Hammad Abbasi
See Claude Code context. Control what it can do.
What it does
Iris is a local control plane for Claude Code. It shows exactly what each request carries, including system prompt, tool schemas, and conversation context. Find unused tools that create a recurring token tax, remove them safely, set Allow / Ask / Deny boundaries before tools run, and review what Claude actually executed.
A local control plane for Claude Code. It inspects what each request carries, changes which tools the model can see, evaluates tool calls against an authority envelope, and records what ran.
See what Claude carries. Kill what you don't need. Control what it can do. Iris sits on 127.0.0.1 between Claude Code and Anthropic. It inspects what each request carries, lets you change which tools the model can see, evaluates tool calls against an authority envelope before they run, and records what actually executed. 5,149 of those tokens are the fixed prefix — the system prompt plus every tool schema, re-sent on every single turn of the session. Your own question is the tail end of that last slice. In this capture half the payload was tool definitions, and the model called almost none of them. Iris opens in your browser at 127.0.0.1:8787 while Claude Code runs as usual in your…from hammadabbasi.com
Does the same job
all alternatives →
hoop.dev - Claude Code GatewayMar 2026 · ▲83Connect Claude Code to your internal systems w/o credentials
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 · 26d 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