What is cmx?
CompressiusMaximus — a local context-compression gateway for AI coding agents.
🧠 Context compression
Replaces stale, low-signal history — old tool outputs, dead-end exploration, logs — with dense summaries. Your agent stays sharp without re-reading everything.
⚡ Cache aware
Rewrites happen only when it matters. Recent context stays byte-identical, so provider prompt-cache hit rates stay high and re-read costs stay low.
🖥️ One command, any harness
A local gateway between your harness (OpenCode, Claude Code, Codex, …) and the model. Works with OpenAI-style and Anthropic-style APIs, streaming included.
📊 Built-in dashboards
Terminal GUI with mouse support and a web dashboard — track saved tokens, context reduction, cache hits and per-session summaries in real time.
The problem
Agent harnesses resend the entire conversation on every turn. Sessions grow into hundreds of thousands of tokens — most of it stale noise you never needed again. You pay for it twice: once in input tokens, once in degraded model attention.
The fix
cmx sits on 127.0.0.1 and proxies your provider traffic. It tags old messages with stable IDs, hands the model a compress tool, and — when the model decides history is stale — crystallizes those spans into compact summaries. Nothing leaves your machine.
Quick start → compressing in 2 minutes
Last updated Sep 1, 2026