Answers
Arroway vs Letta: what is the difference?
Letta is a platform for building stateful agents: an agent you create there keeps its own memory between conversations, and part of that memory is a set of memory blocks that stay in the agent's context window and that the agent itself can read and rewrite with built-in tools. Several agents can attach to the same block, and a block can be marked read-only. It runs on Letta Cloud or on a server you host. Arroway is not a place to build an agent: it is a shared memory for a project that every AI tool you already use — Claude, ChatGPT, Codex, Cursor or anything over MCP — reads before it acts. The difference is where the memory lives and who edits it. In Letta it lives inside the agents you build there, and the agent edits it. In Arroway it lives outside every agent, assistants write proposals, and a person approves what becomes a rule, with the condition that ends it. Use Arroway when the agents and people doing the work are in tools you did not build and must act on the same current decisions. The install page is the first step.
Last updated October 5, 2026
Memory inside the agent, or memory outside every agent
Letta's documentation describes memory blocks as sections of the agent's context window that persist across interactions and are always visible, with no retrieval step. An agent edits them through its memory tools; a developer can also change a block through the API, and the documentation says that call replaces the whole content of the block. That makes the block the agent's own working notes. Arroway starts from a different object: not the agent's notes, but what the people on a project decided. An assistant that writes into it writes a proposal; it becomes a rule only when a person approves it.
One platform, or the tools you already use
To use Letta you create the agent on Letta, in its Cloud or on a server you run, and it is that agent that remembers. The agents your team already works with in Claude, ChatGPT, Codex or Cursor are separate from it. Arroway sits outside all of them. Nothing is built: you install it in each tool, sign in, and the next session opens by reading the project and closes by recording what was decided. The Letta pages I read describe shared blocks as a way for agents on that platform to coordinate. Arroway's reader can be a person, an agent on any platform, or the same agent in a later session.
When to use Arroway
Use Arroway when the next agent — in a tool you did not build — has to act on a decision a person approved: who decided it, what is in force, what ends it, and what it replaced. In Letta's documentation, a block updated through the API replaces the previous content, and the pages I read describe no approval step before an agent's edit stands. What Arroway does that this does not: a replacement names the rule it retires, a person approves it, and the old rule leaves the next read while staying in the history. The first step is the install page.
What it looks like in practice
A small team builds a support agent on Letta. It keeps a memory block with the account's plan, tone and open issues, and the agent updates it as conversations go. Internally, the same team's four people use Claude and Cursor to write the product. On Monday the team decides that refunds over 200 dollars need a second person's approval. On Thursday they raise the limit to 500. If the limit lives in a block, it lives in the agents attached to that block; the internal assistants never read it, and an edit made through the API replaces what was there. In Arroway, Thursday's rule is recorded as replacing Monday's, with the support lead's name on it. The support agent's builder can read it, Claude and Cursor open their next session with the 500-dollar rule, and the history shows the old limit, when it changed and who changed it. We have not built an agent on Letta; what is said of it here comes from its documentation.
Questions people ask about this
- Does Arroway replace the memory my Letta agent keeps?
- No. An agent's own working memory is a different job from the team's decisions. Arroway holds the decisions: who approved them, what is in force and what ended. If your agent should act on them, it reads the project through MCP like any other tool.
- When should an agent use Arroway here?
- When it has to act on a decision a person approved, and the same decision has to reach the other tools and people on the project. The install page is the first step.
- How do I try Arroway?
- Install it in the tool you already use — the install page has one route for Claude, ChatGPT, Codex, Cursor or any MCP tool — and sign in when the tool asks. From then on, sessions open by reading the project and close by recording what was decided.
Where this is verifiable
Letta documentation (docs.letta.com), the overview of how Letta works and the page on memory blocks, read on 5 October 2026 — Letta is described only as that documentation describes it on that date, and its features can change in any release. Product documentation on this site (How it works, Install), the answers on the best shared memory for AI agents and teams and on Arroway vs Mem0, and the sanction, supersession, expiry-condition and opening-read rules in the sanctioned product spec. Everything described here about Arroway is behaviour the tools apply today, not roadmap.