QuoteForge: Local AI proposals with prices you can trust

Description and use

QuoteForge lets freelancers generate proposals locally, keeping client briefs private and ensuring accurate pricing calculations.

Problem

Freelancers need to convert client briefs into accurate proposals without exposing sensitive data to external AI services.

Outcome

QuoteForge enables freelancers to generate proposal drafts locally, ensuring privacy and cost transparency while keeping the model’s output independent of the pricing calculation.

Workflow

• 1. Clone the repository and run docker compose up --build.
• 2. Wait for the Ollama runtime and llama3.2 model to download.
• 3. Open http://127.0.0.1:8000 in a browser.
• 4. Enter service, brief, hourly rate, estimated hours, and expenses.
• 5. The app calculates the quote and prompts the local model to draft the proposal text.
• 6. Review the draft, make edits, and copy it for the client.

Evidence

Enter the service, brief, hourly rate, estimated hours, and expenses; the app calculates the quote and asks a local open-weight model to draft the words around it.

Source

The demo runs locally. Clone the repository, then run: docker compose up --build

Source

The model drafts the proposal; ordinary code calculates rate × hours + expenses, so generated text cannot alter the estimate.

Source

Running the model locally keeps that brief on the freelancer’s machine and avoids sending it to a hosted AI API.

Source