CLIs Are All You Need for Agents
Fun agent I've been playing with - the idea is it only has access to a bash tool, and it's directed to create CLIs for use (with additional direction to make the CLIs composable, follow the Unix philosophy, etc). It persists these CLIs and knowledge about them get injected into the system prompt dynamically, so each time it runs it gets access to a larger and larger toolset of composable CLIs. One interesting dynamic that's emerged from this is I've started using these CLIs myself since they're the same interface for the agent or for me, and it's turned into kind of non-chat channel to…
What it does
In the maker’s words, at launch
Fun agent I've been playing with - the idea is it only has access to a bash tool, and it's directed to create CLIs for use (with additional direction to make the CLIs composable, follow the Unix philosophy, etc). It persists these CLIs and knowledge about them get injected into the system prompt dynamically, so each time it runs it gets access to a larger and larger toolset of composable CLIs. One interesting dynamic that's emerged from this is I've started using these CLIs myself since they're the same interface for the agent or for me, and it's turned into kind of non-chat channel to interact with the agent. One example - I'll add tasks throughout the day myself using the `tasks` CLI it made, then when I interact with the agent it'll run `tasks list` and see everything I've added, or use it to prioritize/update things for me. Later on when I run `tasks list` myself I see all the updates/priorities it set.
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 · 27d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
