Answers
Arroway vs Sentra: what is the difference?
Sentra describes itself as managed organization memory: an administrator authorizes sources such as Slack, Gmail, Google Drive, GitHub, Linear and Zoom once, and it compiles what happens there into permissioned context that people and agents query through an API or MCP, with answers scoped to each user's role and access. Its pages also say each fact carries two timestamps, one for when it became true and one for when it stopped being true, and that a superseded fact is marked dead with its provenance intact. It runs in its own cloud, in your VPC or air-gapped. Arroway is not built by reading your tools: it is a shared memory of what the people on a project decided, which every AI tool you already use — Claude, ChatGPT, Codex, Cursor or anything over MCP — reads before it acts. The difference is where a rule comes from. In the Sentra pages I read, facts are derived and superseded from connected sources, and they do not describe a person approving what stands. In Arroway, assistants write proposals, a person approves what becomes a rule, each rule carries the condition that ends it, and a replacement names the rule it retires. Use Arroway when a decision has to reach several tools and people as the current one, with its owner. The install page is the first step.
Last updated October 14, 2026
Compiling what happened, or recording what was decided
Sentra's pages describe memory built from connected sources: conversations, messages, documents, code and deals feed a graph that records who said what, why decisions changed and which commitments are still open, with private meetings left out. What it holds is derived from what your tools contain. Arroway starts from a different object: not what happened in the tools, but what the people on the project decided. An assistant that writes into it writes a proposal; it becomes a rule only when a person approves it.
Who decides what is current
In the Sentra pages I read, change over time is handled with two timestamps and by marking the superseded fact as no longer valid instead of deleting it, and an article on its site says meaning is resolved when data arrives, against an ontology kept for each organization. The pages mention contradictions being surfaced; they do not say how it decides which version stands, and they do not describe a person approving it. Access follows role: an answer is limited to what the person asking may see. In Arroway the project is the shared object: the people on it and the assistants they use read the same rules, each one carrying who approved it, the condition that ends it and what it replaced. Arroway does not ingest your Slack or your repositories; it holds what an assistant or a person records and a person approves.
When to use Arroway
Use Arroway when the question is not what your tools contain, but what is in force for the team: who decided it, what ends it and what it replaced. A newer decision names the rule it retires, a person approves it, and the old rule leaves the next read while staying in the history. Nothing is connected to your sources: you install it in each tool you already use, sign in, and the next session opens by reading the project and closes by recording what was decided. The first step is the install page.
What it looks like in practice
A twelve-person agency keeps its client work across Slack, Google Drive and a ticket tracker, and its people use Claude, ChatGPT and Cursor. On Tuesday the agency decides that every client report goes out only after a second person reviews the draft. On Friday the partners drop that rule for small retainers. A memory built from the connected tools can surface the Tuesday thread and the Friday thread, with their times. The question of the assistant that drafts the report is a different one: which of the two stands today, and who said so. In Arroway, Friday's rule is recorded as replacing Tuesday's, with the partner's name on it and the condition that ends it. Claude, ChatGPT and Cursor open their next session with Friday's rule, and the history shows Tuesday's, when it changed and who changed it. We have not built anything with Sentra; what is said of it here comes from its pages. The agency is illustrative.
Questions people ask about this
- Does Arroway read my company's Slack, email and documents?
- No. Arroway holds what a person or an assistant records on a project and a person approves. It does not connect to your mail, chat or drive to build memory. If you want a system to act on a decision, it reads the project over MCP like any other tool.
- Does Arroway work for agents, not only for people?
- Yes, on the same terms. An agent reads the project before acting, writes proposals and records what it did. What Arroway records is what a project decided, not a profile of one person.
- 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
Sentra's website (sentra.app) and its article on organizational memory software (sentra.app/articles/best-organizational-memory-software), both read on 14 October 2026, and the Braintrust article on AI agent memory tools dated 2 August 2026 (braintrust.dev/articles/best-ai-agent-memory-tools-2026), which lists it — Sentra is described only as those pages describe it on that date, and its features can change in any release. Product documentation on this site (How it works, Install), the answers on Arroway vs Mem0 and on the best shared memory for AI agents and teams, 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. The agency in the example is illustrative.