Documentation
Collaboration

See your whole team's Claude Code sessions in one place

Claude Code already writes every session to disk. The codecast daemon syncs those files — plus Codex, Cursor, and Gemini — into one live team feed, inbox, and searchable record.

Every Claude Code session your team runs already writes a complete transcript to disk — Claude Code keeps JSONL history files under ~/.claude/projects/, and Codex, Cursor, and Gemini keep equivalents of their own. The sessions are recorded; they just aren't anywhere anyone can see them. Codecast turns those files into one live dashboard for the whole team.

The mechanics

Each teammate runs the installer once:

curl -fsSL https://codecast.sh/install | sh
cast login

That starts a local daemon that watches the agents' own history files and syncs each conversation to your team's workspace as it happens — no change to how anyone runs their agents. A session started in a terminal, tmux, an IDE terminal, or over SSH is picked up the same way, because the daemon reads what the agent writes, not how it was launched.

From then on, two surfaces answer the question this page is named for:

  • The feed (codecast.sh/feed) — every team-visible session, newest first, across all machines and agents. Who is working on what, right now and historically.
  • The inbox (codecast.sh/inbox) — the same sessions sorted by who acts next: working, needs input, done. A session stuck on a permission prompt surfaces at the top, and you can answer it from the web, the desktop app, or the iOS app.

Opening any session shows the full conversation live — messages, tool calls, diffs — and you can type into it from there, so "looking at a teammate's stuck session" and "unblocking it" are the same motion.

What "team-visible" means

Visibility is per directory, not all-or-nothing. Each repo path maps to a team (or stays private); a session inherits the mapping of the directory it runs in. Work in ~/src/product can be team-visible while ~/personal/experiments stays yours — same daemon, same account. Sessions can also be shared individually by link.

Beyond watching

Because every session lands in one place, the record compounds:

  • cast search "auth refactor" — full-text search across every past session on the team.
  • cast ask "how did we fix the flaky deploy?" — ask questions across that history.
  • cast blame src/api.ts:120 — trace a line of code to the conversation that wrote it.
  • Agents themselves get the same access (see Agent memory), so a fresh session can consult what any teammate's agent already solved.

Scope of the answer

Codecast's dashboard covers Claude Code, Codex CLI, Cursor, and Gemini sessions on any machine a teammate runs the daemon on. If you need usage analytics — spend, acceptance rates, seat activity — Anthropic's own analytics dashboard (claude.ai/analytics) is the right tool; codecast is about the sessions themselves: seeing them, steering them, and remembering them.

More guides
How agent snippets work
cast install writes versioned instruction sections into your agents' own config files. This is the mechanism every other guide builds on.
Give Claude Code memory across sessions and teammates
Not notes files: every session can search, read, and watch every other session your team has run. The commands, the scopes, and how agents use them.
How to search your Claude Code history across every machine
Claude Code keeps sessions on the machine that ran them. The built in picker, two local search tools, and how codecast searches every machine and every agent at once.
How to find which AI agent session wrote a line of code
git blame names whoever committed a line. cast blame names the agent session that wrote it and opens the exact message; Git AI and Agent Blame solve it with git notes instead.
Messaging between sessions
cast send turns sessions into teammates: any session can message any other, including a teammate's, and manage what the human sees in the inbox.
Ambient awareness
Stable mode injects a live feed of recent sessions into every new session at start. Combined with messaging, sessions know about each other without being told.
How to share a Claude Code session with your team
Three different asks hide behind that sentence: read a finished conversation, watch a running one, or make every session visible by default. What Anthropic ships, what Lore does, and where codecast fits.
Pinned thread state
cast state keeps one agent-written line saying where a thread stands, pinned above the composer and on the inbox card, with its staleness on show.
Decisions: asking without interrupting
cast decide puts a question, its options and the reasoning into a queue you clear when you choose to. The answer returns to the agent as a message.
Team chat that agents take part in
Channels, threads and direct messages where a mention can wake a role or a session, agent lines are capped, and a Slack workspace mirrors in.
Huddles and walkie
Every huddle is transcribed with exact speaker attribution and leaves a digest, so an agent can quote what was said on the call.
Forks and spawned sessions
cast spawn --subagent delegates a worker that nests under the session that launched it; plain cast spawn and cast fork start independent threads in the human's inbox.
Tasks and plans
The work tracking layer agents report into: tasks, plans, binding, comments, and the dashboard that watches it all.
Triggers
Follow-up work that runs after the session ends: delayed, recurring, or fired by a GitHub event.
Workflows
Execution graphs in DOT syntax: agent steps, shell commands, conditions, and human approval gates.
Orchestration
A conductor agent decomposes a plan, spawns implementers in isolated worktrees, and runs reviewers and critics over the result.
Pull requests and issues as codecast objects
cast pr and issue sync keep a copy of GitHub and Linear objects current from webhooks, send every action back, and wake the session that owns the work.
The org: roles, scopes and the line
Route work to a standing responsibility instead of a session: roles with scopes, wakes, proposals a person accepts, and a line that reviews before it ships.
Driving the human's own Chrome
cast browser works in a background tab of the Chrome that already holds your logins, and puts the evidence in the thread.
Driving a native macOS app
cast computer reads a window as an indexed tree, refuses stale indexes, and reports whether an action was verified.
One typecheck watcher for every session
cast check answers every session from one tsc --watch for each tree and project, so thirty agents do not build the same program thirty times.
The cast-* skills
23 packaged procedures, compiled into the CLI, each a fixed sequence of ordinary cast commands.
Sessions on machines you are not sitting at
How a session starts on, moves to, sleeps on and is watched from another machine, and what each lease does when the machine goes away.
Codex Cloud tasks in codecast
Sync, start and drive Codex Cloud tasks on your ChatGPT plan: attempts as branches, pull requests, applying changes locally, and what happens when the private API changes.
Usage limits are a pause
Codecast parks a session that hits a limit, then continues it at the reset or on a saved account that still has room.
The visual canvas
Agents reply with sandboxed HTML that renders inline: charts, dashboards, diagrams, and small widgets instead of ASCII art.
Published pages
cast publish turns a file into a page at a stable URL, with version history, access gates, and viewer comments that flow back to the session.
How the client syncs
Every surface paints from a local store, an append only log for each scope delivers only what changed, and one window syncs while the others copy it.