Project Info
This project did not submit a demo video on Devpost.
Inspiration
AI-powered tools are changing the way developers think about programming incredibly quickly. Less than two years after its official launch, Copilot's become integral to the programming experience—for its users, over half of the code they write is generated by Copilot. But the terminal, another key component of the developer experience, has remained largely untouched. We found ourselves frustrated with having to constantly switch back and forth being ChatGPT sessions and terminal windows, trying to find the right context to paste in, and still needing to resort to documentation and manpages to debug unfamiliar commands. Beyond that, we wanted a private, personalized solution—one that could learn from our commands, be as "terminal-literate" as possible, and didn't rely on closed models like OpenAI's. We wanted a copilot that (1) integrated directly into the terminal, with UX as seamless as possible, (2) could learn from our commands and become a personalized assistant, and (3) worked offline and open-source, unlike most of the proprietary, closed solutions that are widespread today. So we built zyzx, a copilot that does just that.
What it does
zyzx works as a tiny executable that you can invoke right from your shell
How we built it
We built it in Zig!
Challenges we ran into
We ran into many challenges; this was our first time working with the language Zig, and we also ran into many challenges training the model.
Accomplishments we're proud of
We are proud that we have a functional terminal!
What we learned
We learned a lot about compile time optimization and Zig.
What's next
More commands!
This repository has no readme, or GitHub could not be reached.
Analysis
View
Metric
- 34
- 24
- 13
Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.
Technology
- CSSIn code
- Next.jsIn code
- OpenAIIn code
- PythonIn code
- PyTorchIn code
- ReactIn code
- TypeScriptIn code
7 of 7 appear in the indexed code.
AI coding agents
No AI coding agent signals were found in this repository.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
Source size
40 KB
Source files
16
Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.
Repository
tam-albert/zyzx
47 files · 2.0 MB · @ 2e65c9a
Structure
Interface
5 files · 11%Screens, components and styles rendered to the user.
Application logic
18 files · 38%Domain rules, services and shared utilities.
Data & schema
1 file · 2%Schema definitions, migrations and data access.
Supporting
Layers are inferred from where files sit in the tree, not from reading the code. A project that names its directories unconventionally will read oddly here — open the file browser to check anything the diagram implies.
Languages
- Python52%
- TypeScript38%
- CSS6%
- Markdown3%
Share of indexed source by file size. Binary and vendored files are excluded.
Dependencies
data/requirements.txt
pypi · 20- idna
- Jinja2
- MarkupSafe
- mlx
- mpmath
- multidict
- networkx
- numpy
- openai
- pydantic
- pydantic_core
- requests
- sentencepiece
- sniffio
- sympy
- torch
- tqdm
- typing_extensions
- +2 more
website/package.json
npm · 16- @nextui-org/react
- next
- react
- react-dom
- react-icon
- react-icons
- react-katex
- react-latex-next
- react-router-dom
- +7 more
Declared in the repository’s manifests at the indexed commit. A declared package is not proof it is used, and runtime dependencies are listed first.
This project’s features have not been analysed yet.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.