Documentation: docs.toolfront.ai

Source code: https://github.com/statespace-tech/toolfront

Quickstart

ToolFront is a declarative framework for building modular AI applications in Markdown. Write tools and instructions in .md files and get a live AI application.

Create it

Start with one file: README.md

---
tools:
  - [curl, -X, GET, "https://httpbin.org/status/200"]
---

# Instructions
- Use `curl` to check if the service is up

Serve it

Run your app on your machine:

toolfront serve .

Runs at http://127.0.0.1:8000

Ask it

Export your OPENAI_API_KEY and query your app:

from toolfront import Application

app = Application(url="http://127.0.0.1:8000")

result = app.ask("Is the service up?", model="openai:gpt-5")

{
  "mcpServers": {
    "toolfront": {
      "command": "uvx",
      "args": ["toolfront", "mcp", "http://127.0.0.1:8000"]
    }
  }
}

toolfront ask http://127.0.0.1:8000 "Is the service up?"

Upgraded Example

Your app can grow into a full project:

project/
├── README.md          # Main instructions & navigation tools
├── src/
│   ├── rag.md         # Document search
│   ├── text2sql.md    # Database query
│   └── toolkit.md     # Custom workflow
├── data/
└── tools/

4 directories, 10 files

Add Navigation Tools

Update README.md with tools to explore the project.

---
tools:
  - [curl, -X, GET, "https://httpbin.org/status/200"]
  - [ls]
  - [cat]
---

# Instructions
- Use `curl` to check if the service is up
- Use `ls` and `cat` to browse other files

Add Specialized Tools

Expand your app with specialized workflows.

---
tools:
  - [grep]
---

# Document Search
- Use `grep` for keyword searches in `data/`.

---
tools:
  - [psql, -U, $USER, -d, $DB, -c, { regex: "^SELECT\b.*" }]
---

# Database Access
- Call `psql` to query the database with read-only SELECT statements

---
tools:
  - [python3, tools/analyze.py]
---

# Custom Tools
- Run `analyze.py` to process data, passing `--input` as needed

Deploy It

Create a free Statespace account¹ and deploy your app in one command.

toolfront deploy .

Deploys to https://your-app.toolfront.app. Share it with the community or your team!

Installation

Install toolfront with your favorite PyPI package manager (Requires Python 3.10+).

pip install toolfront

uv add toolfront

poetry add toolfront

Community & Contributing

• Discord: Join our community server for real-time help and discussions
• X: Follow us @statespace_tech for updates and news
• Issues: Report bugs or request features on GitHub Issues

License

This project is licensed under the terms of the MIT license.