SkillFoxx

Mind CLI

A CLI and MCP integration keeping agent decisions and checkpoints in local SQLite so work survives a session change.

  • 204 ★ on the repository
  • Last commit
  • MIT
CLI

Extended access

Why this level

  • The installer and `mind setup` change agent configuration in the home directory.
  • The database accumulates project decisions and code fragments, and optional embeddings send them to an outside API.
All reasons and checks

gabrielmartinmoran/mindAuthor:GabrielMartinMoran

Install

Manual install

curl -fsSL https://raw.githubusercontent.com/GabrielMartinMoran/mind/main/scripts/install.sh | bash

The installer runs without `sudo` and installs Bun if missing. Then run `mind setup`.

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The installer and `mind setup` change agent configuration in the home directory.
  • The database accumulates project decisions and code fragments, and optional embeddings send them to an outside API.

This is third-party code. Review the repository files before installing.

What it does

Mind keeps agent memory in a single local database, `mind.db`. An agent saves decisions, fixes, findings and references, leaves checkpoints for unfinished work and short summaries for finished sessions. Entries link through tags and directional links, and spaces plus three memory tiers keep related items together. The `mind setup` command configures integrations with all supported agents and the shared `mind-management` skill. Agents reach Mind through MCP, and the same store is open from the CLI, an HTTP API and a web interface at `localhost:30303`. Full-text search works without a key, and semantic search is enabled separately through OpenAI or OpenRouter.

Who it is for. Developers using several agents who want one local project memory across sessions and tools.

Good fit when

  • Context is compacted mid-task and the agent must resume from a checkpoint.
  • An architecture decision was made a week ago and has to be found by search.
  • Claude Code and Codex should see the same project memory.
  • You want to browse accumulated notes in a browser, not only through the agent.

Not a fit when

  • You need cloud memory shared across a team on different machines: Mind is local.
  • The task is one-off and context does not need to outlive the session.
  • Running an installer script in the home directory is unacceptable.

Example request

Save to Mind the decision that the CLI uses a command registry, and find what we decided about migrations.

Limitations

The installer installs Bun when missing and writes to user directories without `sudo`. `mind setup` may write configuration for agents that are not installed, so check `mind setup compatibility`: capabilities for different agents are not all verified. Semantic search calls outside APIs if you enable it. Markdown autosync is marked experimental. The last commit dates to October 2026.

How to disable. Remove integrations with the `mind setup` commands from the docs, then delete the binary and the `mind.db` data.

FAQ

How do I install Mind?

Run `curl -fsSL https://raw.githubusercontent.com/GabrielMartinMoran/mind/main/scripts/install.sh | bash` on macOS or Linux, then `mind setup`.

How do I connect a single agent?

Pass its name: `mind setup codex`. `mind setup compatibility` shows what is supported, partial and unverified.

Where is data stored?

In the local SQLite database `mind.db`. `mind serve start` opens it in a browser at `http://localhost:30303`.

Is a key needed for search?

No. Full-text search works at once, and semantic search is enabled separately using OpenAI or OpenRouter.

What does the mind-management skill do?

It tells agents how to work with memory: restore context, leave a checkpoint and close a session.

Discussion

No questions or reviews yet.

CLI tools
Official

Long-term memory for AI agents: a skill and the mindmemos command store facts from conversations and recall them in later sessions

SkillBroad access931

MenteDB keeps agent memory in a Rust database: an MCP server for Claude Code and Cursor in cloud or self-hosted mode.

MCP serverExtended access126

ai-memory keeps long-term assistant memory in local SQLite and serves it over MCP, an HTTP API and a CLI

MCP serverExtended access57
Official

A long-term memory system for AI agents: the agent stores experience and facts, then retrieves them through a built-in MCP server

MCP serverBroad access60.7K

ai-memory retains session knowledge in a Markdown wiki, exposes MCP retrieval and passes context between agents and machines.

MCP serverExtended access15.7K

Self-hosted long-term memory for agents: semantic search, a knowledge graph and autonomous consolidation over MCP and a REST API

MCP serverExtended access2.1K

README in short

The README explains why agents need memory across sessions, gives a LongMemEval benchmark result and walks through install, agent connection and first commands. Details live in docs on interfaces, search and configuration.

README badge

Report a problem