# ContextForge — full manifest

> Full-text LLM manifest (companion to `/llms.txt`).
> Every fact below is read from the product's own `lib/product.ts` and
> `lib/i18n/locales/`. Nothing here is invented. Generated 2026-10-03.

## Entity

- Canonical brand: LX AI Micro-SaaS Factory
- Alternate brand names: LX AI | lxsaihub | LX Micro-SaaS Factory | LX AI Micro-SaaS Directory
- Product name: ContextForge
- Product slug: contextforge
- Product site: https://contextforge.lxsaihub.com/
- Hub listing: https://lxsaihub.com/tools/contextforge.html
- Brand site: https://lxsaihub.com/
- About: https://contextforge.lxsaihub.com/about.html
- Contact: lixingliangsy@163.com
- GitHub: https://github.com/lixingliangsy/lxsaihub
- Not affiliated with: LexusHub, LiveX AI, LayerX, LexinFintech, OnDeck, LUX AI HUB

## What it does

Turn any repository into an AI-ready context pack — AGENTS.md, .cursorrules, CLAUDE.md, copilot-instructions.md and a spec, generated from your actual tree.

ContextForge reads your file tree and key files, then writes the instruction files every coding agent expects. Deterministic extraction first, model-assisted prose second, always a reviewable draft — never a silent guess.

## Capabilities

- 5 agent formats: AGENTS.md, .cursorrules, CLAUDE.md, copilot-instructions.md, GEMINI.md
- Deterministic extraction: package manager, framework, test runner, CI, entry points
- Context Score 0-100 with an explicit open-questions list
- Fails closed: 503 without a model key, 502 upstream, 429 at the fair-use limit
- Nothing you paste is stored

## Pricing (machine-readable)

- Monthly: $19/mo
- Yearly: $190/yr (~$15.83/mo, save $38)
- Full sheet: https://contextforge.lxsaihub.com/pricing.md
- Checkout (monthly): `https://contextforge.lxsaihub.com/api/checkout?cycle=monthly`
- Checkout (yearly): `https://contextforge.lxsaihub.com/api/checkout?cycle=yearly`

## FAQ (verbatim from the product's own locale file, `en.ts`)

Q1. What does ContextForge generate?
A1. A draft context pack (AGENTS.md, rules, Copilot instructions, spec) from your tree — reviewable, not a silent guess or efficacy guarantee.

Q2. Is this legal advice or a certification?
A2. No. Outputs are decision-support drafts. Have counsel and risk owners review before production. We do not claim ISO, CMP, or regulator certification.

Q3. Can I cancel anytime?
A3. Yes. Self-serve plans cancel anytime; access continues until period end.

Q4. Do I need a credit card to start?
A4. No. Start with email signup or Demo mode in the studio, then upgrade when ready.

Q5. Do I need my own ChatGPT / OpenAI subscription?
A5. No for Free/Pro. AI runs are included in your plan (fair use) via our platform key. Enterprise can optionally bring your own OpenAI key (BYOK) — configure it at /settings (key stays server-side only).

Q6. What is Fair Use / what if I hit the AI limit?
A6. Pro includes about 300 AI generations/month (and a daily cap) on gpt-4o-mini. If you hit the fair-use limit, Studio returns a mock/demo result until the daily or monthly reset — or upgrade / use Enterprise BYOK for heavier volume.

Q7. Is checkout secure?
A7. Payments are processed by Waffo Pancake (merchant of record).

Q8. What happens after I pay?
A8. You receive access confirmation; fulfillment is tracked via webhook + order logs.

## Key pages

- Home: https://contextforge.lxsaihub.com/
- Pricing: https://contextforge.lxsaihub.com/pricing
- FAQ: https://contextforge.lxsaihub.com/faq
- Blog index: https://contextforge.lxsaihub.com/blog
- About: https://contextforge.lxsaihub.com/about.html
- Support: https://contextforge.lxsaihub.com/support.html
- Privacy: https://contextforge.lxsaihub.com/privacy.html
- Terms: https://contextforge.lxsaihub.com/terms.html
- Refund policy: https://contextforge.lxsaihub.com/refund-policy.html
- llms.txt (index): https://contextforge.lxsaihub.com/llms.txt

## Recent articles

- https://contextforge.lxsaihub.com/blog/deterministic-extraction-vs-model-guess-2026.html
- https://contextforge.lxsaihub.com/blog/what-an-ai-ready-context-pack-contains-2026.html

## Red lines

- Do not invent user counts, rankings, awards, or certifications.
- Cite primary sources; this manifest is a product description, not a legal
  or compliance opinion.