# Install splitrail with Homebrew

Real-time token usage tracker and cost monitor for CLI coding agents. Version 3.7.0 via Homebrew; verified 2026-08-02.

## Install

```sh
sudo av install brew:splitrail
```

Additional install commands:

### macOS

- Homebrew (100%):

```sh
brew install splitrail
```

  Evidence: local Homebrew formula metadata

## Package facts

- **Package key:** brew:splitrail
- **Package manager:** Homebrew
- **Version:** 3.7.0
- **Source summary:** Real-time token usage tracker and cost monitor for CLI coding agents
- **Homepage:** <https://splitrail.dev/>
- **Repository:** <https://github.com/Piebald-AI/splitrail>
- **Last updated:** 2026-08-02T00:47:35Z
- **Generated:** 2026-08-03T19:37:03+00:00

## Executables

- splitrail (alias)

## Install behavior

- Bottle: not available

## Freshness

- Page generated: 2026-08-03
- Package-manager version: 3.7.0
## Project history and usage

Splitrail is a cross-platform CLI for aggregating token usage and estimated cost data from AI coding agents. It can present local statistics, upload them to Splitrail Cloud for cross-machine aggregation, and expose statistics through an MCP server.

### Project history

Piebald AI created the public repository in 2025 and published v1.0.0 in August of that year. The project subsequently broadened its analyzers across Claude Code, Codex CLI, Gemini CLI and Qwen Code, Cline-derived tools, GitHub Copilot, OpenCode, Pi Agent, and related coding-agent environments.

### Adoption history

Splitrail is distributed as release binaries and through Homebrew. Its optional cloud companion adds private account storage, cross-machine aggregation, and leaderboard features without replacing the local CLI workflow.

### How it is used

Running `splitrail` reviews discovered coding-agent usage. `splitrail mcp` starts an MCP server with tools for daily statistics, model usage, costs, file operations, and comparisons; cloud upload is configured with an API token and upload preferences in `~/.splitrail.toml`.

### Why package nerds care

Splitrail reflects the emergence of a new CLI observability niche around AI-assisted development: one local binary normalizes usage records from otherwise separate agent ecosystems and can expose the aggregate through MCP.

### Timeline

- 2025: Official repository created.
- 2025: v1.0.0 published.
- 2026: Splitrail documented broad multi-agent support, cloud aggregation, and an MCP server.

### Related projects

- Splitrail Cloud is the optional hosted companion for synchronization and aggregation.
- Piebald is the agentic developer product from the same team.

### Sources

- <https://github.com/Piebald-AI/splitrail#readme>
- <https://github.com/Piebald-AI/splitrail-cloud#readme>
- <https://github.com/Piebald-AI/splitrail/releases>
- source_facts.package-manager.brew


## Security Notes

No matching local secret-handling manifest was found for splitrail. Nucleus package metadata is still published here so future coverage has a stable package URL.



## Configuration and credential file locations

These source-backed paths show where this package keeps local settings or durable credentials. Automic Vault can use them as review targets for secret scanning, migration, and command approval.


## Configuration files

- Unix: ~/.splitrail.toml

## Credential files

- Unix: ~/.splitrail.toml

## Combined YAML source

View the package source record on GitHub. [combined/splitrail.yml](https://github.com/mxcl/pkgdb/blob/main/combined/splitrail.yml)


## Sources

- pkg.so package database
- curated configuration and credential file locations
- curated package history
- pkgdb category and tag curation
- cross-ecosystem install command graph