Cogitorium
Agent workflows with a model per agent — and a leash on each
What it does
Most agent tools give you one model, one vendor, and a bill you can't break down. Cogitorium lets you pick a model per agent, draw exactly who may hand work to whom, and see spend per agent — not a lump sum. Delegation, tools, memory and internet access are edges you draw, each enforced by the runtime. No telemetry, no phone-home. One Go binary, Apache-2.0, runs against frontier APIs or fully local models.
A single Go binary for graph engineering: agents are nodes and four kinds of edge are permissions the runtime checks. Free, Apache-2.0, macOS, Windows and Linux.
We build the things we wanted ourselves and could not find in a shape worth trusting. Operational Research Kernel Computing · Est. 2026 · Independent The Elements of Typographic Style Robert Bringhurst · 1992 says 66 characters a line. ours is 41. The End of Print David Carson · 1995 set an interview in dingbats. deliberately. Named, not reproduced — every poster and book here belongs to the people who made it. Japanese flyer and poster archive: flyer-jp.com . A social network that is a bit more, and a bit less, than a social network. It is the product where people would earn money rather than only spend attention — the part that makes it more than a network, and the part that makes it…from orkcom.com
Does the same job
all alternatives →
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