The open standard + search engine for AI-readable web content. Like robots.txt tells crawlers what to index, context.txt tells AI agents what your site is about.
A single text file gives AI agents everything they need. No scraping, no parsing, no wasted tokens.
Add /context.txt to your domain. Plain text, structured for AI. No software to install.
yourdomain.com/context.txtSubmit your domain and we index every section. Sites without context.txt get auto-scraped via AI.
POST /submitAI agents query the index and get structured results in <10ms. MCP server, REST API, or n8n node.
GET /search?q=...<10ms
Response time
vs 5-10s scraping
~2K
Tokens consumed
vs 50K+ from HTML
High
Signal quality
publisher-curated content
Any site
Indexing
context.txt or AI fallback
Traditional RAG indexes your own documents. ProtoContext applies the same idea to the open web — websites publish structured context, your agents query it in real-time. No chunking, no embeddings, no vector database.
Every website that adds a /context.txt becomes a searchable node — queryable by any AI agent, in any framework, in milliseconds. No third-party API keys, no embeddings to generate, no vector database to maintain.
The internet already has the data. ProtoContext makes it readable.
All endpoints available at your engine URL. Authenticate with x-proto-token header.
/searchFull-text search across all indexed sites
qstringrequiredSearch querydomainstringFilter by domainlimitintMax results (default 10)curl "http://localhost:8000/search?q=payments&limit=5" \ -H "x-proto-token: YOUR_TOKEN"
With AI provider:
curl "http://localhost:8000/search?q=payments" \ -H "x-proto-token: YOUR_TOKEN" \ -H "x-ai-key: YOUR_KEY" -H "x-ai-model: gemini/gemini-3-flash-preview"
/siteGet all context sections for a domain
domainstringrequiredDomain to retrievecurl "http://localhost:8000/site?domain=stripe.com" \ -H "x-proto-token: YOUR_TOKEN"
/submitSubmit a new domain to the index
domainstringrequiredDomain to registerai_keystringAI provider keyai_modelstringModel in provider/name formatcurl -X POST http://localhost:8000/submit \
-H "Content-Type: application/json" \
-H "x-proto-token: YOUR_TOKEN" \
-d '{"domain": "example.com"}'/deleteRemove a domain from the index
domainstringrequiredDomain to deletecurl -X POST http://localhost:8000/delete \
-H "Content-Type: application/json" \
-H "x-proto-token: YOUR_TOKEN" \
-d '{"domain": "example.com"}'/batchMultiple search queries in one request
queriesarrayrequiredArray of {q, domain?, limit?}curl -X POST http://localhost:8000/batch \
-H "Content-Type: application/json" \
-H "x-proto-token: YOUR_TOKEN" \
-d '{"queries": [{"q": "payments"}, {"q": "docs", "domain": "stripe.com"}]}'/statsIndex statistics
curl http://localhost:8000/stats \ -H "x-proto-token: YOUR_TOKEN"
/healthHealth check
curl http://localhost:8000/health
All protected endpoints require the x-proto-token header. Tokens are generated during setup or login.
/auth/statusCheck authentication status and mode
curl http://localhost:8000/auth/status
/auth/setupCreate admin account (first run only)
namestringrequiredAdmin nameemailstringrequiredAdmin emailpasswordstringrequiredMin 8 characterscurl -X POST http://localhost:8000/auth/setup \
-H "Content-Type: application/json" \
-d '{"name": "Admin", "email": "[email protected]", "password": "securepass"}'/auth/loginSign in and receive session token
emailstringrequiredAccount emailpasswordstringrequiredAccount passwordcurl -X POST http://localhost:8000/auth/login \
-H "Content-Type: application/json" \
-d '{"email": "[email protected]", "password": "securepass"}'/auth/logoutInvalidate current session
curl -X POST http://localhost:8000/auth/logout \ -H "x-proto-token: YOUR_TOKEN"
Gemini
gemini/gemini-3-flash-previewOpenAI
openai/gpt-4o-miniOpenRouter
openrouter/google/gemini-3-flash-previewCreate a context.txt file, publish it on your domain, and your site is instantly readable by AI agents worldwide. No SDK, no API key, no signup.
# My Startup > AI-powered analytics for e-commerce @lang: en @version: 1.0 @updated: 2026-02-23 @topics: analytics, e-commerce, AI ## section: About We help online stores understand their customers using real-time AI analytics. ## section: Pricing Free tier: 1K events/month Pro: $29/month — 100K events Enterprise: Custom pricing
Copy this prompt into any AI (ChatGPT, Claude, Gemini) and paste your website content. It will output a properly formatted context.txt ready to publish.
You are a context.txt generator for the ProtoContext standard. Your job is to take any website content (text, about pages, docs, product info) and convert it into a properly formatted context.txt file. Follow this exact format: --- # Site Name > One-line description of what this site/product/company does @lang: [language code, e.g. en, es, fr] @version: 1.0 @updated: [today's date in YYYY-MM-DD] @topics: [comma-separated relevant topics] ## section: [Section Title] [Content for this section. Plain text, concise, factual. Written for AI agents to understand, not for marketing. Remove all fluff, CTAs, and promotional language. Keep only the useful information.] ## section: [Another Section] [More content...] --- Rules: 1. Each section starts with "## section: " followed by the title 2. Keep sections focused — one topic per section 3. Write in plain, factual language optimized for AI consumption 4. Remove HTML, markdown links, images, and formatting artifacts 5. Include metadata (@lang, @version, @updated, @topics) at the top 6. The first line is "# Site Name" followed by "> description" 7. Typical sections: About, Products/Services, Pricing, API, Documentation, Contact, FAQ 8. Keep each section under 500 words — be concise 9. Do NOT include navigation elements, footers, cookie notices, or UI text 10. Output ONLY the context.txt content, nothing else Now convert the following website content into a context.txt file:
Copy the prompt, paste it into any AI, then paste your website content after it. Publish the output as yourdomain.com/context.txt