Skip to main content
Glama
Veedubin

memini-ai

by Veedubin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

memini-ai

Local-first memory for AI coding agents. Three MCP tools: remember, recall, orient. Postgres + pgvector for storage, BGE-M3 embeddings on CPU, hybrid vector + full-text search.

Quick start

uv tool install memini-ai --index https://download.pytorch.org/whl/cpu --index-strategy unsafe-best-match
memini-ai db up            # pgvector/pgvector:pg18 on 127.0.0.1:5555
memini-ai migrate          # optional; serve applies migrations on first connection
memini-ai warm             # one-time ~2.2 GB BGE-M3 download, then embeds one string

The --index flags install CPU torch instead of the default CUDA build. Run warm before wiring up a client: the first remember or recall would otherwise download BGE-M3 (about 2.2 GB) inside a tool call and time out until it finishes.

Then, from the project you want memory for:

cd ~/Projects/my-repo
memini-ai init --client claude-code --project my-repo

Restart the client and call orient.

Related MCP server: ContextAtlas

Docs

License

MIT. See LICENSE.

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • CodeGraph

    Phoenixrr2113
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to search code by meaning, explore codebase structure, store and query knowledge with temporal facts, and read source code through a set of MCP tools.
    248 npm
    7
    MIT

  • ContextAtlas

    codefromkarl
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI coding agents to retrieve and manage code context with hybrid search, project memory, and observability via MCP tools.
    29
    MIT

  • Librarian

    arcadeai-labs
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides AI agents with persistent knowledge storage, enabling them to store, search, and retrieve text, documents, and files using semantic and keyword search via MCP tools.
    32
    Apache 2.0

  • memento

    UmoLab
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides persistent memory for AI coding agents via MCP, enabling agents to store and semantically recall facts, events, and lessons across sessions, all running locally without cloud dependencies.
    Apache 2.0