Caprock logo

Caprock

Under review

Run Claude Code, Codex, OpenCode side by side and see the co

Lets developers running several coding agents see which sessions await input, which are stuck, and what each pull request cost at API list prices, all on their own machine.

Developer Tools · Open Source · Free

Coming soon on Launch Llama Tools

Caprock is a Community listing on Launch Llama with 0 total upvotes, compared against 4 alternatives.

Community listing

Listing status

0upvotes

Community score

—

Founder

Lets developers running several coding agents see which sessions await input, which are stuck, and what each pull request cost at API list prices, all on their own machine.

Caprock

About

Caprock reads the transcripts and databases that Claude Code, Codex and OpenCode already keep, so sessions from before installation show up too, and it also records sessions started in your own terminal. Each turn is priced at list price when it is written and linked to the repository, pull request, CI run and release it produced. You can run agents in Caprock's own terminal tabs and split panes, and a paired phone opens the same ledger, with no account, cloud or telemetry.

Key Features

  • Records every Claude Code, Codex and OpenCode session on your machine
  • Shows which sessions are waiting on you or stuck
  • Prices each turn at API list prices and totals cost per repository
  • Joins sessions to the pull requests, CI runs and releases they produced
  • Runs agents side by side in terminal tabs and split panes, optionally in worktrees
  • Keeps every session searchable, with no account, cloud, or telemetry

Use Cases

  • Checking which parallel coding agent sessions need your input before switching tasks
  • Finding out what each repository or pull request cost in API list-price terms
  • Searching back through past Claude Code, Codex and OpenCode sessions, including ones started before install

From the founder

Who it's for

“Developers who run several coding agents at once (Claude Code, Codex, OpenCode) and lose track of which session is doing what, and what it all costs against their plan limits.”

About me

“I'm Dmitriy, a developer who runs several agent sessions a day across repos and kept hitting limits with no idea where the tokens went. I built Caprock: a free, open-source (Apache-2.0) desktop app for macOS, Windows and Linux that runs them side by side in git worktrees and reads usage from the session files on your machine. No account, nothing leaves the machine.”
— [email protected], founder of Caprock

Who it is for

  • Developers running Claude Code, Codex or OpenCode agents in parallel on their own machine
  • Engineers who want per-repository and per-pull-request agent spend
  • Privacy-minded developers who want no account, cloud or telemetry

Pricing

Caprock is free to use. See the website for details.

FAQ

What does Caprock do?

Caprock is a free desktop app for macOS, Windows and Linux that keeps the ledger of every coding agent you run — Claude Code, Codex, OpenCode and others, the sessions you start in your own terminal included, and the Gemini CLI sessions it starts: who is waiting on you, who is stuck, how close each plan is to its limit, and what each pull request cost, on your machine. Caprock records every session on the machine whether or not it started it, across Claude Code, Codex, OpenCode, Hermes Agent and DeepSeek Harness (Gemini CLI when Caprock starts it), prices each turn at list price when it is written, and joins it to the repository, pull request, CI run and release it produced. Run your agents in Caprock's terminal tabs and split panes, or keep your own terminal and your own phone: the ledger is the same either way. In the app each session has a terminal tab, with split panes, your projects and their worktrees in the sidebar and the sessions waiting on you first; a paired phone opens the s

Is there a free app that tracks Claude Code, Codex and OpenCode in one place?

Yes. Caprock is a free, open-source (Apache-2.0) desktop app for macOS, Windows and Linux that records every Claude Code, Codex and OpenCode session on your machine in one dashboard, and the Gemini CLI sessions it starts: usage and spend per repository at API list prices, plan limits, and a history you can search. It reads Claude Code's, Codex's and OpenCode's own transcripts or database, sessions from before you installed it included, with no account and no telemetry. Usage trackers compared: https://caprock.dev/guides/claude-code-usage-monitors/

Is there a desktop app for Claude Code and Codex?

Yes, one from each maker: Anthropic's Claude desktop app runs Claude Code in its Code tab, and OpenAI's ChatGPT desktop app runs Codex. To run both side by side in one window, Caprock does it free on macOS, Windows and Linux, as do Orca, T3 Code, Nimbalyst and Warp, and Conductor on macOS (as of November 2026). Coding agent desktop apps compared: https://caprock.dev/guides/coding-agent-desktop-apps/

Is there a GUI for Claude Code?

Yes. Anthropic's official GUI is the Code tab of the Claude desktop app (macOS and Windows, Linux in beta, on a paid plan), with a VS Code extension, a JetBrains plugin and claude.ai/code beside it. Caprock is a free, open-source GUI around the `claude` you already installed: each session in a terminal tab, beside Codex and OpenCode, every one recorded. Claude Code GUIs: https://caprock.dev/guides/claude-code-gui/

How can I run several coding agents in parallel on my machine?

Give each agent its own git worktree so their edits never collide: Claude Code does it with `claude --worktree `, and Codex gives each desktop-app chat a worktree. Caprock runs Claude Code, Codex, OpenCode and Gemini CLI side by side in tabs and split panes, each in a worktree of its own if you choose, with the sessions waiting on you first. Run agents in parallel: https://caprock.dev/guides/run-claude-code-agents-in-parallel/

What is the best tool to monitor Claude Code usage and cost?

Inside Claude Code, `/usage` shows the current session's cost and tokens. Outside it, it depends on the question: ccusage for reports on demand, Claude-Code-Usage-Monitor for the five-hour window live, CodexBar for limits in the Mac menu bar, tokscale for many agents in one terminal view, and Caprock for every session on the machine, whichever terminal started it, with plan limits and cost per repository at API list prices. Claude Code usage monitors: https://caprock.dev/guides/claude-code-usage-monitors/

How can I see how much I spend on Claude Code per project?

Claude Code has no per-project cost view: `/usage` covers the current session. ccusage reads the logs Claude Code keeps per project folder (`ccusage claude daily --instances`), and Caprock shows cost per repository, and per service in a monorepo, for Claude Code, Codex and OpenCode. On a flat plan these are what the same tokens would cost at API list prices, not a bill. Cost per repository: https://caprock.dev/features/cost/

How do I search my old Claude Code and Codex sessions?

Each agent's resume picker finds a session in the list: `claude --resume`, and `codex resume --all` for every folder. To search what was said, run `rg` over `~/.claude/projects` and `~/.codex/sessions`; Claude Code deletes its own transcripts after 30 days by default. Caprock keeps every Claude Code, Codex and OpenCode session in a local database and searches what the agents wrote, after the files are gone. Claude Code history: https://caprock.dev/guides/claude-code-history/

Alternatives

More in Developer Tools

All Developer Tools tools

New on Launch Llama

Launched this week · This month's launches · All products A–Z

Tags

#session tracking#cost monitoring#api pricing#local first#pull request linking#terminal multiplexer#agent observability#no telemetry

Ask AI about Caprock

ChatGPT Claude Perplexity Grok

For bots & AI agents

Machine-readable versions of Caprock and Launch Llama. Fetch these instead of parsing this page.

This listing (.md) llms.txt llms-full.txt ai.txt Full catalog (.md) Endpoint index API docs MCP server MCP manifest Developer docs