# yoheinakajima/ditto

the simplest self-building coding agent

Repository: https://github.com/yoheinakajima/ditto
Canonical: https://ross.abutalabs.com/products/yoheinakajima-ditto
Language: Python
License: MIT
License Family: permissive
Last push: 2024-10-19T17:58:27+00:00

## Health v2 (maintenance only)
Score: 22/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 49
- inputs: {"age_days": 687, "days_push": 683, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1067, forks 161 (observed 2026-08-28T04:03:27.352285+00:00)

## What it is
Ditto is a simple self-building coding agent that generates multi-file Flask applications from natural language descriptions via a web interface. It uses an LLM loop with a few tools to plan and write routes, templates, and static files automatically.

## Use cases
- generate a flask app from a plain english description
- build a web application without writing code
- prototype multi-file web apps with an llm agent
- self-building coding agent experiment
- turn app ideas into working flask code automatically
- no-code tool to scaffold python web apps

## When to choose
- you want a minimal, hackable agent to generate simple Flask apps from prompts
- you're experimenting with self-building agent loops in Python
- you need quick prototypes of small web applications

## When to avoid
- you need production-grade, reliable code generation
- you want frameworks other than Flask
- you require fine-grained control over generated architecture or testing

## Facets
- artifact type: application
- maturity: experimental
- function: agent-framework, llm-inference, web-framework
- domain: artificial-intelligence, large-language-models, web-development, developer-tools
- platform: python, self-hosted, cross-platform
- tags: self-building-agent, flask, no-code, litellm, natural-language-to-code, code-generation, ai-agents, web-server

## Member repositories
- yoheinakajima/ditto (main) score 22

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:27.352285+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:55:12.893671+00:00, confidence not recorded.
  - readme: https://github.com/yoheinakajima/ditto (fetched 2026-08-28T04:03:27.352285+00:00, sha 5e8901b0af06)
- Data as of 2026-08-30T08:39:29.467469+00:00.