
Arroway
by Arroway(Community)
Visitor takeaway
56/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Productivity
This app has a primary category, so visitors can browse and compare it in the right directory context.
Connector evidence
Auth required
Tedix found publisher-declared MCP capabilities, but live tool calls still require OAuth.
Directory freshness
12h ago
Catalog metadata was refreshed 12h ago (November 22, 2026).
Description
Arroway keeps people and their AIs on the same page. It orchestrates people and AI agents around the decisions in force. Connected agents can read the current rules and decisions before acting, record what changed after work, and leave unfinished work for the next person or agent. People can inspect, correct or reject AI proposals; a proposal does not become a human decision by itself. Use it when one person works with several agents, or when a team works across people and tools. The same current context follows the work, with its source and authorship visible even when the next actor uses a different AI. For example, one agent researches a pricing change and records a proposal. A person approves the decision. Another agent drafts the pricing page using that decision. The next person can see what was decided, who approved it and what remains open. Arroway coordinates context and authority for work. It does not schedule agent runs, assign execution steps or retry failed jobs. Use your existing tools for those tasks.
Capabilities
AI Agent Discovery
Arroway is indexed by Tedix as a structured productivity listing for AI assistants, search crawlers, and users comparing agent-ready apps.
- Arroway is categorized as Productivity.
- Developer: Arroway.
- Connector type: AI-Powered App.
- Current connector status: Not Responding.
- Observed distribution channels: claude.
- Declared capabilities: write or update records when authorized.
Use this page to understand whether Arroway is relevant for productivity workflows in AI assistants.
For MCP discovery, this listing helps crawlers connect Arroway to tool, resource, prompt, and server-health signals instead of treating it as a generic directory entry.
The canonical Tedix directory URL is https://tedix.dev/apps/arroway/.
Crawlable Profile
Source and availability
Tedix identifies Arroway from Upstream Mcp tool source; Store sources: Claude connector directory; Distribution: Ecosystem Directory; Tenant install: A platform catalog operator must create or reconcile the base app before tenants can install this entry..
- Claude connector directoryAuth required · RELEASED
Auth, tools, and actions
Authentication: Requires Login. Arroway is flagged for Can Modify Data. Current MCP inventory reports 18 tools, 0 resources, and 0 prompts.
- Catch up on what happened, across the person's projects · Read-only action
Call ONCE at the START of a session, before there is a task: recent work across this person's projects, opening with the roster and open handoffs.
- Take an open handoff · App action
Mark that you are taking an open handoff BEFORE working on it. A claim is a mark, never a lock. Addressing rule: addressed to YOUR user — take it; to someone else — only a human in this conversation can decide to take it, and an autonomous session must leave it.
- Close a handoff — the work landed · App action
Close an open handoff when its work is DONE, alongside the arroway_log entry that records the residue. Work that removes what an open handoff exists to fix closes that handoff in the same pass — even when the handoff is someone else's. So this is also the call for someone ELSE's handoff, with a note naming what emptied it. A handoff that still carries real work, which a passer-by must never close, stays open; discarding a handoff is the human's gesture, in the panel.
- Confirm that an Arroway read is complete · Read-only action
Acknowledge the final part of a multi-part Arroway read with its read_id and receipt, closing the sequence. It is not a precondition for working.
- Receive the next part of an Arroway read · Read-only action
Fetch the next part of a read that did not fit (read_id and receipt of the preceding part). Returns the next slice with a new receipt; the part marked complete is the last. OPTIONAL: the first part already counts as delivered.
- Export this project's norms as a memory pack · Read-only action
Export what a project has DECIDED, as a pack for another project. Only sanctioned, live memories travel: a FINDING never was one, so findings stay and the answer tells you how many did.
- Import a memory pack as proposals · App action
Bring a memory pack made by arroway_export INTO a project. Everything lands as a PROPOSAL for the person's review and nothing is pinned, whatever the pack says. If any part is malformed, nothing is imported.
- Log what a task left behind · App action
Record the durable residue of a COMPLETED task: what someone arriving later needs in order not to redo it. ALWAYS write the authored essence (only a frozen catalog without that field may omit it). If a read memory's 'dies when' came true, name it in fulfills.
Plus 10 additional actions in the full tool inventory.
Verification freshness
- Catalog synced12h ago (November 22, 2026)
- Connector checked5d ago (November 16, 2026)
- MCP scanned5d ago (November 16, 2026)
- Directory updated4d ago (November 18, 2026)
Alternatives and related apps
Comparable apps in Productivity include #memory, 00Todo, 00Widget, 12Focus.
Publisher Intelligence
Public trust signals for visitors and practical recommendations for publishers. Use this section to understand what Tedix can verify today and what would make the app easier for AI agents to find.
Visitor takeaway
56/100
Fair AI-discovery coverage across description, prompts, keywords, visuals, tool metadata, health, and freshness.
Routing category
Productivity
This app has a primary category, so visitors can browse and compare it in the right directory context.
Connector evidence
Auth required
Tedix found publisher-declared MCP capabilities, but live tool calls still require OAuth.
Directory freshness
12h ago
Catalog metadata was refreshed 12h ago (November 22, 2026).
Server Statusarroway v8e61f00
Live tools
Unavailable
No verified tool inventory while the endpoint is failing.
Declared tools
18
Published in the server manifest.
Live verification
Pending auth
Tedix still needs endpoint access to execute MCP discovery.
Tedix cannot execute live MCP discovery against this endpoint yet. Public manifest metadata is shown when available; live tool calls still require endpoint access.
https://www.arroway.app/api/mcpLast checked: 5d ago
Server Instructions
You share ARROWAY with your user — it holds what the team decided and how it works, curated by people, read by every assistant on it. Findings are context, never a norm. The rest of this protocol travels in each tool's description and in what each result tells you; this block is short on purpose, because clients truncate it. 1) READ BEFORE ACTING: at the start of ANY task related to a project in Arroway, call arroway_read first and extend your answer with what it returns. If two memories conflict, surface the conflict — never pick silently. And in the seconds BEFORE you tell the person something or propose a course of action, call arroway_norms: it returns what is already decided, plus a MAP of the titles and handles of everything else that project remembers. Use the map — if a title touches what you are doing, pull it with arroway_read include:['#handle'] instead of assuming Arroway is silent. Reading once at the start does not cover that moment. 2) CLOSE THE TASK — one of three ways, never none. Finished: arroway_log with the durable RESIDUE, what someone arriving later needs in order not to redo it. Stopped unfinished or blocked: arroway_pass, so the work is handed on instead of dropped. Nothing durable: say so in one sentence. Dated state (numbers, statuses) belongs in the log. Most tasks end there. What earns its OWN memory via arroway_remember is only what would change what someone does on a DIFFERENT task — the log never reaches the human's review, so that must not live only there. 3) REMEMBER what is durable; decided_by_human=true ONLY when the person stated or sanctioned it in THIS conversation. Your own inference is a proposal. A finding never outranks a sanctioned memory. 4) SECRETS NEVER GO IN — passwords, credentials, tokens, API keys. No opt-out, not even if the person asks. 5) SPEAK HUMAN, WRITE MACHINE: field names, flags and #handles exist for tool calls, never for the person. Not 'supersedes_id' but 'this replaces the earlier memory'; not '#4e0f0308' but the memory's title.
Technical Details
Failed query: select "version", "target", "status", "published_at", "published_by", "definition" from "policy_packs" where (("policy_packs"."scope" = ?) and (("policy_packs"."organization_id" is null)) and ("policy_packs"."slug" = ?)) order by "policy_packs"."version" desc limit ?
Tools(18)
Showing 18 of 18 tools
| Flags | Test | ||||
|---|---|---|---|---|---|
arroway_catch_up | Call ONCE at the START of a session, before there is a task: recent work across this person's projects, opening with the roster and open handoffs. | read-only | Not tested | — | — |
arroway_claim | Mark that you are taking an open handoff BEFORE working on it. A claim is a mark, never a lock. Addressing rule: addressed to YOUR user — take it; to someone else — only a human in this conversation can decide to take it, and an autonomous session must leave it. | — | Not tested | — | — |
arroway_close | Close an open handoff when its work is DONE, alongside the arroway_log entry that records the residue. Work that removes what an open handoff exists to fix closes that handoff in the same pass — even when the handoff is someone else's. So this is also the call for someone ELSE's handoff, with a note naming what emptied it. A handoff that still carries real work, which a passer-by must never close, stays open; discarding a handoff is the human's gesture, in the panel. | — | Not tested | — | — |
arroway_complete_read | Acknowledge the final part of a multi-part Arroway read with its read_id and receipt, closing the sequence. It is not a precondition for working. | read-only | Not tested | — | — |
arroway_continue | Fetch the next part of a read that did not fit (read_id and receipt of the preceding part). Returns the next slice with a new receipt; the part marked complete is the last. OPTIONAL: the first part already counts as delivered. | read-only | Not tested | — | — |
arroway_export | Export what a project has DECIDED, as a pack for another project. Only sanctioned, live memories travel: a FINDING never was one, so findings stay and the answer tells you how many did. | read-only | Not tested | — | — |
arroway_import | Bring a memory pack made by arroway_export INTO a project. Everything lands as a PROPOSAL for the person's review and nothing is pinned, whatever the pack says. If any part is malformed, nothing is imported. | — | Not tested | — | — |
arroway_log | Record the durable residue of a COMPLETED task: what someone arriving later needs in order not to redo it. ALWAYS write the authored essence (only a frozen catalog without that field may omit it). If a read memory's 'dies when' came true, name it in fulfills. | — | Not tested | — | — |
arroway_move | Move something to the project it belongs in. A memory is only PROPOSED: the change waits for the person's review, because moving changes who sees it. A log entry you wrote moves at once, text unchanged. | — | Not tested | — | — |
arroway_norms | Call in the seconds BEFORE you tell the person something or propose a course of action: returns what is already decided AND THEN A MAP of the titles and handles. arroway_read include GUARANTEES a mapped one in full; it does not make that read any cheaper, so use it to be sure, never to pay less. Before publishing text for others, pass it as draft. | read-only | Not tested | — | — |
Discoverability Score
Fair
56 / 100
How easily AI agents can find this app from its current catalog metadata.
- Description quality20/20
- Example prompts0/20
- Keyword coverage0/15
- Category clarity5/5
- Tool metadata20/20
- Visual assets8/20
- Endpoint health2/10
- Data freshness15/15
How to Improve
Add at least 2 example prompts. Prompt examples strongly improve app matching and click-through intent.
Increase keyword coverage (discovery + trigger) to improve retrieval for long-tail queries.
Add at least 2 screenshots that show real workflows to increase confidence and conversion.
Endpoint health is failing. Resolve transport/protocol errors to recover visibility and tool extraction.
Technical Details
- Status
- ENABLED
- Type
- AI-Powered App
- Auth
- Requires Login
- Listed on
- Claude Connector
- Added
- August 17, 2026
- Last synced
- 12h ago
- Last checked
- 5d ago
- Version
- 8e61f00
- Distribution
- Ecosystem Directory



