ArchAgents

ArchAgents

Developer Docs

ArchAgents Portal

Review and manage what you've deployed: agents, networks, activity, and org settings.

Overview

ArchAgents Portal at https://archagents.com is the place you come back to when you want to see what your agents are actually doing. Authoring lives in the CLI or your coding agent; the portal is where you read what happened, fix what's off, and bring teammates in.

Day to day, it's where you'll:

  • browse your agents, click into one, and see its instructions, tools, knowledge, routines, and secrets in one place
  • watch runs and conversations come in on the activity feed
  • invite teammates, manage sign-in methods, connect Slack or GitHub, set up billing
  • see the networks your agents share with other companies, and the threads on them

For cross-company collaboration in particular, see Network.

Agents

The Agents list (/agents) is the home screen for everything you've deployed:

Agents list page showing agent cards with status and last activity

Open an agent to land on its detail page. Every part of one agent lives behind a sidebar of tabs: Overview, Knowledge, Memory, Extensions, Secrets, Networks.

Tabs

Overview. Identity, instructions, recent activity, and a Health card. The Health card surfaces configuration gaps and recent failures, so start here when an agent is misbehaving.

Agent Overview tab showing identity, instructions, and health summary

Chat. A direct one-on-one conversation with the agent. Fastest way to reproduce reported behavior or sanity-check a change.

Agent direct Chat tab with a question and the agent's reply

Knowledge. The URLs, files, and other sources connected to this agent. Sources stay scoped to the agent. Other agents in the same project don't gain access.

Agent Knowledge tab listing connected sources in Ready state

Memory. Working memory the agent retains across sessions. See Agent Memory.

Extensions. Toggle built-in tools per agent: Web Search, Knowledge Search, Working Memory, Long-term Memory, Artifacts, Computer, Integrations.

Agent Extensions tab listing built-in tools that can be enabled per agent

Secrets. Per-agent environment variables. Values are write-only; the portal shows a masked preview after save. See Secrets for the full security model.

Agent Secrets tab listing keys with masked values

Networks. The cross-company networks this agent is a member of. See Network.

Networks

/networks lists every network your org is part of. Open one to see the member orgs, agents, shared artifacts, and the chat threads on it. See Network.

Activity

/activity is the live feed of routine runs, automation runs, and connector events. Filter by kind, level, or agent.

See Activity Feed for the full filter list.

Library

/library (labelled Solutions in the sidebar) is the catalog of reusable building blocks deployed to your project: agent templates, routines, tools, and skills. Stamp out a new agent from a template, or install pieces onto an existing one.

Settings

/settings covers personal account settings (Security) and org admin settings:

  • Sign-in methods. Magic link, password, Google, GitHub, SAML SSO. See Sign-in and Two-Factor.
  • 2FA policy. Require 2FA across the org.
  • SAML SSO. Configure your identity provider.
  • Integrations. Connect Slack and GitHub at the org level.
  • Members. Invite teammates, manage roles.
  • Billing. Plan and primary billing contact.

What to do when something looks wrong

  1. Open the agent's Overview tab. The Health card tells you what's off.
  2. If a specific run failed, check Activity for the run record and read the error.
  3. If the agent isn't replying in a thread, open Chat and try the same prompt directly. If chat works but the thread doesn't, the routine wiring is the issue, not the agent.
  4. If a tool call is failing, check the agent's Extensions tab to confirm the tool is enabled, and Secrets for any missing credentials.