#2626th of 48 in Gateways and observability
tokscale
CLI and dashboard that tallies token usage and cost across AI coding agents
- Stars
- 5.8k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Rust
2,025 on 21 Apr 20265,832 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Tokscale is a Rust CLI, distributed on npm, that reads the local session files of dozens of AI coding agents and totals token usage and cost. Supported sources include Claude Code, Codex CLI, OpenCode, Gemini CLI, Copilot CLI, Cursor, Cline and LM Studio. It shows the results in a terminal UI with overview, model, daily, hourly and session views, and can submit them to a public leaderboard on tokscale.ai.
Who it is for: Developers using several AI coding agents who want to track token spend
Strengths
- Reads local session files from 50+ coding agents, so no proxy or code changes are needed
- Terminal UI with overview, models, daily, hourly and session breakdowns
- Covers local inference sources like LM Studio and Unsloth Studio, costed at $0
- MIT license, Rust core, frequent releases
Weaknesses
- Some clients need a manual sync step first, such as Amp, Trae, Warp and Antigravity
- Warp data is aggregate requests and spend only, with no token transcripts
- Freebuff token usage is estimated from transcripts, not measured
- Leaderboard submission sends usage data to a hosted service
What it needs
- no GPU
- Docker + Compose
- Needs Bun or Node.js (npm package)
- Models: Claude Code, Codex CLI, OpenCode, Gemini CLI, GitHub Copilot CLI
Quick answers
Is tokscale open source?
Yes. Its code is on GitHub under the MIT license.
Can you run tokscale with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does tokscale need a GPU?
No, it runs without one.
Also in Gateways and observability
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | OmniRouteLLM gateway routing one OpenAI-compatible endpoint across 372 providers | 96 out of 100 |
| 2 | headroomCompresses tool outputs, logs and history before they reach the LLM | 92 out of 100 |
| 3 | new-apiGateway that unifies LLM providers behind OpenAI, Anthropic and Gemini APIs | 91 out of 100 |
| #4 | MLflowTracing, evaluation and prompt registry for LLM apps, plus ML tracking | 90 out of 100 |
| #5 | LiteLLMOpenAI-format gateway and Python SDK for calling 100+ LLM providers | 87 out of 100 |