Generate a tailored prompt for an AI coding tool before asking it to add a feature to your real project.
Get a structured bug fix prompt that includes your project's actual security and architecture context.
Build custom plugins to add project specific checks to the prompts DevObin generates.
Compare prompt quality across OpenAI, Anthropic, Google, or local Ollama models for the same task.
| mobinhasanghasemi/devobin | 0c33/agentic-ai | adennng/stock_strategy_lab | |
|---|---|---|---|
| Stars | 14 | 14 | 14 |
| Language | Python | Python | Python |
| Setup difficulty | easy | hard | hard |
| Complexity | 2/5 | 4/5 | 4/5 |
| Audience | developer | developer | researcher |
Figures from each repo's GitHub metadata at analysis time.
Requires an API key from OpenAI, Anthropic, Google, or a running Ollama instance.
DevObin is a command line tool that looks at your existing software project and writes detailed instructions, called prompts, that you can hand to an AI coding assistant like Claude, Codex, Cursor, or GPT. It does not write any code itself. Instead it reads your actual files, works out what frameworks, languages, and database you are using, and turns that understanding into a prompt tailored to your real codebase rather than a generic template. When you run DevObin, you connect it to an AI provider such as OpenAI, Anthropic, Google, or a locally running Ollama model, describe what you want built or fixed, and it produces a markdown file with the finished prompt. That file typically contains around twenty structured sections covering things like the project's tech stack, coding rules, accessibility requirements, security rules, and expected deliverables, though which sections appear changes depending on whether you are asking for a bug fix, a new feature, or a performance improvement. The tool also keeps a running knowledge graph of your project so it can select only the parts of that context that are relevant to your current request, rather than dumping everything into every prompt. There is an optional prompt optimization step that checks for contradictions and can refine the wording before you copy it out, and a small plugin system lets developers add their own custom checks. DevObin is installed through pip and requires Python 3.12 or newer along with an API key for whichever AI provider you choose to use. It is aimed at developers who already work with AI coding tools and want the prompts they hand those tools to be grounded in their actual project instead of copied from a generic checklist. It is released under the MIT license.
A Python CLI that reads your codebase and writes detailed, project specific prompts for AI coding assistants like Claude or Cursor to use.
Mainly Python. The stack also includes Python, CLI, OpenAI.
MIT license: free to use, copy, modify, and distribute, including commercially, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Verify against the repo before relying on details.