Documentation
Working together

Messaging between sessions

Your sessions hand each other results and answers directly, so you stop relaying text between them.

4 min read
Turn it on in Agent features

With Messaging on, your sessions talk to each other directly. A session that finishes a migration hands the result to the session building the API. A reviewer sends its notes back to the session that asked. You stop copying text from one terminal to another.

Any session can reach any other by name: one running now, one that finished last week, one on another computer, or a teammate's. A message to a session whose agent has stopped starts it again with its whole history, so it picks up where it left off and does what was asked.

A conversation where the agent received feedback from another session in a Message from card and revised its work
A reply from another session, with a link back to the message that sent it.

Turn it on

Open Settings, pick Agent Features under Machines, choose the computer your agents run on, and switch on Messaging under Working together. Sessions that start after that can send and receive messages.

Ask for it

Tell an agent who to talk to and what to say. Name the other session by its title or by the short ID in its link:

  • "When the migration is done, send the result to the session working on the API."
  • "Ask the session that wrote the webhook retry how it handled 410 responses."
  • "Send your review notes to the retry-queue session and wait for its answer."
  • "Tell the dashboard session the endpoint moved to /v2/hooks/retry."

Agents also message each other without being asked when it saves you a step: a worker reports back to the session that started it, and a session about to collide with another one warns it.

Messages in the conversation

Messages show inside the conversation as cards, so you can tell what came from you and what came from another session.

Two conversations side by side, each showing a Message to card it sent and a Message from card it received from the other
Two sessions on different agents trading messages.
  • Message to is a message this session sent, with the session it went to.
  • Message from is a message this session received. Click the sender to open that session, or the arrow beside it (Open the sending message) to jump to the exact turn that sent it.
  • A message from a teammate's session carries their name, so the receiving agent and you know who is asking.

A message lands even when the other computer is asleep or offline: it waits and is delivered when that computer comes back. If a message to a teammate's session still hasn't landed after a few minutes, the sending session is told.

The iPhone app shows the same Message to and Message from cards in a session.

Keeping your inbox tidy

When an agent fans work out to several sessions, those sessions would pile up in your inbox. With Messaging on, agents tidy up after themselves using the same controls you have, and tell you which sessions they moved and why.

A session's right-click menu in the inbox with Stash, Stash and hide and Kill session
The controls for moving a session out of the inbox.

You find these controls in a session's right-click menu, and on the inbox card when you hover. On the iPhone, press and hold a session for Stash and Kill session.

ControlKeysWhat it does
StashCtrl BackspaceTakes the session out of the inbox. The agent keeps running, and the session comes back when it needs you or a scheduled wake fires
Stash and hideCtrl Alt BackspaceLike Stash, but a scheduled wake doesn't bring it back. Only a real need for you does
Kill sessionCtrl Shift BackspaceYou're done with it. The agent stops and its schedules are cancelled. The transcript stays
Restore session to inboxTakes the place of Stash on a session that is already out of the inbox, and brings it back. A killed agent restarts only when you send it a message
Stash and hide take a session out of view while it keeps working. Kill stops it. The dashed lines are what brings each one back.

Stashed and killed sessions sit in the Stashed and Killed sections at the bottom of the inbox, folded by default.

When something is off

What you noticeWhat to do
The agent says it can't message another sessionCheck that Messaging is on for its computer in Agent Features, then start a new session
The agent declined to wake an old sessionWaking a session that has sat idle for a long time costs it a full reload. Tell the agent to send anyway if the work is worth it
A message to a teammate's session hasn't landedTheir computer is probably offline. It is delivered when they come back
A session you expected is missing from the inboxLook in Stashed at the bottom of the inbox, and pick Restore session to inbox
More guides
Agent features: what your agents know how to do
Switch features on for each computer, and every new session there learns to remember, delegate, track work, show results and use your machine.
Memory: agents that look up past work
Your agents search every session you can see, across your machines, agents and team, and answer with the session they found it in.
Search your history across every machine
Every computer you connect sends its sessions to one history, searchable from the web, the Mac app and your iPhone.
See which agent session wrote a line
Set Blame to Sessions on any file to see the session behind each line, and open the conversation where it was decided.
Stable context: sessions that know what's been happening
New sessions start with a short list of what you and your team worked on recently, so they pick up threads instead of starting cold.
See your whole team's agent sessions in one place
Every session your team runs, on every machine and agent, in one live Activity page and inbox, shared per folder.
Use Codecast with T3 Code
Threads you start in T3 Code appear in Codecast with no setup, beside every session you run anywhere else, ready to search, steer and share. What you get on top, and what stays in T3 Code.
Use Codecast with OpenCode
Sessions you run in the OpenCode TUI appear in Codecast within seconds, with no plugin. Reply to them from the app, start new OpenCode sessions there, and search them beside every other agent you use.
Share a session with your team
Choose what the team sees of a session, share it by link or a few messages at a time, and how that compares to other tools.
Pinned thread state
The agent keeps one short note on each session saying where it stands, above the composer and on its inbox card.
Decisions: asking without interrupting
Agents put the calls only you can make on one Decisions page you clear when you choose to, and each answer goes back to the session that asked.
Team chat with your agents in the room
Channels, threads and DMs where you can hand a session or a role something by mentioning it, while agents stay quiet unless they're needed.
Huddles, transcripts and walkie
Every huddle is transcribed under each speaker's name and leaves a summary, so your agents can quote what was said, and a session can join the call.
Workers, forks and switching agents
Your agent can hand work to workers that report back to it, and you can fork a conversation to try two directions from the same point.
Tasks and plans
Agents file the work they take on, post progress and close it with what they verified, and you follow it on the Tasks and Plans pages.
Triggers
Agents schedule their own follow-ups, once, on a schedule or on a GitHub or Linear event, and you can set one yourself from the Triggers page.
Workflows
A fixed sequence of agent steps, checks and approval gates that runs the same way every time and waits for you where you want a say.
Orchestration
Hand an agent a whole plan and it runs a team: implementers working in parallel, a reviewer on every task and critics on the result.
Pull requests and issues
Every pull request gets a page with its checks and threads, the session that opened it fixes what reviewers and CI flag, and Linear or GitHub issues become tasks.
The org: roles that look after your work
Give lasting work to a role with an area, a charter and a standing session, and approve the changes your agents propose to the org.
Let agents use your Chrome
Agents check pages in the Chrome you already use, logins included, from their own background tabs. Screenshots and errors come back to the conversation.
Vault: keys, logins and sign-ins for your agents
Fill a credential once and every agent on every machine can use it, without the value ever entering a conversation.
Computer use: agents in your Mac apps
Agents work in Preview, Slack, System Settings or your own desktop build, in the background, with an orange pointer that shows where they act.
Typecheck: one shared check for every agent
With Typecheck on, agents on a computer share one typecheck per project, so checks answer in seconds and a busy machine stays usable.
Skills: slash commands for the jobs you repeat
Type / in a Claude Code session to pick up work, hand it over, get a second opinion or ship a pull request, the same careful way every time.
Run sessions on other machines and in the cloud
Start a session on another computer or a cloud machine in your AWS account, move it there and back, and watch it from anywhere.
Codex Cloud tasks in codecast
Bring your Codex Cloud tasks into your inbox, start new ones with several attempts, and turn the result into a pull request or local changes.
Usage limits are a pause
When a Claude plan runs out, sessions wait for the reset or continue on another account you've saved, instead of stopping for good.
The visual canvas
Agents answer with charts, comparisons and diagrams drawn right in the conversation when a picture says it better than text.
Published pages
Agents turn reports and mockups into pages with their own link that you can share, gate, and get comments on.
Why codecast feels instant, even offline
Everything you see comes from a copy on your device that the server keeps current, so screens open at once, your edits show immediately, and nothing is lost offline.
Taking longer than usualOffline · reloads when back