lowfat is a lightweight CLI tool that reduces AI token costs by filtering unnecessary CLI output before it reaches your agent.
Cost / License
- Free
- Open Source (Apache-2.0)
Since
- Since 2026
Thailand



Apps similar to tokendoctor include lowfat, which is free and open source. Other options are Caveman, Headroom, Context Mode and RTK. In total there are eight AI Coding Assistants like tokendoctor for Mac, Windows, Linux, self-hosting and the web.
lowfat is a lightweight CLI tool that reduces AI token costs by filtering unnecessary CLI output before it reaches your agent.



Why use many tokens when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

RTK is a high-performance command-line proxy that reduces the shell output your AI coding agent reads—cutting common development-command output by 60–90%. It filters, groups, truncates, and deduplicates verbose terminal output before it enters your LLM context, helping agents...
An open-source skill for coding agents that examines the affected code before choosing the smallest practical change. It favors existing components and native platform capabilities, while preserving validation, error handling, security, accessibility, and focused tests.




Menu bar app that cuts Claude Code and ChatGPT Codex token costs by ~50% by compressing tool output, logs and boilerplate locally.




condense.chat sits between your app or AI agent and the LLM provider. It manages and compresses the context sent on every call, so your provider bills you for fewer tokens.
