Skip to main content

Persistent memory standard for AI agents — local, portable, zero config

Project description

rememb cover

Rememb MCP server

AI agents forget everything between sessions. rememb gives them persistent memory — local, portable, and works with any agent.

rememb chat demo


The problem

Every dev using AI professionally hits this wall:

Session 1: "We're using PostgreSQL, auth at src/auth/, prefer async patterns."
Session 2: Agent starts from zero. You explain everything again.
Session 3: Same thing.

Existing solutions (Mem0, Zep, Letta) require servers, API keys, and cloud accounts.
You just want the agent to remember your project.


Install

pip install rememb

Quick Start

With MCP (recommended)

Zero friction. No CLI commands. Native IDE integration.

1. Add to your IDE's MCP config:

{
  "mcpServers": {
    "rememb": {
      "command": "rememb",
      "args": ["mcp"]
    }
  }
}

2. Restart your IDE.

The agent now automatically reads memory at session start, writes when learning something new, and searches when needed.

Without MCP

rememb rules   # Print generic rules for AI agents

Copy the output to your editor's rules file (.windsurfrules, .cursorrules, CLAUDE.md, etc.)


How it works

.rememb/
  entries.json   ← structured memory (project, actions, systems, user, context)
  meta.json      ← project metadata

A JSON file in your project. Your agent reads it at the start of every session.

User: "We're using PostgreSQL, auth at src/auth/, async patterns"
Agent: [rememb_write] → Saved

[New session]
Agent: [rememb_read]  → Context loaded
Agent: "I see you're using PostgreSQL with auth at src/auth/..."

Search uses local semantic embeddings (no API, no cloud). Falls back to keyword search if embeddings aren't available.


Memory sections

Section What to store
project Tech stack, architecture, goals
actions What was done, decisions made
systems Services, modules, integrations
requests User preferences, recurring asks
user Name, style, expertise, preferences
context Anything else relevant

TUI

rememb includes a full terminal UI built with Textual.

rememb          # Open the TUI

Features:

  • Grid of memory cards — browse all entries organized by section
  • Sidebar navigation — filter by section with entry counts
  • Inline search — press / to search across all entries
  • Side panel — create or edit entries without leaving the screen
  • Dynamic layout — grid adapts to terminal width (1–4 columns)
  • Keyboard shortcutsCtrl+N new, Ctrl+R refresh, / search, Q quit

CLI

rememb          # Open the TUI
rememb mcp      # Start MCP server for AI agent integration
rememb --version, -v    # Show version
rememb --help, -h       # Show help

Design

  • Local first — plain JSON file in your project
  • Portable — copy .rememb/ anywhere, it works
  • Agnostic — any agent, any IDE (MCP or CLI)
  • No lock-in — no servers, no API keys, no accounts

Contributing

git clone https://github.com/LuizEduPP/Rememb
cd rememb
pip install -e ".[dev]"

PRs welcome. Issues welcome. Stars welcome. 🌟


License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rememb-0.4.1.tar.gz (29.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rememb-0.4.1-py3-none-any.whl (30.4 kB view details)

Uploaded Python 3

File details

Details for the file rememb-0.4.1.tar.gz.

File metadata

  • Download URL: rememb-0.4.1.tar.gz
  • Upload date:
  • Size: 29.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for rememb-0.4.1.tar.gz
Algorithm Hash digest
SHA256 dc72921ef381d1fbdbb9114fa84d978f8e4e228c97c7eaeabee6db0273b5c702
MD5 cfeda74e68dcb5d907fe55dff77aa106
BLAKE2b-256 b54211948c0f469ca30e3328d97df566291edc806d49d2eaba597e0b1a3fc020

See more details on using hashes here.

File details

Details for the file rememb-0.4.1-py3-none-any.whl.

File metadata

  • Download URL: rememb-0.4.1-py3-none-any.whl
  • Upload date:
  • Size: 30.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.4

File hashes

Hashes for rememb-0.4.1-py3-none-any.whl
Algorithm Hash digest
SHA256 7acc605f1562ae468f6f7a083528e232392c308168c65142ca135f889cdd31d2
MD5 a4716fad32a02e7ddd82b468c0a2a77f
BLAKE2b-256 cce7872660bf8ad8f9c33516fd5a7a140b286502e6756bc05a5c032c036809ad

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page