Hexum — 85% fewer tokens to the model
Save token costs and remove code spaghetti
What it does
Hexum cuts up to 85% of token usage without losing context, precision, or code quality. 📉 Slash Token & API Costs: Compress codebases and large prompts efficiently. 🧹 Eliminate Code Spaghetti: Clean and structure context so models generate cleaner, more accurate outputs on the first try. 🔌 Seamless Integration: Drop it into your existing AI workflows and pipelines in minutes. Stop paying LLMs to process redundant boilerplate. Ship faster, spend less, and get sharper completions with Hexum.
One hexum_live_ key. Five MCP surfaces: Efficient shrinks the turn, Arch fails a bad import, Review posts on the PR, Control catches drift, Loop gates the build. ZDR.
Hosted MCP for Cursor and Claude Code. Shrink the turn, fail the import, review the PR, stop the loop. Same billing. Zero data retention. efficient.hexum.dev runs hexum_shrink. Token counts come back on the call. There is no CLI and no browser IDE. arch.hexum.dev runs hexum_check. Deterministic. It does not call a model. Drift fails the turn. Mint hexum_live_ at /app. Hub /mcp lists every tool. Product hosts list only theirs. Same key. Same bill. { "mcpServers": { "hexum": { "serverUrl": "https://hexum.dev/mcp", "headers": { "Authorization": "Bearer hexum_live_…" } } } } In short Hexum is the control plane for coding agents. One hexum_live_ key authorizes hosted MCP on hexum.dev and on…from hexum.dev
Does the same job
all alternatives →
- CACodeBurn – Analyze Claude Code token usage by taskApr 2026 · github.com · ▲112
Built this after realizing I was spending ~$1400/week on Claude Code with almost no visibility into what was actually consuming tokens. Tools like ccusage give a cost breakdown per model and per day, but I wanted to understand usage at the task level. CodeBurn reads the JSONL session transcripts that Claude Code stores locally (~/.claude/projects/) and classifies each turn into 13 categories based on tool usage patterns (no LLM calls involved). One surprising result: about 56% of my spend was on conversation turns with no tool usage. Actual coding (edits/writes) was…
- LCLibrarian – Cut token costs by up to 85% for LangGraph and OpenClawFeb 2026 · uselibrarian.dev · ▲8
Hi HN, I'm building Librarian (https://uselibrarian.dev/), an open-source (MIT) context management tool that stops AI agents from burning tokens by blindly re-reading their entire conversation history on every turn. The Problem: If you're building agentic loops in frameworks like LangGraph or OpenClaw, you hit two walls fast: Financial Cost: Token usage scales quadratically over long conversations. Passing the whole history every time gets incredibly expensive. Context Rot: As the context window fills up, the LLM suffers from the "Lost in the Middle" effect. Response latency…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com