LettaBot

LettaBot is an autonomous agent and bot framework developed by Letta AI (the creators of MemGPT/Letta). It was designed to run conversational and tool-using agent workflows with persistent memory and execution capabilities across terminal environments and communication channels. In daily operations, LettaBot operates as an orchestration agent that executes tasks using modular skills, file systems (MemFS), and scheduled background jobs. It supports human-in-the-loop tool calling through interactive approval workflows, automated delivery options for cron-based tasks, and voice interfaces alongside standard text prompts. What set LettaBot apart was its deep integration with Letta's stateful memory architecture and background execution tooling, allowing agents to retain context and trigger tasks on a schedule. However, LettaBot has been deprecated and officially archived by Letta AI in favor of Letta's native Channels and Remote Environments infrastructure. LettaBot is open source and hosted as a public archive on GitHub. Because the repository is archived and read-only, it is primarily of historical reference for developers studying MemGPT/Letta agent architectures rather than for active production deployments.

Tags: ai agent, chatbot, cli, developer tools, memory, OpenSource

Visit LettaBot

Key features

  • Interactive Tool Approvals — Supports human-in-the-loop workflows using commands like /approve and /disapprove before executing tools. - Automated Cron Jobs — Includes background scheduled tasks with configurable execution and direct message delivery via the --deliver flag. - Skill Extensions — Utilizes a modular .skills directory structure to register specialized agent actions and capabilities. - MemFS Integration — Integrates with Letta's virtual memory file system architecture with server-mode awareness. - Voice Capabilities — Incorporates voice interface handlers and configurations for voice-driven agent interactions. - Containerized Deployment — Provides standard Docker configurations for running isolated bot instances in CI/CD and remote environments.

Use cases

Use Case: Scheduled Context-Aware Notifications Developers can configure LettaBot to run background cron jobs that inspect system logs or repository changes and deliver formatted summaries directly to designated communication endpoints with memory persistence.

Use Case: Interactive Tool Execution Guardrails Teams can run LettaBot to automate code operations while maintaining oversight, using /approve and /disapprove controls to review risky terminal commands before execution.

Use Case: Prototyping Stateful Memory Agents Engineers exploring Letta's memory concepts can analyze and run LettaBot locally to understand how memory file systems (MemFS) interact with skills and agent orchestration loops.

Who it is for

LettaBot was targeted at developers building autonomous agents with persistent memory and interactive bot integrations across platforms. It is not recommended for teams looking for an actively maintained, production-ready coding assistant, as the repository is archived in favor of Letta's newer Channels and Remote Environments features.

Install guide

Installation Because the repository is archived, install by cloning the source repository directly: bash git clone https://github.com/letta-ai/lettabot.git cd lettabot Standard Docker builds or local package installations can be executed from the repository root: bash docker build -t lettabot .

First Run Ensure your Letta server or LLM API keys are exported in your environment prior to launching the bot: bash export LETTA_SERVER_URL="http://localhost:8283" export OPENAI_API_KEY="your-api-key"

Example Session Execute the bot or run a cron-triggered action with delivery flags: bash # Run a scheduled task with response delivery lettabot cron run --deliver # Review tool calls during interactive sessions /approve

Part of CLI Coding Agents

Categories: AI Coding Agents, Chatbot Development, Developer Tools, Memory

Related CLI agents

  • Data Olympus — Data Olympus is an open-source knowledge base and Model Context Protocol (MCP) server harness created by knaisoma. Built in Python…
  • Vestige — Vestige is an open-source agent harness and persistent memory infrastructure framework developed by samvallad33. Designed specifically for AI coding agents…
  • Agent Memory System — Agent Memory System is an open-source agent orchestration harness developed by RavByte-AI. It provides structured memory retention and retrieval mechanisms…
  • GoodMemory — GoodMemory is an open-source agent memory orchestration harness and context management system developed by hjqcan. Designed to give AI agents…
  • pi-mem — pi-mem is an open-source memory harness and persistent context manager developed by Jo Inc for the Pi CLI coding agent.…
  • Beads — Beads (bd) is an open-source task coordination and state orchestration harness for AI coding agents developed by Gastown Hall. It…
  • AI Tools
  • Categories
  • Industries
  • CLI Coding Agents
  • MCP Servers
  • MCP Categories