The pit crew for your projects. Point it at any codebase and get scored, AI-ready context in 60 seconds.
Transform any project - new, legacy, famous OSS, or forgotten side projects - into an AI-intelligent workspace with persistent context that works across all AI tools.
FAF scores completeness of its own context schema; it does not measure whether an AI can understand a repository or whether a project is production ready.
| What Exists | What It Tells AI |
|---|---|
| README.md | "What this does" (for humans) |
| docs/ | "How to use it" (for humans) |
| project.faf | "How to help build this" (for AI) |
Documentation tells humans how to use your code. AI context tells AI how to help you build it. They're completely different things.
| Project Type | What FAF Wizard Does |
|---|---|
| Brand new | Perfect AI context from line one |
| Legacy nightmare | AI finally understands the archaeology |
| Famous OSS | Even React doesn't have this |
| Side projects | Stop re-explaining every session |
| Client handoffs | Portable context for any AI tool |
| Team projects | Shared context that everyone can use |
Before: "This 50k-line PHP codebase from 2015..."
AI: "I don't understand this architecture"
After: 60 seconds with FAF Wizard
AI: "I see this is a Laravel-based e-commerce system with
payment processing, inventory management, and multi-tenant
architecture. Here's how I can help..."
Before: Every AI session starts with context explanation
Time lost: 5-10 minutes per session
After: project.faf exists
AI: Instant understanding, productive from message one
Time saved: 2+ hours per day
faf auto
# Scans manifest files, directory structure, dependencies
# Detects: React + TypeScript + Tailwind + Vercel
# Auto-generated project.faf
project:
name: my-saas-dashboard
goal: Customer analytics platform
stack:
frontend: react-18
css: tailwind
deployment: vercel
human_context:
who: Solo founder
what: SaaS analytics dashboard
why: Customer insights for small businesses
✅ Generated: project.faf
🏆 AI-Readiness: 87% Bronze - Production ready
Filled: 9/11 active slots
Ignored: 22 slots (not applicable)
To reach Silver (95%):
+ Add API documentation (+5%)
+ Define deployment details (+3%)
Analyzed 8,400+ Projects:
Automatically detects and configures:
.faf loadingAlready have AI context files?
# Migrates existing context
faf migrate --from .cursorrules
faf migrate --from CLAUDE.md
faf migrate --from README.md
# One format, works everywhere
faf sync --target all
npm install -g faf-cli
cd your-project
faf auto
{
"mcpServers": {
"faf": {
"command": "npx",
"args": ["-y", "claude-faf-mcp@latest"]
}
}
}
Install from Chrome Web Store - works on any Git repository.
package.json, Cargo.toml, pyproject.toml, etc.| Project Type | Avg Score | Time to Bronze | Detection Rate |
|---|---|---|---|
| React/Vue | 89% | Instant | 99.8% |
| Python Django | 91% | Instant | 99.5% |
| Rust CLI | 85% | Instant | 99.1% |
| Legacy PHP | 76% | 30 seconds | 94.2% |
| Monorepo | 82% | 45 seconds | 91.8% |
Use faf-wizard for:
Use faf-expert for:
Upstream quality and packaging claims — verify against the selected version:
# One command, done forever
npx faf-cli auto
# Check the results
cat project.faf
Install the browser extension and click "Generate FAF" on any repo.
# Set up team-wide MCP server
faf mcp install --team
faf sync --target all --watch
Stop explaining your project every session. FAF Wizard - because AI should understand your project as well as you do.
Before generating or syncing, inspect existing project.faf, CLAUDE.md, AGENTS.md and other target instruction files. Preserve their user-authored rules, preview the diff and apply only scoped changes; sync --target all is not authorization to overwrite unrelated instructions. Never place credentials or confidential source in context files. Timing, adoption and accuracy figures above are upstream claims, not evidence established by this catalog. Upstream integration model.