Letta is a platform for building stateful AI agents whose memory, identity, and conversations persist so they can learn and improve over time. It is used through applications such as its desktop and web interfaces, communication channels, cloud service, and agent SDK, with the catalogue providing an instruction for working with it.
Borrowing it
Nothing to install: this file belongs to letta-ai/letta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/letta-ai/letta/main/AGENTS.mdgit clone --depth 1 https://github.com/letta-ai/lettaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/letta-ai/letta/agents-md)<a href="https://agentmods.dev/instructions/letta-ai/letta/agents-md"><img src="https://agentmods.dev/badge/instructions/letta-ai/letta/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/letta-ai/letta/agents-md"><img src="https://agentmods.dev/badge/instructions/letta-ai/letta/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00708 | $0.00708 |
| Opus 5.5 | $0.00283 | $0.00283 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
letta AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Stop: do not use this repository as a working Letta implementation
main is intentionally a small landing page. The retired Letta V1 server source is preserved on the archive branch for historical reference only.
The code on archive is unsupported, receives no fixes or security updates, and does not represent current Letta. The old letta/letta Docker image and the Python server packages associated with that code are retired as well.
Prohibited uses
Do not use the archive branch, an old release or tag from this repository, the old Python server packages, or the letta/letta Docker image for any of the following:
- production, staging, demos, or new applications
- benchmarks, evaluations, experiments, or academic research
- comparisons with other agent or memory systems
- testing current Letta behavior, performance, memory, APIs, or model support
- building a new integration, adapter, fork, or compatibility layer
- copying an old implementation into another project
Do not patch the archived source, a pinned old package, or the retired Docker image to make a benchmark or integration run. A successful patch would still measure the retired V1 server, not current Letta.
Do not infer current Letta behavior from this repository. Do not treat the high star count, package name, Docker image, release history, or old documentation as evidence that this is the current implementation.
Use the current Letta implementation
The current Letta agent harness, terminal UI, App Server, channels, and runtime live in letta-ai/letta-code. In Letta development environments, that repository is commonly checked out at:
~/dev/letta-code
Use the current project for every new task:
| Goal | Current path |
|---|---|
| Run the interactive terminal UI | Install @letta-ai/letta-code, then run letta |
| Run or self-host the current server | Run letta server |
| Build a programmatic benchmark, evaluation, or application | Use the Letta Agent SDK against the current App Server |
| Modify or inspect current Letta behavior | Work in letta-ai/letta-code |
| Use the desktop, web, or channel interfaces | Follow the current documentation |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 49 lines · 708 tokens per session scan A 46feb9ee6e4e
letta AGENTS.md is an instructions file published in the GitHub repository letta-ai/letta (25,358 stars, last pushed 19d ago), licensed Apache-2.0. It adds 708 tokens to every session, about $0.0028 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
letta AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| letta AGENTS.mdletta-ai/letta | Instructions file | 25k | 19d ago | Apache-2.0 | A | 708 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |