
bikeshed
Inference playground
Repository Info
About This Server
Inference playground
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
BikeShed
WIP: This project should be considered a work-in-progress. Currently, Linux Only
Bikeshed, a place to sweat the details, however trivial.
Overview
BikeShed is an experimental project built as a Model Context Protocol (MCP) client. There are many like it, this is mine.
This project aims to provide a flexible playground creating reusable context sets: instructions, tools, resources. The main goal is to be able to experiment with simple workflows to create artifacts. Eventually, a goal it to generate a detailed specification for a workflow that can be "compiled" into a executable application.
Table of Contents
- Features
- Installation
- Usage
- Contributing
- License
- Contact
Features
- Experimental: BikeShed serves as a playground for developers interested in experimenting with MCP-related concepts.
- Declarative Workflow Syntax: Trying to make building simple workflow components using YAML easy
- Context Management: Tools for managing and manipulating model contexts.
Installation
To get started with BikeShed, follow these steps:
- Clone the repository:
git clone https://github.com/wesnick/bikeshed.git
cd bikeshed
- Install dependencies:
You need uv, rust, go, npm, deno installed. Sorry, this is a developer app so these are table stakes.
OS dependencies, assuming Debian-flavored distro
sudo apt-get install libmagic1 graphviz graphviz-dev
Python
uv sync
Rust
cargo install just
cargo install monolith
Golang
go install github.com/stripe/pg-schema-diff/cmd/pg-schema-diff@latest
Node
npm install
Deno
curl -fsSL https://deno.land/install.sh | sh
- Run the project:
From here on out, use just
just setup-env # be sure to edit your .env
just docup
# Dev has 3 processes
just fastapi-dev
just frontend-dev
just arq-dev
Make sure to check the [docs/project.md] for additional info.
Usage
TBD
Contributing
We appreciate contributions to BikeShed! If you're interested in contributing, please fork the repository and submit a pull request. You can also report issues or propose features through the GitHub issues page.
- Fork it (https://github.com/wesnick/bikeshed/fork)
- Create your feature branch (
git checkout -b feature/MyNewFeature) - Commit your changes (
git commit -m 'Add some feature') - Push to the branch (
git push origin feature/MyNewFeature) - Create a new Pull Request
License
BikeShed is licensed under the MIT License. See the LICENSE file for more information.
Contact
For questions, feedback, or inquiries about BikeShed, please reach out:
- GitHub Issues: https://github.com/wesnick/bikeshed/issues
Disclaimer: BikeShed is an experimental project and may contain bugs or unfinished features. It is intended for exploration and should be used with caution in production environments.
Quick Start
Clone the repository
git clone https://github.com/wesnick/bikeshedInstall dependencies
cd bikeshed
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.