SHAI – a (yet another) open-source, terminal-native AI coding assistant
Since I mostly work within the terminal, I wanted an AI coding assistant that integrates seamlessly with it. Something I could call from SSH, integrate into scripts or just invoke quickly without leaving the shell. Most existing tools (at the time) were either closed, required various dependencies, or tied to a specific vendor. I wanted a free, open-source alternative that: - installs with a single binary (useful on bare servers) - talks to any LLM endpoint and especially self-hosted open weight model - could run headless, composable, and Unix-like SHAI stands for SHell AI! Along the way I…
In plain words
SHAI is an open-source, terminal-native AI coding assistant designed for developers who work primarily in the shell. It installs as a single binary, works with any LLM endpoint including self-hosted models, and integrates seamlessly into scripts and SSH sessions without external dependencies. Built in Rust and Unix-like in philosophy, SHAI prioritizes headless operation and modularity, allowing users to swap components or layer additional interfaces on top. The creator also developed the Rust crate shai-llm as part of the project to provide LLM abstraction similar to existing Python tools.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Since I mostly work within the terminal, I wanted an AI coding assistant that integrates seamlessly with it. Something I could call from SSH, integrate into scripts or just invoke quickly without leaving the shell. Most existing tools (at the time) were either closed, required various dependencies, or tied to a specific vendor. I wanted a free, open-source alternative that: - installs with a single binary (useful on bare servers) - talks to any LLM endpoint and especially self-hosted open weight model - could run headless, composable, and Unix-like SHAI stands for SHell AI! Along the way I couldn’t find a `lite-llm` equivalent for Rust, so I built the crate `shai-llm`. I tried to make it as modular as possible so new tools can be added, UIs swapped, or an API layered on top. It was also my first major project in rust, I hope you'll like it :) Key features: - Open-source and LLM-agnostic: connect to any OpenAI-compatible endpoint - Works out of the box using OVHcloud AI Endpoints (unauthenticated, strongly rate-limited) - Function calling and MCP support (with OAuth) - Custom Agent Configuration (model, system prompt, tool set) SHAI is still evolving, but it's part of Hacktoberfest so contributions and feedback are most welcome.
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, October 2025
the whole month →
- SA
I went down the rabbit hole on a side project and ended up building this: Strange Attractors(https://blog.shashanktomar.com/posts/strange-attractors). It’s built with three.js. Working on it reminded me of the little "maths for fun" exercises I used to do while learning programming in early days. Just trying things out, getting fascinated and geeky, and being surprised by the results. I spent way too much time on this, but it was extreme fun. My favorite part: someone pointed me to the Simone Attractor on Threads. It is a 2D attractor and I asked GPT to extrapolate it to…
AI · Oct 2025 · blog.shashanktomar.com
- ASAutism Simulator▲779
Hey all, I built this. It’s not trying to capture every autistic experience (that’d be impossible). It’s based on my own lived experience as well as that of friends on the spectrum. I'm trying to give people a feel for what masking, decision fatigue, and burnout can look like day-to-day. That’s hard to explain in words, but easier to show through choices and stats. I'm not trying to "define autism". I’ve gotten good feedback here about resilience, meds, and difficulty tuning. I’ll keep tweaking it. If even a few people walk away thinking, "ah, maybe that’s why my coworker struggles in those…
Life & fun · Oct 2025 · autism-simulator.vercel.app
