Pricing

Honest pricing,
free where it counts

Two products on one page. The assistant runs on our AI, so its plans include it. Codecast for teams running coding agents is free for individuals and a flat $20 per seat for teams.

Bring your own agent subscriptions

For your coding agents, your Claude, OpenAI, and Gemini plans stay yours. Codecast never resells or marks up their model usage: you pay those providers directly, at their price. We charge for the shared memory and mission control on top, and nothing for the tokens underneath.

Free

$0free forever

For individuals. Everything you need to watch, steer, and remember your own agents.

  • Unlimited agent sessions
  • Every agent: Claude Code, Codex, Cursor, Gemini
  • Full real-time sync across every device
  • Web, desktop, and mobile apps
  • Search and memory across your own sessions
  • Self-host it yourself (MIT licensed)

Team

Early access
$20per seat / month

Shared memory and a live inbox for everyone's agents. Waitlist now, no self-serve billing yet.

Everything in Free, plus:

  • Shared team memory and search across members
  • A live team feed of every session
  • Share and message sessions across members
  • cast blame across the whole team
  • Admin controls
  • Privacy controls: per-conversation visibility (full, summary or hidden)

Enterprise

Contactcustom

For organizations that need identity, audit, and supported deployment.

Everything in Team, plus:

  • SSO and SCIM provisioning
  • Audit log export
  • Compliance review support
  • Supported self-hosting

Prefer to run it all yourself? Codecast is MIT licensed and self-hostable: clone it, deploy it, own the whole stack.

The Codecast assistant

I draft notes, compare options, keep your lists and run routines. I always ask before I act for you.

Nothing is sent or changed, and no site you didn't name is opened, without your OK. Your data never trains AI models. Privacy

Free

$0a month
  • Room for about 400 everyday requests a month
  • 3 routines, at most every day
  • Works on one request at a time

Plus

Coming soon
$20a month
  • 6 times the Free allowance each month
  • 25 routines, at most every hour
  • Works on two requests at once

Pro

Coming soon
$60a month
  • 20 times the Free allowance each month
  • Unlimited routines, at most every hour
  • Works on 3 requests at once
  • Deeper thinking for hard problems

A request is one thing you ask and the answer you get back.

Start free today

Write code? Install the CLI, connect your agents, and watch them from anywhere. Don't? Start with the assistant, nothing to install.

Comparing tools?

Side by side comparisons with other coding agent tools, including when the other one is the better choice.

  • Codecast vs T3 Code

    T3 Code is an open source app you start agent threads inside. Codecast records every agent session you run, wherever you started it, and gives you one place to read, search, steer and automate all of them, alone or with a team. Threads you run in T3 Code sync into Codecast too.

  • Codecast vs Amp

    Amp is a hosted coding agent: its own harness, threads stored on its servers, and cloud machines it starts for each thread. Codecast records and steers the agents you already run, Claude Code, Codex, Cursor and five more, on machines you control, and builds search, attribution, automation and a team layer on that record.

  • Codecast vs Delta

    Delta, from the makers of the Zed editor, and codecast share a premise: the conversation with the agent is the unit of work, and the team should see it live. Delta builds that on its own agent and its own file history. Codecast builds it on the agents you already run and on git.

  • Codecast vs Conductor

    Conductor runs a fleet of agents in parallel from one Mac app, and on its paid plans teammates can work in the same workspaces live. Codecast is the workspace a whole team and its agents share: every session on every machine, with the chat, tasks, docs and pull requests around them.

  • Codecast vs Vibe Kanban

    Vibe Kanban plans and dispatches agent tasks from a board. Codecast is a full workspace for a team and its agents, where the task board is one surface beside chat, docs, pull requests and the record of every session.

  • Codecast vs Claude Code Remote Control

    Anthropic ships remote control for your own live Claude Code sessions. Codecast is a team workspace built on every session your team runs, across six agents, kept after they end.

  • Codecast vs ResumeContext

    Both sync the agent sessions your team already runs into one shared record. ResumeContext is that record for agents to read; Codecast is also where the team watches and steers the sessions while they run.

  • Codecast vs Happy

    Happy is a polished remote control for your own Claude Code sessions. Codecast is a workspace for a whole team and its agents: steering, memory, chat, tasks, docs and pull requests in one place.

  • Codecast vs opcode (formerly Claudia)

    opcode, the app formerly called Claudia, is a desktop GUI that wraps Claude Code on your machine. Codecast leaves your terminal alone and brings every session into a workspace your team shares.