Our take
Inactiveno commits in over a year- Activity
- 19
- Community
- 31
- Issues
- 21
- Pull requests
- 20
+2 stars in the last 30 days
- Fewer contributors than 82% of the projects we track
Ditto is a lightweight experiment for Flask scaffolding, but its inactive status and stated lack of ongoing maintenance make it a risky foundation for an actively maintained product.
Good fit if
- You want to experiment with generating a Flask app from a natural-language prompt.
- You are comfortable with Python, an OpenAI API key, and checking or fixing generated code yourself.
- You want to study a compact coding-agent prototype under the MIT license.
Look elsewhere if
- You need an actively maintained tool: there have been no commits in over a year and no recent releases.
- You need dependable support or regular issue handling: the project is inactive, and most of the code comes from one person.
- You need a production-ready generator with documented reliability guarantees; the README frames Ditto as an exploration and cautions that results may fall short.
All health signals
| Last commit | 2024-10-19 (2 years ago) |
|---|---|
| Commits, last 90 days | 0 |
| Releases, last 12 months | 0 |
| Contributors | 3 (top contributor: 75% of commits) |
| Issues closed, last 90 days | 0 |
| Pull requests merged, last 90 days | 0 |
| Project age | 2 years |
Checked on 2026-10-24 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
1,068Forks
159Change since Nov 16, 2026: 0 stars·0 forks
Overview
Ditto is a self-building coding agent built around LiteLLM and a simple tool-using LLM loop. It takes a plain-English description and attempts to generate a multi-file Flask application, including routes, templates, and static files, through a web interface served locally at port 8080.
It is aimed at people who want to experiment with turning an app idea into a runnable Flask project without manually creating its initial structure and code. The repository describes itself as a quick exploration and notes that generation may only get close to a working result.
Key Features
- Accepts a natural-language description of a Flask application.
- Uses an LLM loop with tools to plan and generate application code.
- Creates routes, templates, and static files for a multi-file project.
- Organizes generated code into separate directories.
- Provides a browser interface for submitting requests and monitoring progress.
- Lets users rerun the Flask app to try the generated result.
Use Cases
- A Flask beginner can explore how a simple app idea might translate into routes and templates.
- A developer can quickly scaffold a throwaway prototype from a written specification.
- A product or design collaborator can test whether a rough concept can be expressed as a runnable web app.
- Someone exploring coding agents can inspect a small example of an LLM-driven code-generation loop.
What you need
Detected in the repository
- Python (from requirements.txt)
License in plain words
MITpermissive
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the copyright and license notice
- Share your changes: no
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Install the dependency, set OPENAI_API_KEY, and start the local interface:
pip install litellm
python main.py
Open http://localhost:8080 in a browser. See the README for environment setup and usage details.
Alternatives
- bolt.diy: bolt.diy generates and edits Node.js applications in a browser workspace, while ditto creates Flask apps through a local web interface.
- gpt-engineer: gpt-engineer turns specifications into code through a Python CLI, rather than generating Flask applications through a local web interface.
- gpt-pilot: GPT Pilot guides developers through planning, coding, review, and debugging applications, rather than using a simple agent loop to generate Flask apps.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| ditto | Python | MIT | 1.1k | Inactive |
| bolt.diy | TypeScript | MIT | 19.9k | Active |
| gpt-engineer | Python | MIT | 55.1k | Archived |
| gpt-pilot | Python | – | 33.6k | Quiet |
Considerations
The repository has had no commits in over a year, no recent releases, and no recent issue closures or merged pull requests. It has only a small contributor group, with most code concentrated in one contributor, so fixes and compatibility updates may be slow or absent. The README itself says the project is a quick exploration and that generation may not produce a fully functional app. Running it requires Python and an OpenAI API key; the supplied requirements information does not indicate tests or CI. The project is MIT-licensed.
Found this useful?
Share it with someone who would like ditto.