Frequently Asked Questions
698 grounded answers to the questions users actually ask, organized into 14topics. Each answer links to the full documentation page. Use your browser's find (Ctrl/Cmd+F) on this page to search all questions.
Inside Trinity: Agentic Operating System for AI-Native Companies — the big questions about Trinity, answered in an interview
Nov 2026
Getting Started
What Trinity is, installing, first login, the first Dashboard, whitelist, templates
32 questions
Agents
Creating agents, templates, runtimes, lifecycle and reboots, the Agent Detail page, config, files, logs
61 questions
Chat & Sessions
Workspace conversations, chat tabs and Main, the composer, models, files, the rail, background work
42 questions
Credentials & Subscriptions
Credential files & declarations, the vault, encryption, OAuth, subscription headroom and failover, PATs
43 questions
Scheduling & Automation
Cron schedules, webhooks, loops, self-reminders, fan-out, asks and approvals, the skills library and the abilities plugins
69 questions
Agent Collaboration
Agent-to-agent permissions, events, report-back, shared folders, systems, rooms, asks and deliverables
53 questions
Channels & Messaging
Slack, Telegram, WhatsApp, public links, progress indicators, proactive consent, voice, phone calls
41 questions
MCP & API
MCP server, API keys and scopes, inline email auth, REST auth, receipts and polling, idempotency, CLI
41 questions
Operations & Monitoring
Dashboard views and tiles, org overlay, the Operations page, health, executions, costs, retention
50 questions
Sharing, Access & Monetization
Sharing, roles, access requests, quotas, the Workspace Inbox, clients and sessions, paid agents
53 questions
Deployment & Upgrades
Install paths incl. prebuilt images, 1-Click, AWS and Vultr, ports, upgrading, backups, retention, PostgreSQL, public exposure
58 questions
Security
Isolation, credential protection, admin gates and key scopes, guardrails, telemetry, audit log, hardening
54 questions
Advanced Features
Voice mode, canvas, images, avatars, dashboards, GitHub sync & repo binding, pipelines, abilities
42 questions
Troubleshooting
Symptom → cause → fix for the most common problems
59 questions
All questions
- •What is Trinity?
- •Do I have to use Claude, or can my agents run on other models?
- •What do I need to run Trinity on my own machine?
- •How do I install Trinity?
- •Can I use Trinity without hosting it myself?
- •What happens the first time I open Trinity in my browser?
- •What is the panel that opens over my Dashboard after I first log in?
- •How do I re-run the first-run setup, or get back to a step I skipped?
- •Where did the Getting started checklist go?
- •How do I log in to Trinity?
- •What is the email whitelist?
- •Why can't my teammate log in with their email?
- •Why didn't I receive my 6-digit login code?
- •Why does the login page say no email provider is configured?
- •I requested a login code on localhost and nothing arrived — am I locked out?
- •Why does nothing load when I open http://localhost?
- •Where do I find the web UI, the API, and the interactive API docs?
- •How is the web UI organized?
- •How do I create my first agent?
- •I'm starting a new organisation on Trinity. Which agents should I build first, and how many?
- •Which agents come with a fresh install, and can I delete them?
- •Where do I find things in Settings?
- •Trinity asked me to opt in to "Security & product updates" — what is that, and is it the same as usage sharing?
- •Why does the Sign-in email step ask me for a code?
- •Why does my new server ask for an EC2 instance ID before I can create the admin?
- •Where does the trinity-system agent come from?
- •Which database does a new install use?
- •What is a template?
- •Is Trinity free to use?
- •Are some features only available in an enterprise edition?
- •When do I need the enterprise edition?
- •Where can I get help if I'm stuck?
- •What are the different ways to create an agent?
- •Can I create an agent from a private GitHub repository or a specific branch?
- •Can I create an agent from a public GitHub repository without a token?
- •Do I need to write my own template to create an agent?
- •What goes in template.yaml?
- •How do I make sure my agent's Claude Code plugins survive a rebuild or a move?
- •Why did creating my agent fail with an error about the base image?
- •What's the difference between the Claude Code, Codex, and Gemini runtimes?
- •How do I start and stop an agent?
- •Do my agents come back on their own after the server reboots?
- •What survives an agent restart, and what survives a recreate?
- •How should I organise my agent's workspace?
- •What happens when I delete an agent — is everything gone immediately?
- •Why can't I create a new agent with the same name as one I deleted?
- •Why is my agent's name different from what I typed?
- •Why does the Create Agent dialog look different?
- •What happens when I rename an agent?
- •How do I change an agent's friendly display name without renaming it?
- •What's the difference between renaming an agent and giving it a display label?
- •How is the Agent Detail page organized?
- •What's in an agent's Settings tab?
- •Where did the Info, Credentials, Access and Folders tabs go?
- •What does the bar at the top of Settings mean, and when does it clear?
- •How do I change an agent's execution timeout, and why was my new value refused?
- •How do I find a setting on the agent's Settings tab?
- •How do I limit how much CPU and memory an agent can use?
- •How long can an agent task run before it times out?
- •What does read-only mode do?
- •What does the autonomy toggle actually control?
- •Which model do schedules, reminders and wakes run on?
- •Why can't my agent schedule its own wake-up or run a cron job from inside a task?
- •How do I move an agent to another Trinity instance?
- •Can I get shell access to my agent's container?
- •How do I browse and edit the files inside my agent's workspace?
- •What can someone I shared my agent with do in the Files tab?
- •Why was my file write refused?
- •How do I get a file into my agent's container, and can I send a ZIP?
- •Where can I see my agent's logs?
- •What is the compatibility report on the Overview tab, and can Trinity fix what it finds?
- •Is there a limit on how many canvases an agent can hold?
- •I already have a GitHub repo — how do I turn it into an agent?
- •I already run several Claude Code agents on my own machine. How do I move them onto Trinity?
- •Why was my new agent created pull-only instead of getting its own working branch?
- •How do I turn my agent's auto-sync on or off?
- •My agent was created from a public template and can't push anywhere. Can I fix that without recreating it?
- •Why did a Push untrack some of my agent's files, and where do I see what changed?
- •Does my agent's .claude/settings.json get committed to its repository?
- •Why does my agent's .gitignore contain rules I never wrote, right after creation?
- •Can my agent disable or edit its own guardrails?
- •Where do I see which credentials an agent still needs?
- •Where does the list of GitHub templates come from?
- •What does "What is this repository?" mean when I create an agent from my own repo?
- •I asked for 8 CPUs but the server only has 4 — will my agent fail to start?
- •Does a Gemini agent remember earlier turns?
- •Why did my agent's chat reply show up as a failure even though it wrote some text?
- •Do guardrails and read-only mode protect agents on every runtime?
- •Why did the Canvas tab jump to a different canvas while I was reading?
- •How do I give every agent on my instance the same rules?
- •Where should my fleet's shared knowledge, the "company brain", live?
- •Should every agent get its own email address and accounts?
- •My agent started a background task on itself and heard nothing back. Should it send the task again?
- •How do I start chatting with an agent?
- •What's the difference between the Workspace and the Chat tab?
- •What does the agent actually remember between turns in the Workspace?
- •Does the agent remember me from one chat to the next?
- •Why doesn't my agent seem to remember anything between turns?
- •Why does a long conversation suddenly take much longer on one turn?
- •Is the context window always 200K tokens?
- •What is the Main chat, and what does Reset do?
- •How do I start a new chat with an agent, and can I rename it?
- •Will I lose what I was typing if I switch to another agent or chat?
- •What is "Suggested for you" in the Workspace?
- •How do I make the agent forget the conversation and start fresh?
- •What do / and @ do in the Workspace composer?
- •Who can see my chat history?
- •Where can I see what a chat message cost?
- •Can several chats run on the same agent at once?
- •Why am I told the conversation is already handling a message?
- •How can I tell what the agent is doing while it works in the Workspace?
- •How do I stop a turn that's stuck or running too long?
- •Why did my message fail, and why isn't there always a Retry button?
- •Why does a chat turn show as failed when the agent had already written part of an answer?
- •Will my chat pick up where a scheduled run left off?
- •Do chat_with_agent calls share a conversation with my Workspace chats?
- •Where are my earlier conversations on the Chat tab?
- •Why does the Chat tab say "Agent Not Running"?
- •Can the agent keep working on something in the background while I chat?
- •What happens if I close my browser while the agent is still working?
- •Can I pick a different model for a chat?
- •What are the Fable 5 and Sonnet 5 models?
- •Does chat render markdown, and can I attach files?
- •How do I send files to my agent in the Workspace, and where do they end up?
- •How do I remove an attachment before sending it?
- •How do I know a reply has arrived when I'm not looking at the chat?
- •How is the Workspace Inbox sorted?
- •Can I switch the Workspace between light and dark mode?
- •What are the tabs in the rail beside the conversation?
- •What is the Steward card on a project page?
- •Why did the agent update a canvas I wasn't looking at, or say which canvas it changed?
- •Can I pin or delete canvases, and who is allowed to?
- •How do I share a canvas with someone outside Trinity, or save it as a PDF?
- •Why does the Workspace say earlier messages in this chat aren't shown?
- •Can I talk to my agent with voice?
- •How do credentials work inside a Trinity agent?
- •How do I add or edit credentials on an agent?
- •Can I change credentials on a running agent without restarting it?
- •What is the .credentials.enc file, and is it safe to commit to git?
- •Do I need to re-enter credentials every time an agent restarts?
- •Why didn't my MCP server pick up a credential I just changed?
- •What kinds of credential files can I inject into an agent?
- •Why does Trinity reject some files when I try to inject them?
- •Can I inject binary credentials like certificates or keystores?
- •Can I connect an agent to Google, Slack, GitHub, or Notion without pasting API keys?
- •Why does a Google sign-in link from my agent appear unredacted in chat?
- •Why does a hostname or link in my agent's reply show as ***REDACTED***?
- •Can I add my Claude key without SSH-ing to the server?
- •What happens to my agents when I connect the first Claude credential or remove the platform API key?
- •Can I check a subscription token before registering it?
- •Why was my Gemini key refused, and which agents get it?
- •What are subscription credentials?
- •Do I have to assign a subscription to every new agent manually?
- •What happens when my agent hits a rate limit on its Claude subscription?
- •Why didn't my agent switch subscriptions when a turn hit its turn limit or said the prompt was too long?
- •What happens when every subscription is rate-limited?
- •If I mix Claude Code, Codex and Gemini agents, which ones get subscription pooling and failover?
- •How do I keep model cost down?
- •How do I see how much of a subscription's limit is already used?
- •Why does a subscription show more than 100% of its limit?
- •Does reading subscription headroom cost me quota?
- •Can Trinity warn me before a subscription hits its weekly limit?
- •How does Trinity know a rate-limited subscription has recovered?
- •If I rotate a subscription token, will it interrupt agents mid-task?
- •I put an Anthropic API key in my agent's .env, so why does it still use the subscription?
- •Why is the Register Subscription button disabled in Settings?
- •Should I use a per-agent GitHub PAT or the platform-wide one?
- •Can I use my own GitHub token instead of the platform-wide one?
- •Do I need a GitHub token to build an agent from a public repo?
- •Are my credentials ever stored in Trinity's database?
- •I upgraded Trinity — do I need to rotate my platform API keys?
- •What is the Credential Vault, and how does an agent use it?
- •How do I rotate the platform encryption key?
- •How do I move an agent's credentials to another Trinity instance?
- •Can an agent ask me for a credential that belongs to an agent on another Trinity?
- •How do I know which credentials an agent actually needs?
- •How does a template declare the credentials it needs?
- •I rotated the platform GitHub token — do I need to restart my agents?
- •How do I schedule a recurring task for an agent?
- •Can I set a timezone for my schedule?
- •How do I know my cron expression is valid before I save the schedule?
- •Can a scheduled run deliver its output to a person's Workspace instead of only the execution log?
- •Can a scheduled brief remember things about the person it's for?
- •Why was my companion agent's scheduled brief skipped with "Held"?
- •Why didn't my schedule fire even though it's enabled?
- •What's the difference between disabling a schedule and turning off autonomy?
- •Can I run a schedule right now without waiting for the next cron tick?
- •What happens when a schedule fires while the agent is already busy?
- •How long can a scheduled task run before it times out?
- •Do failed scheduled runs retry automatically?
- •Can Trinity check that a scheduled run actually did its job?
- •What happens to the execution history if I delete a schedule?
- •Can my agent skip a scheduled run when there's nothing to do?
- •Can an agent schedule itself to run again later?
- •How is an agent self-reminder different from a cron schedule?
- •Do agents run on a heartbeat, or on triggers?
- •How does an agent carry a piece of work that takes many days across many sessions?
- •How do I see or cancel the reminders an agent set for itself?
- •How do I trigger a schedule from an external system like CI/CD?
- •What should I do if my webhook URL leaks?
- •Why are my webhook calls getting rejected with 429?
- •What is an agent loop and when should I use one instead of a schedule?
- •What happens to a running loop if the backend restarts?
- •Can I start and watch a loop from the Workspace?
- •Can I just tell my agent in chat to run a loop or check something every few minutes?
- •Can each loop iteration see the previous iteration's result?
- •How do I keep a loop from running forever or burning my budget?
- •What happens to a loop when one iteration fails — does it stop or keep going?
- •Can an agent start a loop on another agent it has no permission for?
- •How do I run many tasks in parallel on one agent?
- •What are skills and playbooks, and how do I run one?
- •How do I find out which agents already have a given skill?
- •Can I assign a skill from the Library page?
- •What happens if I assign a skill the library marked deprecated?
- •Can a skill be a whole folder of files instead of a single markdown file?
- •Why does my playbook say "No description available"?
- •Does a skill's allowed-tools frontmatter limit what the agent can do?
- •How do I assign skills to an agent, and do I need to restart it?
- •Why does a library skill show "name conflict" instead of installing?
- •Why is my orchestrator agent refused with skill_management_not_permitted?
- •How do I make a skill wait for someone's approval before it runs?
- •What happens after a gated skill request is approved?
- •What does the approval card for a gated skill show, and who gets it?
- •Why didn't I receive an approval request for a gated skill?
- •What happens when an agent's work needs a human decision?
- •How can I see whether a schedule is actually performing well?
- •Can the skills library sync from more than one repository?
- •I upgraded from a single skills-library URL — where did my library go?
- •Where do skills have to live inside a source repository?
- •Will a skills-library update reach my running agents automatically?
- •What happens when I unassign a skill — do the files stay on the agent?
- •Why is the community skills source pinned to a tag instead of tracking a branch?
- •The add-project-management plugin installs nothing — where did it go?
- •Do I need to install the trinity plugin inside my agent before it can run /trinity skills?
- •My template declares schedules — will Trinity create them?
- •What should a schedule's message contain?
- •My scheduled skill hangs every run and burns its whole timeout — why?
- •Can an agent trigger a schedule to get around the agent-to-agent chain limit?
- •How do I stop a webhook sender's retries from firing my schedule twice?
- •What does "Something else" on an approval do?
- •Why was my agent's ask refused with too_many_options or title_too_long?
- •Can I talk an ask through with the agent before I answer it?
- •How do I tell an agent its ask doesn't need a decision?
- •Why does an expired approval say "whether the action went ahead is unknown"?
- •Why does a heads-up in the Operations queue say "seen 5 times" instead of filing new rows?
- •Why did my agent get a "queue flood" heads-up?
- •Can I use a legacy timezone name like US/Eastern in a schedule?
- •How do agents talk to each other in Trinity?
- •Why can't my agent call another agent?
- •Why was my agent's call refused with "inter_agent_depth_exceeded"?
- •How do I let one agent call another?
- •Does the Permissions tab control who can call my agent, or who my agent can call?
- •What does granting permission actually let an agent do?
- •What is a peer skill grant, and why was my agent's call refused with "skill_not_granted"?
- •Can one agent hand off a long-running task to another without waiting?
- •Why did my agent get a caller_wake turn that nobody scheduled?
- •How do I stop an agent from being woken when the runs it delegated end?
- •Can an agent grant itself permission to call another agent?
- •What does my agent see when it lists agents with its own key?
- •What happens when I remove a permission between two agents?
- •My agent's call to another agent timed out — should it send the message again?
- •How do I share files between two agents?
- •Why doesn't the shared folder show up in my consuming agent?
- •How do event subscriptions between agents work?
- •Why isn't my agent receiving events it subscribed to?
- •Why did Trinity skip my event subscription's tasks with a "dispatches capped" alert?
- •Is it safe to put text from outside into an event payload?
- •Can an agent be notified the moment another agent's task finishes, instead of polling?
- •Can a worker agent report back to its caller automatically when it's done or fails?
- •Can several of my agents hold a conversation together in one shared session?
- •Who sets a room's limits, and who can rename it or change who's in it?
- •Can I add a colleague to a room, or leave one?
- •What happens if an agent writes a very long reply in a room?
- •Why did the agents in a room pause and wait for me?
- •What does the notice about a client reading the room mean?
- •Can I stop an agent that's working in a room?
- •Can agents in a room see the files and screenshots I send?
- •Do files I attached in a 1:1 come along when I @mention another agent?
- •Can an agent read another agent's metrics?
- •How can I watch agents collaborating on the Dashboard?
- •Can I deploy a whole team of agents in one step?
- •Can I remove a whole deployed system in one step?
- •How do I restart all agents in a system at once?
- •Can I export a deployed system as a manifest and deploy it again somewhere else?
- •Can external orchestrators discover and call my Trinity agents?
- •Can my agents call an external A2A agent?
- •How do I let an agent on another Trinity instance call my agent without handing out a key?
- •Why does an A2A call from my own private network now need a credential?
- •My A2A call came back as working — did it fail?
- •An outbound A2A call timed out — should I just try again?
- •Can my agent message me proactively instead of waiting for me to ask?
- •Can my agent ask a specific person a question and wait for their answer?
- •What happens when an agent asks a question during a room conversation?
- •Why does a card say it is waiting on someone else, and what happens when the agent's primary contact changes?
- •I answered my agent's request but nothing happened — why?
- •What does it mean when an agent's ask shows as withdrawn?
- •How does an agent deliver a report to a specific person?
- •What happens when someone rates a deliverable, and what does the agent get to see?
- •My agent handed work to another agent that finished after I left the conversation — where does the result go?
- •What's the difference between an agent loop and agent collaboration?
- •How do I connect my Trinity instance to Slack?
- •After I click Install to Workspace, Slack sends me to a page that doesn't load. Did the install fail?
- •What is the difference between Socket Mode and webhook mode for Slack?
- •Can multiple agents share one Slack workspace?
- •Can each agent have its own Slack bot identity instead of sharing one?
- •Can I control whether an agent posts to a Slack channel on its own?
- •Which agent answers when someone DMs the Slack bot?
- •Why does my agent keep replying in a Slack thread without being @mentioned?
- •How does my agent show its own name and avatar in Slack?
- •How do I connect an agent to Telegram?
- •Why doesn't my Telegram bot see every message in a group?
- •Does my Telegram agent know what the group said before it was tagged?
- •Can users send voice messages to my Telegram bot?
- •Which Gemini model transcribes Telegram voice notes, and where does the key come from?
- •Does my agent's Markdown render properly in Telegram, and what happens to long replies?
- •Why did a long Telegram reply arrive as several messages?
- •How do I connect an agent to WhatsApp?
- •Should I use the Twilio sandbox or a production WhatsApp sender?
- •Can my agent join WhatsApp group chats?
- •Is Discord supported?
- •How do users verify their email from Telegram or WhatsApp?
- •Why does my Telegram or WhatsApp bot say "Too many sign-in code requests"?
- •How do I let people chat with my agent without a Trinity account?
- •Does a public chat link remember returning users?
- •Can I use a different model for public and channel conversations?
- •Can I give my agent extra instructions that only apply to strangers?
- •Can my agent speak its replies as voice notes?
- •Why did my agent's voice reply arrive as plain text?
- •Can my agent place real phone calls?
- •What limits apply to agent phone calls, and what happens after a call?
- •How does Trinity know who is messaging my agent from a channel?
- •Can I change how many proactive messages my agent can send?
- •Does Telegram show anything while a long task is running?
- •An agent delegated my Telegram request to another agent — will I hear back?
- •Why can't my agent use all its tools when replying in Slack?
- •Why won't my agent post to a Telegram group on its own?
- •A file someone sent my agent in Slack never arrived. Why?
- •How do I stop a recurring agent from sending the same message every run?
- •Why did my agent's message come back with sent: false?
- •Can my agent post into an existing Slack thread on its own?
- •Can my agent start a WhatsApp conversation on its own?
- •What is the Trinity MCP server?
- •How do I create an MCP API key?
- •What is the difference between user, agent, and system key scopes?
- •How do I connect Claude Code to Trinity?
- •Which URL should I point my MCP client at — port 8080 or my domain?
- •Why does my client get external_mcp_access_off?
- •How many MCP tools are there, and what can they do?
- •How does an agent record a business metric over MCP?
- •Can I expose one of my agents as its own MCP tool?
- •Why can't my agent call another agent over MCP?
- •What's the difference between revoking and deleting an MCP key?
- •How do I authenticate against the REST API?
- •Can I use an MCP key instead of a JWT on the REST API?
- •Why did my API calls start returning 401 after I restarted Trinity?
- •What is the Idempotency-Key header for?
- •Why is chat_with_agent returning queued_timeout instead of a reply?
- •What is a receipt on chat_with_agent, and what do I do with it?
- •How do I poll a fan-out batch that outlived the call?
- •Can I start a fan-out and collect the results later?
- •How do I run a long task via the API and check its result later?
- •How do I cancel a running task or chat turn through the API?
- •Can I attach files to a chat or task call through the API?
- •Why was my chat or task call refused with "is not a model id"?
- •Is there a command-line tool for Trinity?
- •Where can I browse the full REST API?
- •Which endpoints work without a token, and where is the health check?
- •Why doesn't my MCP client see Trinity's tools after a backend restart?
- •Do I have to reconnect my MCP client when Trinity's MCP server restarts or is redeployed?
- •Can I connect an MCP client to Trinity without creating an API key first?
- •What is the MCP key panel on an agent's Settings tab for?
- •Why does my automation get a 403 on an endpoint my account is admin on?
- •How do I receive Trinity's real-time events in my own client?
- •Is there a browser terminal for my agent?
- •Can I ask Trinity questions about Trinity from my MCP client?
- •Can an agent read or answer the Operating Room queue over MCP?
- •Why does listing or creating MCP keys with an API key return 403?
- •Can I see what an agent can do before I call it over MCP?
- •Can I set an agent's GitHub token over MCP?
- •Can I turn git auto-sync or pull-sync on through the API?
- •Do I need an enterprise entitlement to register outbound A2A endpoints?
- •What happens when an external A2A agent I call wants payment?
- •How do I see what all my agents are doing at once?
- •What's the difference between the Timeline, Grid, and List dashboard views?
- •Where did the Agents page go?
- •Can I put fleet-level readouts on the Dashboard Grid?
- •Why doesn't the Recent failures tile just say zero when there are no failures?
- •Will my Dashboard Grid layout follow me to another browser?
- •What do the "sub limit", "sub 429s", and "sub auth" chips on agent tiles mean?
- •What does the "ready" or "calibrating" badge on an agent mean?
- •Why do dashboard panels show a skeleton, a scanline sweep, or a "stale" stamp?
- •Do new agents show up on the Dashboard right away?
- •Can I show my fleet as an org chart?
- •How do I see structured results an agent produced, without reading its chat?
- •Does a green "completion" number mean the work was good?
- •What is the Operations page and what do its tabs show?
- •What does the badge on the Operations entry in the navigation bar mean?
- •How do I turn on fleet health monitoring?
- •Why is my agent shown as unhealthy?
- •Why does the Health tab show some agents as unknown?
- •Why is my new GitHub-template agent unhealthy even though its container is running?
- •What does an alert about missed agent heartbeats mean?
- •How do agents ask me questions or request approval before doing something risky?
- •Why are there items in Needs Response that no agent sent?
- •Can I clear or cancel a pile of pending operator-queue items at once?
- •Why does an alert card say "seen 12 times"?
- •Why did an alert leave Needs Response without anyone answering it?
- •What is the "Cancel N closed by the agent" button?
- •How do I see notifications my agents send me?
- •How do I see every task my agents have run?
- •Can I watch a running execution live?
- •Can I see what my agents are running from inside the Workspace?
- •Why does an execution's response start with a "Background work lost" warning?
- •How do I stop an execution that's running too long?
- •How does Trinity track what my agents cost?
- •Can I set a daily spending limit or get cost alerts?
- •What does the "circuit open" badge on my agent mean?
- •How do I turn the circuit breaker on for an agent, or reset one that's open?
- •How do I show business numbers like revenue on an agent's dashboard?
- •Why is a metric tile on my agent's dashboard marked stale?
- •Why does my agent's metrics.json no longer show up?
- •What happens if my agent records a corrected value for a metric point it already sent?
- •What are agent reports and where do I find them?
- •What does the Overview tab on an agent's page show?
- •Where can I see the CPU, memory, and disk usage of the host machine?
- •Do my agents come back after a host reboot?
- •Where did the Terminal tab on the agent page go?
- •Where is the "Help improve Trinity" usage-sharing ask, and how do I see what it sent?
- •Will Trinity ever automatically delete my execution history, logs, or deleted agents?
- •Why was a data cleanup blocked until I approved it?
- •Can two Trinity installs share one Docker host without deleting each other's data?
- •Does Trinity back up its database automatically?
- •How do I share an agent with a teammate?
- •Why did the invitation email for someone I shared an agent with have no link?
- •What can my teammate do with an agent I've shared with them?
- •Why can't my teammate see my past conversations with a shared agent?
- •What's the difference between Settings › People and the Channels tab?
- •What user roles does Trinity have and what can each one do?
- •Who can create agents?
- •Why am I getting an agent quota error when I create an agent?
- •What role does a new user get the first time they log in?
- •Why does everyone, me included, have to accept terms of use on first sign-in, and can I change them?
- •Can people sign up for my Trinity instance on their own?
- •How does someone request access to my agent, and what happens when I approve it?
- •What's the difference between Restricted and Open access on an agent?
- •What's the difference between sharing an agent and creating a public link?
- •Can I connect a public link to Slack?
- •What is the Workspace?
- •How do I bring a second agent into a conversation?
- •What can a client see about an agent in the Workspace?
- •What can I do with an agent's canvases from the Workspace rail?
- •How do I share a canvas with someone by link, and can I take it back?
- •Why did my copied public link used to be just /chat/..., and what URL does it use now?
- •Are public links rate limited?
- •What expiry values does a public link accept?
- •What's the difference between a public link, sharing, and the Workspace?
- •How long does a client stay signed in to the Workspace?
- •Why does the Workspace ask me to accept terms of use before I can see my agents?
- •Why does the Workspace say "Add an email to use the Workspace"?
- •What's the difference between "Sign out" and "Sign out of Trinity" in the Workspace?
- •Which model does a client's conversation run on, and can they choose it?
- •Can my agent deliver a report to one specific client, and what happens when they rate it?
- •What is the Decisions section in the Workspace?
- •What does "What it may do unprompted" mean on an agent's Info tab?
- •Why does the role card say the agent "owns no objective yet"?
- •Can my agent ask a client a question, and where does the client answer it?
- •What is the Workspace Inbox?
- •How do I tag a colleague in a Workspace conversation?
- •Why does clicking an agent open an empty chat instead of my last conversation?
- •How do I close a chat tab, and can I get it back?
- •Does the Workspace have keyboard shortcuts?
- •How do I reply to one specific message from the agent?
- •Why does a Workspace link say "This chat isn't available" or "You don't have access"?
- •How do I sign a client out of the Workspace, or block them?
- •Are there limits on how much a client can send through the Workspace?
- •Can my own product sign a customer into the Workspace on their behalf?
- •How do I keep a growing fleet of agents organized?
- •Can I manage Trinity from my phone?
- •Can I charge people to chat with my agent?
- •How do I set the price for my paid agent, and can I test payments without real money?
- •How can I see the payments my agent has received?
- •My Nevermined plan is paid by card. Does that work?
- •Why does a buyer's payment token get rejected for the wrong resource URL?
- •Can other systems pay to call my agent over A2A?
- •How does my agent share a file with someone outside Trinity, and how do I revoke the link?
- •What hardware and operating system do I need to run Trinity?
- •How many agents can I run on one machine?
- •I claimed my new instance in the browser — when does the system agent appear?
- •Should I deploy Trinity locally, on a single server, or with public access?
- •Can I install Trinity from prebuilt images instead of building them myself?
- •Why did re-running start.sh --hosted upgrade my instance?
- •I checked out a new release on my Droplet, but the web UI still shows the old version — why?
- •How does the DigitalOcean Marketplace 1-Click work, and where is my admin password?
- •I opened my new Droplet and it asks me to create an admin account — is that right?
- •What does the DigitalOcean installer script do differently from the 1-Click?
- •How do I install Trinity on DigitalOcean from my own computer?
- •Can I run Trinity on AWS?
- •Why does the setup page on my AWS instance ask for an EC2 instance ID?
- •My EC2 instance got a new IP after a stop/start — do I need to do anything?
- •Can I run Trinity on Vultr?
- •Can I run Trinity on a cheap VPS?
- •Does Trinity run on ARM hosts?
- •Which docker compose files go together?
- •What ports does Trinity use?
- •How do I change the port the web UI runs on?
- •Which environment variables do I have to set myself, and which does start.sh generate?
- •How do I change the admin password?
- •I forgot the admin password on a hosted install or a claimed Droplet — how do I reset it?
- •Can I have an AI agent install Trinity for me, or run a no-prompt install?
- •What happens if I lose or change my credential encryption key?
- •How do I upgrade Trinity safely?
- •What changes by default when I upgrade from 0.9.5 to 1.0?
- •Why should I use docker compose restart instead of down and up?
- •Why can't I start any agents after running docker compose down?
- •Do my agents come back after the host reboots?
- •When do I need to rebuild the agent base image?
- •How do I back up my Trinity instance?
- •Do I still need a backup cron job, and what do backup-database.sh and restore-database.sh do?
- •How do I restore from a backup?
- •Where does Trinity actually store my data?
- •How long does Trinity keep my data, and does upgrading change it?
- •Should I use SQLite or PostgreSQL?
- •I upgraded and Trinity refuses to start. Why?
- •Can I roll a hosted install on the bundled PostgreSQL back to an older release?
- •Why does start.sh refuse to run because POSTGRES_PASSWORD is missing?
- •How do I get HTTPS on a plain VM?
- •How do I expose Trinity to the internet for webhooks and public chat links?
- •Does the whole platform need to be exposed publicly?
- •Can MCP clients connect if only ports 80 and 443 are open?
- •Why does my webhook URL show http:// instead of https://?
- •What is the Trinity Ops Agent, and when should I use it instead of raw Docker commands?
- •How do I reach a remote instance's UI without opening ports on the server?
- •How do I verify my deployment is healthy after an upgrade or restart?
- •Why is Docker using so much CPU when I run Trinity locally on Docker Desktop?
- •What does saving a Public URL (domain) actually change?
- •I saved my domain but Trinity says "waiting for the first visit" — what does that mean?
- •My domain shows a certificate error, but Trinity says the domain is set. Why?
- •If I only reach Trinity over a VPN, do I still need the web server in front of it?
- •Why do I have to log in again after restarting the backend?
- •After rebuilding the base image, how do agents pick it up?
- •How do I confirm the running deployment is actually the build I just shipped?
- •Can a container log fill my disk?
- •Is it safe to run docker system prune on a Trinity host?
- •Can agents see each other's files?
- •Can someone I share an agent with read its .env or other credential files?
- •Can someone I share an agent with get it to do what they can't do themselves?
- •Can an agent reach the platform database or Redis?
- •Do Trinity containers run as root?
- •Are my credentials stored in Trinity's database?
- •Is it safe to paste my Claude, GitHub, or Gemini key into the browser instead of .env?
- •Can my API keys leak into logs?
- •Is the GitHub token stored in my agent's git remote?
- •Should I rotate the platform GitHub token after upgrading?
- •Is it safe to commit the .credentials.enc file to git?
- •What is recorded in the audit log?
- •Does a refused MCP tool call show up in the audit log?
- •Can audit log entries be edited or deleted?
- •How long does my login session last?
- •Does changing my password sign me out everywhere?
- •Why does my login script get a 403 even though the password is right?
- •Why doesn't Trinity put my login token in WebSocket URLs?
- •Can a user receive WebSocket events for agents they can't access?
- •If I change someone's role or suspend them, do their open connections keep the old access?
- •Can a user read the event history of agents they can't access?
- •What do guardrails actually block?
- •Can an agent — or a git push to its repository — remove its own guardrail hooks?
- •Can an agent change how its guardrail hooks run?
- •Can an agent send its model traffic to another server or through its own proxy?
- •Why are some Claude Code tools missing during a scheduled or headless run?
- •What is read-only mode?
- •Is it safe to expose a fresh Trinity install to the internet before setup?
- •Can I delete or overwrite an agent's protected files from the file manager?
- •Can an event payload inject instructions into the agent that receives it?
- •Can a crafted Host header get a restricted key past its route limits?
- •Why do I need a code to change my sign-in email?
- •Can an agent publish one of its canvases to the open internet on its own?
- •Can an agent turn on its own wake-on-answer?
- •Can an agent change its own autonomy, resources, or guardrails?
- •How do I let an orchestrator agent create agents or change another agent's schedules?
- •Can an agent use its own API key to reach another agent directly through the backend?
- •Is a webhook URL secure enough on its own?
- •How do agents and the backend authenticate to each other?
- •Does Trinity phone home?
- •What does Trinity record about my usage, and does any of it leave my server?
- •How do I turn usage-data sharing on or off?
- •What should I do before exposing Trinity to the internet?
- •My instance came from a cloud marketplace and answers on a bare IP — how do I lock it down?
- •Who controls which users can access an agent?
- •An admin API key can do anything an admin can — is that a problem?
- •Can my admin API key act on behalf of one of my agents?
- •Why can't my script create or list MCP API keys using another API key?
- •What is an Ops (read-only) API key, and when should I use one?
- •How do I know my agent is authenticating to Trinity as itself?
- •What does turning on AAuth publish, and who can call my agents afterwards?
- •Who can change the AAuth settings, and can an agent do it?
- •Can a skills repository push executable code to my whole fleet without me noticing?
- •Is anything stopping a retention setting from wiping my history?
- •Can I talk to my agent by voice in the browser?
- •I clicked Talk and the call didn't start — why?
- •What is a Direct call, and how is it different from a voice call?
- •What can the agent do during a voice call, and can I limit it?
- •Can I keep talking while the agent works on a task during a call?
- •How long can a voice call last, and how do I end it?
- •Can I change my agent's voice or how it speaks?
- •Can the Workspace read the agent's replies aloud?
- •Can I dictate a message in the Workspace instead of typing?
- •What happened to Workspace Mode?
- •What is the agent canvas, and what can it show?
- •How do I get my agent to build a canvas — does it need a skill?
- •Who can see an agent's canvas?
- •How does an agent know which canvas I mean?
- •Can an agent share, pin or bulk-delete its own canvases?
- •Can Trinity generate images?
- •How do agent avatars work?
- •Why does my new agent show initials instead of an avatar?
- •Why did my agent's avatar generation fail?
- •Where do I set the ElevenLabs key for voice replies and dictation?
- •Can my agent build its own dashboard?
- •Why does my agent's Dashboard tab say some widgets were skipped?
- •My dashboard widget is bound to a metric — does it still need a value?
- •What happens if my agent records a metric value and then corrects it?
- •Why does my metric tile say "stale"?
- •What's the difference between Source mode and Working Branch mode in GitHub sync?
- •Does my agent push its changes to GitHub automatically?
- •Can my agent run git push or gh from its own terminal?
- •How can my agent use a website that needs a login, like posting or filling in forms?
- •What is a fork-to-own template?
- •What is the A2A agent card?
- •Can my agent run a long multi-stage pipeline, and can I watch its progress?
- •What are agent reports?
- •How do I turn on retrieval memory, and can I see what my agent remembers?
- •What is the abilities plugin marketplace?
- •What happened to the pre-built domain agent templates in create-agent?
- •Can I stop Trinity installing the trinity plugin into my agent at boot?
- •How do I deploy an agent I built with Claude Code to Trinity?
- •I created an agent straight from a bare GitHub repo — how do I make it Trinity-compatible?
- •How do I keep a deployed agent's schedules and plugins in sync with its template.yaml?
- •What files does my own agent template need?
- •What is the Brain Orb?
- •Why did everything log me out all of a sudden?
- •Why did signing out in one tab sign me out of my Workspace tab too?
- •My new agent shows as unhealthy right after I created it
- •My agent won't start
- •My agents are restart-looping or say the network is missing after docker compose down
- •The system agent never appears on a small (2-CPU) host
- •My agents didn't come back after the host rebooted
- •The Workspace says the conversation is already handling a message
- •Why is the Workspace microphone missing, or why does dictation fail?
- •My scheduled task didn't run
- •Every validated schedule run raised a "Validation Failed" alert
- •curl localhost:8001/health fails, but the scheduler seems fine
- •An execution has been stuck in "queued" for a long time
- •My execution failed with a timeout
- •The git sync indicator is red / sync keeps failing
- •Pull says my agent is pinned to a tag
- •Git in my agent says index.lock already exists
- •An alert says an agent's git remote still carries an embedded credential
- •Creating an agent fails: the GitHub token "is not allowed to push"
- •A push untracked files from my agent's repo
- •My webhook suddenly returns 404 or 401
- •Credentials I updated aren't taking effect
- •Settings won't save my Gemini API key
- •PUT /api/settings/<key> returns 422
- •My agent's context is at 90%+ / it hit the context limit
- •I'm getting rate-limit or auth errors from Claude mid-run
- •A failed run says Tried: … every candidate refused
- •A run fails with model_unsupported
- •A failed run shows API Error: 400 … instead of a timeout or memory message
- •A subscription's rate-limited badge won't clear
- •My Codex agent gets 401 on every turn
- •I get 403 on POST /api/token with the right password
- •The "Create your admin account" form never appears
- •My hosted install shows a login page but I never set a password
- •I changed ADMIN_PASSWORD in .env and restarted, but the old password still works
- •My MCP client can't reach port 8080
- •Docker Desktop pegs my CPU and my fans won't stop
- •I see "database is locked" errors in the backend logs
- •Port 80 or 8000 is already in use when I start Trinity
- •Where do I find the logs for X?
- •My disk keeps filling up
- •My retention windows changed after an upgrade
- •My loop stopped before finishing all its runs
- •Usage sharing says the receiver answered 404, or that the last send went somewhere else
- •The Operations queue shows "Legacy skills-library adoption refused" and Got it doesn't clear it
- •My agent's operator-queue requests stopped appearing
- •The same platform alert keeps coming back after I dismissed it
- •A "Database backup failed" or "Database backups are stale" alert appeared
- •Settings → Retention won't let me edit the windows
- •The backend log warns about unowned agent volumes
- •The canvas Share button is missing
- •An agent says it can't create a new canvas
- •The usage-sharing question never came back after I skipped it
- •My agent can't reach another agent
- •My agent's sudo command is refused by guardrails
- •A public-link visitor sees "The agent couldn't respond right now"
- •A copied public link is just /chat/… with no host
- •A Workspace link opens with no message box
- •I deleted an agent by accident