Documentation
Recall

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.

3 min read
Turn it on in Agent features

A coding agent starts every session knowing nothing about the work that came before it. With Memory on, your agents look things up instead of working them out again: why a function backs off the way it does, what a teammate's session already tried, which session settled the current design. They search every session you can see, across your machines, your agents and your team, read the parts that matter, and answer with the session they found it in.

A conversation where the agent was asked why webhook retries back off the way they do, searched past sessions, and answered with a link to the session where it was decided
The agent looked the decision up and cited the session. Click the link to open that conversation.

Turn it on

Memory is on by default when you connect a computer to codecast (Getting started covers connecting one). To check it or switch it off:

  1. Open Settings (⌘,), then Agent Features under Machines, and pick the computer.
  2. Find Memory under Context. The switch on its card turns it on or off for that computer.
  3. Click How it works on the card for what changes and a question to try.
The Context section of Agent Features, with the Stable context and Memory cards
Memory and Stable context, under Context.

Memory and Stable context work together. Stable context hands each new session a short list of recent sessions before it starts. Memory lets the agent find anything else, however old.

Ask for it in plain words

Agents look things up on their own when they start a task someone has touched before, when they debug, and when you mention earlier work. You can also ask directly:

  • "Why do webhook retries back off the way they do?"
  • "Has anyone on the team fixed this error before?"
  • "Do it the way we did the auth migration."
  • "What did my session on the laptop yesterday decide about the schema?"
  • "Before you start, check what's already been tried on the flaky deploy test."

What you see

  • Answers that cite their source. The agent names the session a decision came from, and the name is a link. Click it to open the conversation and check the reasoning yourself.
  • Its lookups, folded away. Each search or read shows as a small card above the reply. Open it to see what the agent looked for and what came back.
  • Less repeated work. An agent that finds a teammate's session already fixed the bug starts from that fix.

You can run the same search yourself: press ⌘K anywhere in the app and type, then ⌘↵ for the full search page. Search your history across every machine covers the search page and its filters.

What it can see

  • Only what you can see. An agent searches with your access. Your private sessions are visible to your own agents, and a teammate's session shows up only if it is shared with the team. Sharing is set per folder; see Team sessions.
  • Every machine and every agent. Sessions from all your connected computers are in one history, so an agent on your desktop can read what your laptop did. Claude Code, Codex, Cursor and Gemini sessions are all searchable, whichever agent is asking.
  • It only reads. Looking something up never edits, messages or reopens the session it reads.

When something is off

What you noticeWhat to do
The agent rediscovers something you know was settledCheck that Memory is on for that computer, then ask it to look the decision up
A teammate's session never comes upIt may not be shared with the team. Ask them, or see Team sessions
Work from another computer is missingThat computer needs codecast running and signed in to the same account
An answer quotes a decision that was later reversedAsk the agent to check for anything newer; it can read the later session too

For agents and scripts

Agents do this with cast search and cast read. You can run the same commands in a terminal, but the search page gives you the same results with filters.

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