letta
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
GraphCanon updated 4d · GitHub synced 4d
Decision brief
letta is a Python-based platform designed to foster the development of stateful AI agents with capabilities for advanced memory techniques that support continuous learning and self-improvement. The Apache-2.0 license it鳧
Good fit when
- When you require an AI agent with robust memory features that enable continuous learning and adaptation over time.
- In scenarios where the application needs to maintain a state across interactions, allowing the AI to build on previous knowledge.
Avoid when
- If you are looking for a simple stateless AI solution without advanced memory capabilities, as letta is geared towards more complex stateful agent development.
- When your project's requirements involve strict limitations around data retention and privacy where even anonymized interaction logs might be considered sensitive.
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of 4d
- Provenance
- Not a fork · Organization account
- As of 4d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
git clone https://github.com/letta-ai/lettaHow it fits your stack(6)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
hermes-agent231k★
AutoGPT187k★
mem063k★
Memori16k★
honcho6.7k★
langflow153k★
mempalace58k★
langchainjs18k★
memvid16k★hermes-agent231k★AutoGPT187k★mem063k★Memori16k★honcho6.7k★langflow153k★mempalace58k★langchainjs18k★memvid16k★Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
letta-ai/letta is a development platform focused on creating stateful AI agents capable of learning and self-improvement through advanced memory techniques.
Capability facts
No sourced capability facts yet. Facts appear after ingest scans repo manifests (Dockerfile, package.json, MCP configs).
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 17, 2026)
npm install -g @letta-ai/letta-codeSource link
Tags
README
Letta
Build stateful agents with memory that can learn and improve over time.
Letta (f.k.a. MemGPT) is actively developed. The current source code lives in letta-ai/letta-code, which includes the agent harness, interactive terminal UI, App Server, channels, and the runtime used by the desktop and web apps.
[!NOTE] This repository now serves as a landing page for the Letta project. The retired Letta V1 server source is preserved on the
archivebranch for historical reference.
Get started
Install Letta from npm:
npm install -g @letta-ai/letta-code
Launch the interactive terminal UI:
letta
Run the App Server for local or self-hosted agents:
letta server
You can also use Letta through:
- the desktop app for macOS, Windows, and Linux
- chat.letta.com in your browser, including on mobile
- Slack, Telegram, Discord, and custom channels
- the Letta Agent SDK for building agents into TypeScript applications
- Letta Cloud for keeping agent memory, identity, and conversations available across computers
See the letta-ai/letta-code README and the Letta documentation for current installation, development, and deployment instructions.
Historical source
The archive branch contains the retired Letta V1 API server as it existed when this repository was archived. Existing tags and releases remain available for reproducibility. That source is unsupported, receives no fixes or security updates, and should not be used in production.
For agents
This page has a .md twin and JSON over the API.