freshcrate
Skin:/
Home > AI Agents > splitrail

splitrail

Fast, cross-platform, real-time token usage tracker and cost monitor for Gemini CLI / Claude Code / Codex CLI / Qwen Code / Cline / Roo Code / Kilo Code / GitHub Copilot / OpenCode / Pi Agent / Piebal

Why this rank:Strong adoptionRecent releaseHealthy release cadence

Description

Fast, cross-platform, real-time token usage tracker and cost monitor for Gemini CLI / Claude Code / Codex CLI / Qwen Code / Cline / Roo Code / Kilo Code / GitHub Copilot / OpenCode / Pi Agent / Piebald.

README

Check out Piebald

We've released Piebald, the ultimate agentic AI developer experience.
Download it and try it out for free! https://piebald.ai/

Join our DiscordXScroll down for Splitrail. 👇

Splitrail

Splitrail is a fast, cross-platform, real-time token usage tracker and cost monitor for:

Run one command to instantly review all of your CLI coding agent usage. Upload your usage data to your private account on the Splitrail Cloud for safe-keeping and cross-machine usage aggregation. From the team behind Piebald.

Note

⭐ If you find Splitrail useful, please consider starring the repository to show your support! ⭐

Download the binary for your platform on the Releases page.

Screenshots

Screenshot of the Splitrail CLI

Screenshot of the Splitrail VS Code Extension

Screenshot of Splitrail Cloud

MCP Server

Splitrail can run as an MCP (Model Context Protocol) server, allowing AI assistants to query your usage statistics programmatically.

splitrail mcp

Available Tools

  • get_daily_stats - Query usage statistics with date filtering
  • get_model_usage - Analyze model usage distribution
  • get_cost_breakdown - Get cost breakdown over a date range
  • get_file_operations - Get file operation statistics
  • compare_tools - Compare usage across different AI coding tools
  • list_analyzers - List available analyzers

Resources

  • splitrail://summary - Daily summaries across all dates
  • splitrail://models - Model usage breakdown

Configuration

Splitrail stores its configuration at ~/.splitrail.toml:

[server]
url = "https://splitrail.dev"
api_token = "your-api-token"

[upload]
auto_upload = false
upload_today_only = false

[formatting]
number_comma = false
number_human = false
locale = "en"
decimal_places = 2

Development

Windows

On Windows, we use lld-link.exe from LLVM to significantly speed up compilation, so you'll need to install it to compile Splitrail. Example for winget:

winget install --id LLVM.LLVM

Then add it to your system PATH:

:: Command prompt
setx /M PATH "%PATH%;C:\Program Files\LLVM\bin\"
set "PATH=%PATH%;C:\Program Files\LLVM\bin"

or

# PowerShell
setx /M PATH "$env:PATH;C:\Program Files\LLVM\bin\"
$env:PATH = "$env:PATH;C:\Program Files\LLVM\bin\"

Then use standard Cargo commands to build and run:

cargo run

macOS/Linux

Build as normal:

cargo run

License

MIT

Copyright Š 2026 Piebald LLC.

Release History

VersionChangesUrgencyDate
v3.5.4## What's Changed * Fix Piebald cached input accounting by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/167 * Remove GPT-5.2 Codex pricing warning by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/168 * [codex] Add missing model pricing entries by @Wraient in https://github.com/Piebald-AI/splitrail/pull/164 * v3.5.4 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/169 ## New Contributors * @Wraient made their first contribution in https://github.com/Piebald-AHigh5/30/2026
v3.5.3## What's Changed * Fix GPT-5.5 Pro pricing by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/153 * fix: support newer Gemini CLI and Copilot session formats by @jimyag in https://github.com/Piebald-AI/splitrail/pull/155 * Add pricing entries for newly observed models by @zhangzqs in https://github.com/Piebald-AI/splitrail/pull/156 * Fix Copilot CLI shutdown metric segmentation by @zhangzqs in https://github.com/Piebald-AI/splitrail/pull/157 * feat: add all-tools period aggregation viHigh5/29/2026
v3.5.2## What's Changed * Add GPT-5.5 long-context pricing by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/151 * v3.5.2 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/152 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v3.5.1...v3.5.2High4/24/2026
v3.5.1## What's Changed * Add pricing for Gemini 3.1 Pro Preview Custom Tools by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/148 * feat: add TUI defaults for sort and empty periods by @jimyag in https://github.com/Piebald-AI/splitrail/pull/146 * Add GPT-5.5 pricing by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/149 * v3.5.1 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/150 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v3.5.0...v3.5.1High4/23/2026
v3.5.0## What's Changed * Claude Opus 4.7 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/142 * fix(gemini-cli): accept multi-modal content (string | Part | Part[]) by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/143 * Support GitHub Copilot CLI and improve CLI accounting by @zhangzqs in https://github.com/Piebald-AI/splitrail/pull/141 * Add pricing for GPT-5.4 nano and GPT-4.5 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/144 * feat: support external model andHigh4/20/2026
v3.4.0## What's Changed * fix: correct TuiStats size comment, revert cost_cents to u32 by @Sewer56 in https://github.com/Piebald-AI/splitrail/pull/132 * Add aliases for Gemini 3.1 Pro - low and medium and high by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/135 * Include token counts for Piebald that were accidentally ignored by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/136 * feat: add SQLite database support to OpenCode analyzer by @mike1858 in https://github.com/Piebald-Medium4/5/2026
v3.3.5## What's Changed * Fix capped large token totals in TUI stats by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/130 * v3.3.5 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/131 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v3.3.4...v3.3.5Low3/14/2026
v3.3.4## What's Changed * Fix GPT-5.2 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/119 * feat: add Claude Sonnet 4.6 pricing by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/121 * Fix JSONL parsing warnings and add missing model pricing by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/127 * feat: add Gemini 3.1 Pro pricing and model aliases by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/125 * fix: widen token columns and add overflow-safe formattinLow3/12/2026
v3.3.3## What's Changed * fix(piebald): use per-message model instead of chat-level model by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/112 * fix: strip non-standard numeric format annotations from MCP JSON schemas by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/114 * feat: add pricing for Gemini 3 Flash and GPT-5.3-Codex by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/115 * v3.3.3 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/116 **Full ChangeLow2/13/2026
v3.3.2## What's Changed * Add Opus 4.6 support by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/110 * v3.3.2 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/111 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v3.3.1...v3.3.2Low2/5/2026
v3.3.1## What's Changed * Fix #104 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/105 * Add a --dry-run flag for uploading by @basekevin in https://github.com/Piebald-AI/splitrail/pull/106 * Add support for Z.AI/Zhipu AI, xAI, and Synthetic.new models by @Sewer56 in https://github.com/Piebald-AI/splitrail/pull/107 * Add per-model daily stats to the JSON output by @signadou in https://github.com/Piebald-AI/splitrail/pull/108 * v3.3.1 by @mike1858 in https://github.com/Piebald-AI/splitrailLow1/30/2026
v3.3.0### Memory Efficiency Overhaul This release brings a big architectural improvement to how Splitrail tracks your usage data. **Contribution Caching** — We've introduced a new contribution caching system with different strategies for different analyzers. This means dramatically lower memory usage when watching huge conversation histories, with file-level incremental updates that avoid reprocessing unchanged data. Thank you @Sewer56 for this amazing contribution! ### New Model Support Low1/16/2026
v3.2.2## TUI Improvements This release brings several quality-of-life improvements to the TUI: **Cached Tokens Visibility** — The session view now displays cached tokens instead of a redundant tool column, giving you better insight into your token efficiency and cost savings from prompt caching. **Smarter Summary Totals** — When viewing sessions, the summary totals now filter to show only the selected day's statistics, making it easier to understand your daily usage at a glance. **Reverse Low12/27/2025
v3.2.1## Update Notifications Splitrail now keeps you informed when a new version is available. On startup, the TUI checks GitHub Releases in the background and displays a yellow banner when there's an update, which is dismissible by pressing `u`: ``` New version available: 3.2.0 -> 3.2.1 (press 'u' to dismiss) ``` This is a quality-of-life improvement to help you stay current with the latest features and bug fixes. ## What's Changed * feat(tui): add background version check with updateLow12/13/2025
v3.2.0## [<img src="https://github.com/Piebald-AI/piebald/raw/main/assets/logo.svg" width="20"> **Introducing Piebald Support**](https://piebald.ai/) We now officially support [<img src="https://github.com/Piebald-AI/piebald/raw/main/assets/logo.svg" width="15"> **Piebald**](https://piebald.ai/) — the ultimate agentic AI control experience for developers. Track your Piebald usage across all your favorite providers, whether you're using OpenAI, Anthropic, Google, or any compatible API. ## New ModLow12/13/2025
v3.1.1## GPT-5.1-Codex-Max Pricing Update Because OpenAI released it on the API, we updated the pricing for `gpt-5.1-codex-max` to match the official rates: | Token Type | Previous (estimated) | Official | |------------|----------------------|-----------| | Input | $2.50/1M | $1.25/1M | | Output | $20.00/1M | $10.00/1M | | Cached | $0.25/1M | $0.125/1M | Your historical cost calculations for this model will now be more accurate. Note thatLow12/5/2025
v3.1.0## Support for Pi coding agent! We now officially and completely support the [Pi coding agent](https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent) — available in the CLI and Cloud. ## The Next.js Vulnerabillity There was a [critical vulnerability in React Server Components](https://react.dev/blog/2025/12/03/critical-security-vulnerability-in-react-server-components), which indirectly affected Splitrail Cloud, so we updated the Next.js and RSC versions. The vulnerabilitLow12/4/2025
v3.0.0# Introducing Splitrail 3.0.0 We rewrote the underlying engine from the ground up for hardcore performance, accuracy and visibility. ## Performance Introducing **Persistent Caching** — Splitrail now remembers every file it has ever parsed, storing results in memory-mapped files with zero-copy deserialization powered by `rkyv` and `memmap2`. Cold starts that once took seconds now happen in milliseconds. We replaced our file discovery system with `jwalk` for parallel directory walking,Low11/30/2025
v2.2.3## What's Changed * Fix: Timezone issue in TUI & Add: Gemini CLI reasoning tokens by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/45 * Feat: Add --full and --force-analyzer flag to upload command by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/46 * Add code-signing for Windows and macOS builds by @signadou in https://github.com/Piebald-AI/splitrail/pull/47 * Install `cargo-audit` using `taiki-e/install-action` by @signadou in https://github.com/Piebald-AI/splitrail/pullLow11/24/2025
v2.2.2## What's Changed * Change upload chunk size from 1000 to 3000 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/43 * v2.2.2 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/44 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v2.2.1...v2.2.2Low11/21/2025
v2.2.1## What's Changed * Fix `REQUEST_ENTITY_TOO_LARGE` uploading errors by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/41 * v2.2.1 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/42 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v2.2.0...v2.2.1Low11/20/2025
v2.2.0## What's Changed * Greatly improve performance by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/36 * Allow `content` to be an array of content blocks or a string in CC analyzer by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/38 * Add support for searching across days by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/37 * Add support for estimated pricing; add GPT-5.1-Codex-Mini and (estimated) GPT-5.1-Codex-Max by @mike1858 in https://github.com/Piebald-ALow11/20/2025
v2.1.0## What's Changed * Add support for Code - Insiders as a valid fork. by @mcowger in https://github.com/Piebald-AI/splitrail/pull/30 * Also add for Roo, and check vscode-server paths by @mcowger in https://github.com/Piebald-AI/splitrail/pull/31 * Add basic copilot parsing support. by @mcowger in https://github.com/Piebald-AI/splitrail/pull/32 * Add support per-session token + cost tracking by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/34 * v2.1.0 by @mike1858 in https://githuLow11/19/2025
v2.0.0## What's Changed * Add support for Cline, Roo Code, and Kilo Code; add (anticipated pricing) GPT-5-Codex-Mini and Gemini 3 Pro by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/25 * Add support for Qwen Code by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/26 * v2.0.0 by @mike1858 in https://github.com/Piebald-AI/splitrail/pull/28 ## New Contributors * @mike1858 made their first contribution in https://github.com/Piebald-AI/splitrail/pull/28 **Full Changelog**: https:Low11/10/2025
v1.2.0## What's Changed * Correct Claude Code token aggregation for split messages by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/23 * v1.2.0 by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/24 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v1.1.3...v1.2.0Low10/27/2025
v1.1.3## What's Changed * Add support for Claude Haiku 4.5 by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/21 * v1.1.3 by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/22 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v1.1.2...v1.1.3Low10/24/2025
v1.1.2## What's Changed * Add support for Claude Sonnet 4.5 and ignore "file-history-snapshot" entries by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/18 * v1.1.2 by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/19 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v1.1.1...v1.1.2Low10/1/2025
v1.1.1## What's Changed * Add shared warn_once utility and tighten Codex missing-model handling by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/15 * Fix Codex CLI analyzer by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/16 * v1.1.1 by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/17 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v1.1.0...v1.1.1Low9/18/2025
v1.1.0## What's Changed * Add a link to download by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/12 * Update Codex support by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/13 * v1.1.0 by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/14 **Full Changelog**: https://github.com/Piebald-AI/splitrail/compare/v1.0.1...v1.1.0Low9/18/2025
v1.0.1## What's Changed * Format and fix lint errors by @signadou in https://github.com/Piebald-AI/splitrail/pull/9 * Rearrange the readme by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/10 * v1.0.1 by @bl-ue in https://github.com/Piebald-AI/splitrail/pull/11 ## New Contributors * @signadou made their first contribution in https://github.com/Piebald-AI/splitrail/pull/9 * @bl-ue made their first contribution in https://github.com/Piebald-AI/splitrail/pull/10 **Full Changelog**: https://githLow9/15/2025
v1.0.0**Full Changelog**: https://github.com/Piebald-AI/splitrail/commits/v1.0.0Low8/9/2025

Dependencies & License Audit

Loading dependencies...

Similar Packages

aicageRuns agentic coding assistants in Docker containersmain@2026-06-05
meerkatMeerkat - A modular, high-performance agent harness built in Rust.v0.6.34
mentisdbMemory that lasts and compounds. MentisDB gives agents durable memory so they do not just remember, they improve over time. It stores append-only thought chains plus a Git-like skills registry, lett0.10.1.46
be-my-butlerOrchestrate multiple agents to execute Claude Code workflows with cross-model verification for reliable AI code automation.main@2026-06-05
ai-agent-session-centerA real-time dashboard for monitoring AI agent sessions (Claude Code, Gemini CLI, Codex) with 3D visualizationv2.10.29

More from Piebald-AI

tweakccCustomize Claude Code's system prompts, create custom toolsets, input pattern highlighters, themes/thinking verbs/spinners, customize input box & user message styling, support AGENTS.md, unlock privat

More in AI Agents

hermes-agentThe agent that grows with you
awesome-copilotCommunity-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.
CopilotKitThe Frontend Stack for Agents & Generative UI. React + Angular. Makers of the AG-UI Protocol
e2bE2B SDK that give agents cloud environments