A local web UI that scans any project folder on your machine, lets you select and annotate files, and generates a structured prompt you can paste directly into any LLM chat — Claude, ChatGPT, Gemini, or any other.
Every other tool in this space is a CLI that dumps your entire repo into one file. ContextForLLM gives you a browser UI where you can:
- Toggle individual files in or out
- Add a note to any file that gets embedded into the prompt
- Generate an AI summary of your project using Groq
- Automatically split large projects into sequenced prompt parts
- Set your task so the LLM knows exactly what to do
Screenshot / GIF coming soon
You need Python 3.8 or higher installed.
pip3 install contextforllm
contextforllmThat's it. The browser opens automatically.
git clone https://github.com/Desai-23/ContextForLLM.git
cd ContextForLLM
bash install.sh
bash run.sh- Paste the path to any project folder on your machine
- Click Scan
- Review the files — toggle any file off to exclude it from the prompt
- Add annotations to files if needed (the LLM will see these notes)
- Optionally generate an AI summary of your project using Groq
- Set your task — what you want the LLM to do
- Click Generate Context Prompt
- Copy the prompt and paste it into any LLM chat
- Local — your code never leaves your machine
- Browser UI — no terminal required after launch
- Per-file exclusion — toggle files in or out with a switch
- Per-file annotations — add notes that get embedded into the prompt
- Token counter — live token count with a visual usage bar
- Prompt splitting — large projects automatically split into sequenced parts with handoff instructions
- AI project summary — uses Groq to generate a project summary injected at the top of every prompt
- .contextignore support — create a .contextignore file in any project to permanently exclude files
Create a .contextignore file in any project folder to exclude files automatically on scan. Uses the same pattern syntax as .gitignore.
Example:
*.test.js
migrations/
old_auth.py
The AI summary feature requires a free Groq API key.
- Get a free key at console.groq.com
- Click "Add Groq Key" in the top right of the UI
- Paste your key — it is held in memory only and never saved to disk
- Python / Flask — backend server
- Vanilla HTML, CSS, JS — frontend UI
- tiktoken — token counting
- Groq — AI project summary (optional)
MIT