Does my codebase fit in context?
This is one of the first dev tools I created - for me was in the "Openclaw days" - early February into March of this year, was using Codex and some local Ollama; where I kept hitting the wall: context limits were rigid and often insufficient. Now with 1M token contexts, and more robust frontier models, etc - the need for the tool is less. I'm now largely using frontier models and honestly use it nearly never. But it was helpful at a moment in time. Might still have value for those running local LLMs with limited contexts.
Also, for full transparency - I snafu'd on my first public project - came up with the name quite organically - "context lens" - searched out ctxlens on npm, found the space open - built the tool. Published it, started getting downloads on day one. Odd. Turns out dabit3 (a real dev) had created a project with the same name on GH and pointed to an npm package he never published. I reached out and offered the namespace to him, and created "tokendu" as a backup repo/package. No response as the interest in the project had presumably faded, so I kept the name. Maintained, for now. ;)
Problems it hoped to solve:
"Will my project fit in context?" — Instant answer across 23 models from 7 providers. Know you're safe on Claude, tight on GPT-4o, and blown past Grok — without switching tools.
