Splitrail
Piebald-AI/splitrail
Monitor em tempo real de tokens e custos para agentes IA CLI
Ver no GitHubRastreador em tempo real de uso de tokens e custos para múltiplos agentes de IA CLI, como Gemini, Claude Code, Cline, GitHub Copilot e outros. Oferece visão consolidada do consumo de tokens, cálculo de custos e sincronização na nuvem privada para agregação entre máquinas.
Instalação
npx convez-ai Piebald-AI/splitrail1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Rastrear consumo de tokens de múltiplos agentes de código IA
- Monitorar custos de API em tempo real
- Agregar dados de uso entre diferentes máquinas na nuvem
- Integrar estatísticas de uso em fluxos de IA via MCP
Veredito

Ferramenta sólida e necessária para quem usa múltiplos agentes de IA em linha de comando e precisa visibilidade sobre gastos com tokens. Implementação em Rust garante performance e portabilidade; integração MCP adiciona valor para automação.
README
A tradução para o português deste README ainda está na fila.
Check out Piebald
We've released Piebald, the ultimate agentic AI developer experience.
Download it and try it out for free! https://piebald.ai/
Scroll down for Splitrail. :point_down:
Splitrail
Splitrail is a fast, cross-platform, real-time token usage tracker and cost monitor for:
- Gemini CLI (and Qwen Code)
- Claude Code
- Codex CLI
- Cline / Roo Code / Kilo Code (VS Code extension + CLI)
- GitHub Copilot (VS Code)
- GitHub Copilot CLI
- OpenCode
- Pi Agent
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
Splitrail CLI
Splitrail VS Code Extension
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 filteringget_model_usage- Analyze model usage distributionget_cost_breakdown- Get cost breakdown over a date rangeget_file_operations- Get file operation statisticscompare_tools- Compare usage across different AI coding toolslist_analyzers- List available analyzers
Resources
splitrail://summary- Daily summaries across all datessplitrail://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
Copyright © 2026 Piebald LLC.