Letta
Official@letta-ai
Letta is an AI lab building machines that learn
Agent Skills by Letta
Showing 136 vetted skills indexed across 5 GitHub repositories.
capturing-tui-visual-proof
Captures before-and-after screenshots and GIFs of the Letta Code Ink TUI for pull requests.
creating-mods
Creates and edits trusted local Letta Code mod files with tools, commands, events, and providers.
submitting-feedback
Submits user-approved agent feedback reports to the Letta team via CLI.
generating-mod-envs
Generates and validates JSON learning envs for Letta Code mod behavior evaluation.
customizing-commands
Creates and registers custom slash commands for Letta Code mods.
image-generation
Generate and edit images from text prompts via Letta's hosted image API.
messaging-agents
Send messages to other agents on a Letta server via the conversations API.
Context Doctor
Diagnose and repair degradation in agent system prompts, memory files, and skills.
migrating-memory
Migrate memory blocks between Letta agents using memfs export and git sync.
using-mcp-tools
Discover, inspect, and invoke MCP server tools through the letta mcp CLI.
syncing-memory-filesystem
Diagnose and repair MemFS Git repository setup, sync, authentication, and merge conflicts.
managing-shared-memory
Create and manage git-tracked shared memory repositories attached to multiple Letta agents.
self-configuration
Inspect and modify Letta Code agent memory, model, permissions, and runtime settings.
scheduling-tasks
Creates and manages scheduled reminders and recurring tasks via the letta cron CLI.
letta-guide
Fetches and caches official Letta documentation via an ETag-verified Node.js helper script.
customizing-statusline
Creates, edits, and migrates Letta Code statusline mods in ~/.letta/mods/statusline.tsx.
dispatching-coding-agents
Dispatch stateless coding subagents through Claude Code and Codex CLIs for parallel research and review.
editing-letta-code-desktop-preferences
Edits Letta Code Desktop preferences by merging updates into the desktop_preferences.json file.
finding-agents
Find and filter agents on a Letta server by name, tags, or fuzzy query.
browser-use
Automate Chromium browsers via Chrome DevTools Protocol for navigation, input, and screenshots.
teleporting-between-environments
Moves agent conversations between Cloud, Desktop, and remote environments while preserving memory.
acquiring-skills
Discover and install skills from Hermes, ClawHub, and GitHub registries.
code-review
Parse GitHub PR review comments into actionable code change plans.
github-action
Update tracking comments and commit code within GitHub Actions workflows.
Frequently Asked Questions About Letta
FAQPage SchemaWhat specific tasks can I perform using Letta's agentic framework?▼
You can initialize structured memory blocks for persistent agents, manage terminal-based services like email, calendars, and media players, and execute complex data processing tasks such as PDF parsing, audio transcription, and video frame extraction.
Which technical personas benefit most from these capabilities?▼
Systems engineers, data scientists, and security researchers benefit from the ability to bridge high-level reasoning with low-level terminal operations, binary analysis, and scientific computing tasks like Bayesian MCMC sampling or Raman spectra fitting.
What are the prerequisites for running Letta-based agents?▼
Users require a Unix-like environment, basic familiarity with YAML configuration for agent memory schemas, and access to the specific terminal-based backends or runtimes required by the desired skill, such as ffmpeg, SQLite, or specific model inference engines.