In multi-turn agent loops, the full context re-sends on every API call. A tool result added at turn 3...
In multi-turn agent loops, the full context re-sends on every API call. A tool result added at turn 3 gets billed again at turns 4, 5, 6, 7... forever. Most of it is never read again.
Standard observability tools tell you the total token count. They never tell you what's in there or how much of it is waste.
That's what ContextLens fixes.
What it does
ContextLens is a diagnostic profiler for LLM agent context windows. It:
Does my codebase fit in context? This is one of the first dev tools I created - for me was in the...
In my last post I described graphlens — what it does, how it works — and along the way I casually...
Context pruning removes low-value tokens before inference to cut LLM costs and improve output. Learn core techniques and where…
I built a local-first profiler that sits as a transparent reverse proxy between your coding agent...
TL;DR: AI coding agents are now part of the dev workflow, but most repos still treat context like it...
TL;DR Context Mode is an open-source MCP-based context management system. It doesn't...
