RadarTopicsBuildersWeeklyReads
Open Source Radar
alexgreensh/

token-optimizer

GitHub

Token Optimizer is a Python tool that runs in the background to audit and compress AI tool outputs, providing a live dashboard and per-session savings without requiring manual intervention.

1.8kstars
146forks
3issues
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

Token Optimizer is a Python-based tool that runs automatically to audit, compress, and optimize token usage across AI coding assistants. It provides a live dashboard and per-session savings, with commands to trigger audits and view reports.

How it works

The project implements automatic, session-wide token compression with multiple features including checkpoints before auto-compact and restoration after, a session database (SQLite, 15 tables, full audit trail, zero network), and a live dashboard that reflects savings and context quality. It supports per-component audits and model routing nudges to steer tasks to appropriate tiers. It exposes several commands for interacting with audits, dashboards, reports, and memory reviews.

Getting started

Install options are provided for Claude Code and other platforms. Example install paths include:

/plugin marketplace add alexgreensh/token-optimizer
/plugin install token-optimizer@alexgreensh-token-optimizer
codex plugin marketplace add alexgreensh/token-optimizer
openclaw plugins install github:alexgreensh/token-optimizer
git clone https://github.com/alexgreensh/token-optimizer.git
token-optimizer/install.sh --hermes
git clone --depth 1 https://github.com/alexgreensh/token-optimizer.git
cd token-optimizer
bash install.sh --copilot

There are additional Linux/macOS installation steps and a Windows note indicating to use only the plugin install on Windows.

After install, run /token-optimizer once to set up hooks. From there, everything runs automatically: compression, checkpoints, quality scoring, dashboard updates. You don't need to run any command again unless you want an audit.

Recent releases

Latest releases show ongoing fixes and improvements, including v5.11.80 and prior patch notes. Examples:

  • v5.11.80 (2026-08-03): OpenClaw/OpenCode parity + a real fix for the recurring dead-dashboard; Dashboard daemon cleanup fix.
  • v5.11.79 (2026-08-03): Savings dashboard reconciliation and transparency fixes.
  • v5.11.78 (2026-08-03): Dashboard install-failure nudge improves user notification.
  • v5.11.77 (2026-08-02): Windows reliability fixes for hooks and UI components.
  • v5.11.76 (2026-08-01): Windows reliability release focused on hook initialization.

Traction

GitHub stars: 1805

Behind the repo

Not provided in the data.

Caveats

License: PolyForm Noncommercial (as shown on badges in README). Language: Python. Created: 2026-02-26. Last push: 2026-08-03. Open issues: 3. Platform coverage includes macOS, Linux, Windows. Tags include ghost-tokens, token-optimization, token-optimizer, context-engineering, and related integrations.

SharePost on XLinkedIn
All trending reposRevenue-verified startups →