Context-Compression

Ever watched your AI agent burn through tokens on 65,000 characters of JSON tool output — just to answer “yes, the service is down”? Yeah, me too. I’ve been running Claude Code and Codex daily, and my token bills were starting to look suspiciously like a second mortgage. (Code-review-graph cut my review tokens 82x, but that only covers the review step — I needed something for every agent interaction.) So when Headroom crossed my radar at 59.7k GitHub stars and #2 on Trending, I had to see what the fuss was about. ...

Your AI coding agent is getting expensive. Not because you’re using it more — because it’s re-sending the same files on every turn. Same context, same tokens, same bill. But tokdiet fixes that. tokdiet is a local streaming reverse proxy that sits between your AI agent (Claude Code, Cursor, Codex) and the model API. It meters every token, compresses bloated context, and — here’s the kicker — runs a shadow evaluation to prove quality didn’t drop. Cut your input tokens by ~71% with 95–97% quality parity. And it’s MIT open source, 68 stars on GitHub as of writing. ...

If you’re a heavy Claude Code or Cursor user, you know the feeling: one innocent “search the codebase” command and boom — 20,000 tokens gone. $0.30 per query doesn’t sound like much until you’re doing it 50 times a day. I’ve been watching my API bills creep up for months. Honestly, I was starting to wonder if AI coding agents were a luxury I couldn’t justify for side projects. So when I saw a project called Headroom trending on GitHub (+9,421 stars this week alone), I had to check it out. The pitch is simple: compress everything you send to the LLM before it gets there. Save 60–95% on tokens. Keep the same answer quality. ...