LIVE
Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|
AppRisingofficial publisher

Letta

App : A product you use directly

Managed-memory agent platform, successor to MemGPT.

The most advanced solution for long-term agent memory, but demanding to set up.

Official site GitHub · 25,248 ★
Overall score
7.2 /10
Security: one caveat, see the card
Utility
7.5
Reliability
10.0
Security
One caveat
Ease
Technical · Technical

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Most conversational agents forget everything between sessions: each conversation starts from scratch, with no memory of preferences, context, or past exchanges. Letta solves this by giving agents a persistent, structured memory that evolves over time.

In practice, Letta manages a dynamic context for each agent: important information is retained, reorganized, and versioned, much like a Git repository for memory. The agent can learn from past interactions, refine its identity, and improve its responses without manual intervention.

Letta is aimed at developers and technical teams who want to integrate long-memory agents into their TypeScript applications, internal tools, or workflows. Companies such as Bilt, 11x, and Hunt Club already use it in production.

However, Letta is not designed for general audiences without technical skills: installation, configuration, and deployment require a basic command of command-line tools and server environments.

What it offers

  • ·Persistent per-agent memory: each agent retains its memories, identity, and conversation history across sessions.
  • ·Git-inspired memory versioning, allowing the evolution of an agent's context to be tracked and restored.
  • ·Interactive command-line interface to launch and control an agent directly from the terminal.
  • ·Desktop application available on macOS, Windows, and Linux for local use without server configuration.
  • ·Web access via chat.letta.com, usable from a browser including on mobile.
  • ·Integration with Slack, Telegram, Discord, and custom channels to deploy an agent within everyday tools.
  • ·TypeScript SDK (Letta Agent SDK) for embedding a memory-enabled agent into your own applications.
  • ·Letta Cloud to synchronize an agent's memory, identity, and conversations across multiple computers. (paid)

In practice

Price
Freemium
Commercial use
Commercial use: yes
Available on
web, docker, cli
Licence
Apache-2.0

Security and data

Rating
Security: one caveat, see the card
Your data
Local or cloud depending on use
Maintenance
Active
Last release
14 May 2026

Links and repository checked on 25 October 2026 · added on 1 October 2023

How to install Letta

1. Make sure Node.js is installed on your machine (required for npm). 2. Install Letta globally via npm: npm install -g @letta-ai/letta-code. 3. Launch the interactive interface by typing letta in your terminal. 4. To host a local server, run letta server. 5. Alternatively, download the desktop app from docs.letta.com or go directly to chat.letta.com. 6. Never share your API keys in a public repository: store them in environment variables.
npm install -g @letta-ai/letta-code

In the same category

Whole category Feed (memory, context) →