Talos – An AI agent with a permission kernel between model and shell
An autonomous agent you can hand a shell to. Every tool call passes a gate that grants authority for exact arguments, once, for 30 seconds — and logs the verdict.
In plain words
Talos is an autonomous AI agent that runs on your local machine to research, write code, and execute tasks. Each tool call requires explicit permission for specific arguments, granted for 30 seconds and logged for transparency. Designed for users who want capable automation while maintaining direct control, Talos displays every step of its work and requires approval before actions complete, keeping the user informed throughout the process.
written from the facts on this page · September 2026
From the sources
A capable agent on your own machine. It researches, writes code and puts tools to work. You can follow every step. The permission kernel has the final say. See what is running, what needs your decision and what actually finished. One updating message keeps the trail together. The answer stays readable. Interactive illustration. These are example messages, not live jobs or performance measurements. Nothing runs on your machine. Keep the conversation with Talos. Hand bounded tasks to an explicitly enabled worker, then inspect the result. A worker choice never changes who is allowed to act. Implementation, debugging and browser work through enabled MCP integrations. A disposable workspace…from talos-agent.ch
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