories (RAG). Prefer this over `recall` when you need a synthesized answer rather than a ranked list, e.g. 'what did we decide about X?'. Returns the answer text plus the supporting memory sources.

• batch_remember

  Store many memories at once (up to 100). Use this when you have a list of independent facts to persist - e.g. extracting structured data from a document. For a single item, prefer `remember`.

• create_agent

  Create a new Memanto agent (memory namespace). Most users only need one agent per project - it is fine to leave this disabled and rely on auto-create.

• delete_agent

  Delete an agent's local metadata. Note: by default this does NOT delete the remote Moorcheh namespace - memories are retained until explicitly purged via the Memanto CLI/REST API.

• get_agent

  Look up an agent's metadata by id.

• list_agents

  List every Memanto agent visible to the current API key.

• recall

  Search long-term memory for relevant context (semantic search, top-N results). Call this on your own, without waiting to be asked: - at the start of a new task or topic, before writing code or running commands, to pick up the user's rules, preferences and earlier decisions - when the user refers to earlier work ('like last time', 'the bug we fixed') - before choosing a library, pattern or convention the user hasn't specified - before asking the user for something they may have told you before Use a natural-language query ('what are the user's rules for git?'), not keywords.

• recall_as_of

  Point-in-time recall: return only memories that were known before the given timestamp. Use this when the user asks historical questions like 'what did we know on 2025-11-01?' or to reconstruct context at a previous moment.

• recall_changed_since

  Differential retrieval: return memories created or updated after the given timestamp. Use this for 'what's new since X?' or to catch up on activity between sessions.

• recall_recent

  Return the most recently stored memories (newest first). Use this to surface fresh context - e.g. 'what did we just decide?' - when you don't have a specific search query.

• remember

  Description is built at runtime.

Signals

Stars

2,340

Forks

736

Open issues

5

Contributors

138

Weekly downloads

259

Last commit (this folder)

Oct 23, 2026 (7 days ago)

Last release

Oct 23, 2026 (7 days ago)

Last package publish

Oct 23, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.moorcheh-ai/memanto

Version

0.1.4

Auth

No auth

Packages

pypi memanto-mcp

License

MIT

Repository

github.com/moorcheh-ai/memanto

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql