arizuko › products › Discord team agent

Discord team agent

One agent in a Discord guild, with channel-scoped persona and thread context but per-member memory, grants, and a full web workspace.

what you get

Personal cloud storage. Each member gets a private workspace accessible via WebDAV. Mount it in Finder, VS Code, or any file manager. Store notes, uploads, agent outputs — persistent across sessions.
Web interface. A browser-based chat at /chat/<token>/ against the same agent. Take the conversation off Discord onto a phone or laptop without losing context.
Google Docs and web page access. The agent can read public web pages and Google Docs you share with it — paste a URL and it fetches the content. Private docs require sharing the link; no OAuth into your Google account.
Dashboard. Operators and members with dashboard access see usage, privileges, routing rules, and scheduled tasks at /dash/. Per-member usage tracking shows turns, tokens, and tool calls.
Per-member memory. The agent maintains a memory file per member — preferences, recurring tasks, prior conclusions. Alice has hers, Bob has his.
Per-member grants. Per-member grant rules decide which actions each person can ask the agent to take. Operators set defaults; individuals can have overrides.
Linked identities. Channel use needs no sign-in — guild membership is the fence. A member who signs in at /auth/login with GitHub, Google, or Discord links that identity to one user record, so the same person reaches the same memory and grants from the web chat or a DM.

system shape

Channel as workspace. A Discord channel maps to an arizuko group folder. The product ships its base persona and rules in ~/.claude/CLAUDE.md; the channel’s own ~/CLAUDE.md overrides and extends them — allowed tools, citation rules, refusals, voice for this channel.
Thread context. Discord threads behave like conversation branches. The agent sees thread history as context, replies stay in-thread.
Customisable, upgradable in place. Persona, skills, and channel rules are plain Markdown edited via WebDAV or chat. Each release ships migrations the agent applies as a per-group 3-way merge, preserving local edits.

This page is the Discord twin of the Slack team agent — same folder model, same grants, same web workspace. The three platform deltas (no AI sidebar, mention syntax, JID shapes) are listed in that page’s same shape on Discord section.

example: shared thread, member-scoped state

#dev-chat · thread

  alice  @bot summarize the fix from the cold-start runbook for this thread
  bot    Bundle growth after deploy is coming from broad SDK imports.
         Recommended: switch back to per-service imports.
         source: /docs/runbooks/lambda-cold-start.md:67

  bob    @bot save that conclusion to my notes
  bot    Wrote notes/lambda-cold-start.md in your workspace.

  alice  @bot remember: prefer per-service imports for any new lambda
  bot    Saved to your memory.

Same thread, same channel CLAUDE.md, different resolved member state. The answer is visible to the team; Bob’s write lands in Bob’s workspace; Alice’s preference lands in her memory file. Shared deliberation, member-scoped state.

how members use it

In a channel. The bot stays quiet by default. @bot mentions fire a turn. With the recommended routing rule (see setup), channel chatter lands in #observe — agent reads for context but doesn’t reply unless called on.
In a thread. Replying to one of the bot’s messages counts as a mention — the agent answers in the same thread, with the thread’s history as context.
In a DM. Every message is for the bot. No mention needed; replies come back in the same DM.
File uploads. Drop a file on the bot or in a mentioned thread. The agent reads it and replies in-thread.
Web interface. Sign in at /auth/login to get a personal chat URL. Same agent, same memory, browser-based.
WebDAV workspace. Mount your personal cloud at /dav/<your-folder>/. Access agent outputs, notes, and uploads from any file manager.

use cases

support and analysis agent

A support agent answers questions from a knowledge base, cites sources, and escalates when it doesn't know. Useful for community support channels, internal help desks, or documentation Q&A.

Searches a facts/ directory of markdown files for answers
Cites the source file and line when answering
Says "I don't know" rather than guessing
Can triage and tag issues, track resolution status
Escalates to human operators when stuck or when the user requests it

#help-desk

  user   How do I reset my API key?
  bot    To reset your API key:
         1. Go to Settings → API Keys
         2. Click "Regenerate" next to the key you want to reset
         3. Copy the new key immediately — it won't be shown again
         source: docs/api-keys.md:45

  user   What about enterprise SSO setup?
  bot    I don't have documentation on enterprise SSO in my knowledge base.
         I've flagged this for the team. Someone will follow up.

trading and market analysis agent

A collaborative research agent that ingests news, tracks market data, and synthesizes analysis. Works best when multiple members contribute observations and the agent aggregates them.

Fetches and summarizes news from URLs you paste
Tracks observations members share over time
Maintains a shared research diary with timestamped entries
Cross-references multiple sources to identify patterns
Produces synthesis reports on request

#market-watch

  alice  https://example.com/article-about-earnings
  bot    Summarized: Q2 earnings beat estimates by 12%. Key drivers:
         cloud revenue +34% YoY, hardware flat. Guidance raised for Q3.
         Logged to research diary.

  bob    I noticed unusual options activity on XYZ today
  bot    Noted. Adding to today's observations. You've logged 3 observations
         this week on XYZ — want me to compile a summary?

  alice  Yes, give us the weekly synthesis
  bot    Weekly synthesis for XYZ:
         - Monday: Earnings beat, guidance raised (source: earnings article)
         - Wednesday: Insider filing showed CEO sold 10k shares
         - Today: Unusual options activity (Bob's observation)
         Pattern: Mixed signals. Fundamentals strong but insider selling
         and options activity suggest caution.

general team assistant

The default configuration: Q&A, summarization, file processing, and task tracking for a team channel.

data & trust

Your server. Conversation history, channel files, per-member memory, channel-scoped secrets, agent state — all live under /srv/data/arizuko_<name>/. Backup is one tar of the directory; no DB dump.
Default outbound paths. Discord for bot traffic; Anthropic for model calls. Any extra agent egress goes through crackbox and only reaches hosts you allowlist per channel.
Channel-scoped secrets. API keys for tools the agent calls live in the secrets table, AES-256-GCM encrypted at rest. Folder-scoped values are merged into the container's spawn env; guild channels get folder secrets only.
Channel boundary. A member in #dev-chat sees that channel’s context and their own workspace; #marketing’s files and persona are inaccessible unless granted explicitly.

setup

arizuko create acme
cd /srv/data/arizuko_acme
$EDITOR .env             # set Discord token; enable the adapter
arizuko run acme

# in Discord:
#   create the bot at discord.com/developers/applications
#   set DISCORD_BOT_TOKEN in .env
#   invite the bot to your guild with the OAuth2 URL generator
#   members sign in via OAuth at /auth/login for linked identities

Full step-by-step is in the operator setup guide. Per-channel CLAUDE.md override lives in the channel folder; edit via WebDAV or directly on the server.

go deeper

primitives — the same pipeline as every other agent
grants — per-member and per-group action scoping
personas — how voice + skills + frontmatter shape one channel’s agent
auth — OAuth providers, account linking, identity resolution
webdav — mounting the channel workspace
crackbox — per-channel egress isolation
deployment guide — first instance, first channel, first invite