Forge Modules

Each forge module extends the base pipeline with domain-specific scanners, belief templates, derivation rules, and review criteria.

Built-in modules

Module	Input	Best for
code	Git repos, source files	Architecture beliefs, technical decisions, API contracts
project	Issue trackers, PRs	Project state, decisions, blockers, team knowledge
product	GitHub/GitLab/Jira	Product beliefs, user needs, feature priorities
paper	PDFs, arXiv, DOIs	Research claims, citation networks, findings
document	Any documents	General-purpose belief extraction

Code Forge

Analyzes codebases to extract architectural beliefs, technical decisions, and API contracts.

reasonsforge code --repo ./my-project --output reasons.db

Scanners: Reads source files, parses function signatures, analyzes git history for decision patterns.

Best for: Understanding a codebase’s architecture, tracking technical decisions, onboarding new developers.

Project Forge

Extracts project state from issue trackers and pull requests.

reasonsforge project --github owner/repo --output reasons.db

Scanners: Pulls issues, PRs, comments, labels, and milestones from GitHub, GitLab, or Jira.

Best for: Project status dashboards, decision tracking, identifying blockers and dependencies.

Product Forge

Analyzes product data to extract user needs, feature priorities, and product beliefs.

reasonsforge product --github owner/repo --domain "Payment platform" --output reasons.db

Scanners: Pulls issues with product labels, user feedback, feature requests, bug reports.

Best for: Product roadmap analysis, user need identification, competitive analysis.

Paper Forge

Processes academic papers to extract claims, track citation networks, and build research knowledge bases.

reasonsforge paper --arxiv 2301.12345 --output reasons.db

Scanners: Parses PDFs, fetches arXiv/DOI metadata, extracts claims with citation links.

Best for: Literature reviews, research synthesis, tracking claims across papers.

Document Forge

General-purpose belief extraction from any document format.

reasonsforge document --input ./docs/ --output reasons.db

Scanners: Reads markdown, text, HTML, and PDF files from a directory.

Best for: Converting existing documentation into a queryable, justified knowledge base.

Choosing a module

Pick the module that matches your data source. Each module shares the same pipeline — the difference is in the scanners (what data it pulls) and the templates (how beliefs are structured for that domain).

If none of the built-in modules fit, build your own.