Letta
LettaAgent harness for long-lived agents that keep persistent memory and rewrite their own memory blocks, skills and prompts as they work. Letta Code runs as a terminal interface, a desktop app and an App Server that applications reach through the Letta Agent SDK, and its agents can run on schedules, call subagents and answer in Slack, Telegram or Discord. Letta, the team behind MemGPT, builds it.
Read against letta-ai/letta-code, where Letta's current source lives. The original letta-ai/letta repository now holds only a pointer to it, and the retired Python server sits on an archive branch.
Openness
5 high confidence- license
- Apache-2.0(Letta Code harness, terminal interface and App Server)+MIT(bundled self-configuration skill)
- source
- public
- core features withheld
- no — the 2,450-path tree at 94145d7 carries the root Apache-2.0 LICENSE and one MIT skill LICENSE, with no ee/, enterprise/, commercial/ or proprietary/ path
- commercial
- Letta-Cloud
Letta Code is Apache-2.0 licensed, and its public source holds the harness, terminal interface and App Server, which run entirely on the user's own machine without a Letta account. Letta's paid plans sell hosted services beside it, such as cloud-stored agent state, remote sandboxes and model usage, rather than features cut from the code.
- https://docs.letta.com recorded 2026-10-07
The documentation home says "The Letta agent harness is fully open source" and offers "managed deployment with Letta Cloud or running the complete runtime yourself with the Letta App Server".
- https://docs.letta.com/self-hosting recorded 2026-10-07
The self-hosting page says "Letta agents can run entirely on infrastructure you control" and that in the local runtime "all agent state, including messages, memory, and provider connections, stays on-device, and no Letta account is required."
- https://raw.githubusercontent.com/letta-ai/letta-code/main/LICENSE recorded 2026-10-07
The root LICENSE is the Apache License 2.0 text with "Copyright 2025, Letta authors".
- https://raw.githubusercontent.com/letta-ai/letta-code/main/package.json recorded 2026-10-07
The package manifest for @letta-ai/letta-code declares "license": "Apache-2.0" and builds the CLI from the repository source.
- https://raw.githubusercontent.com/letta-ai/letta-code/main/src/skills/builtin/self-configuration/LICENSE recorded 2026-10-07
The bundled self-configuration skill carries its own MIT License, "Copyright (c) 2026 Letta, Inc."
- https://raw.githubusercontent.com/letta-ai/letta/main/README.md recorded 2026-10-07
The original repository README says "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."
- https://www.letta.com/pricing recorded 2026-10-07
Pricing sells Free, Pro ($20/month), an API plan, Teams Pro and Enterprise for the hosted app and Letta API: Letta Auto model quota, remote sandboxes, shared agents, SSO and usage-based agent hosting; no plan names a harness feature withheld from the source.
Adoption
3 medium confidenceAdoption is read from npm downloads of @letta-ai/letta-code over the trailing month, the package Letta's own instructions install. The letta package on PyPI is left out because its download history mixes the retired Python server with the current wrapper, and the desktop app is not counted.
- https://api.npmjs.org/downloads/point/last-month/@letta-ai/letta-code recorded 2026-10-07
550,932 downloads of @letta-ai/letta-code between 2026-09-05 and 2026-10-04
Capability
4 medium confidenceLetta Code agents keep persistent memory, rewrite their own memory, skills and prompts, call subagents and run on schedules across several messaging channels. That is the same self-improving, long-running agent design as Hermes Agent, and like Hermes Agent it has no published benchmark result.
- https://docs.letta.com/self-hosting/app-server recorded 2026-10-07
The App Server page says it "lets you deploy the Letta agent harness as a service" and "can manage running multiple agents in parallel in a single process", reached through the Letta Agent SDK or a WebSocket protocol.
- https://raw.githubusercontent.com/letta-ai/letta-code/main/README.md recorded 2026-10-07
The README's feature table lists self-improvement and learning through memory blocks and skill learning, message search, MemFS, skills, subagents and multi-agent calls, messaging integrations, hooks, permissions, and crons and schedules; no benchmark figure.
Verified 2026-10-07, except some scores, still awaiting re-confirmation