Search engine for AI agents

Context for the
agent era

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.

Sub-10ms latencyPure signal, no noise

How it works

A single text file gives AI agents everything they need. No scraping, no parsing, no wasted tokens.

01

Publish

Add /context.txt to your domain. Plain text, structured for AI. No software to install.

yourdomain.com/context.txt
02

Index

Submit your domain and we index every section. Sites without context.txt get auto-scraped via AI.

POST /submit
03

Search

AI 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

The new paradigm

RAG for the entire internet?

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.

Traditional approach
01Scrape HTML from websites
02Parse and clean messy DOM
03Chunk text into fragments
04Generate embeddings ($$$)
05Store in vector database
06Retrieve with semantic search
07Hope the chunks are relevant
~5-10s latency50K+ tokensnoisy data
ProtoContext
01
Website publishes context.txtplain text, structured
02
ProtoContext indexes itauto, instant
03
Agent queries the indexGET /search
04
Gets structured results<10ms, ~2K tokens
~7ms latency~2K tokenspure signal

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.

API Reference

All endpoints available at your engine URL. Authenticate with x-proto-token header.

GET/search

Full-text search across all indexed sites

qstringrequiredSearch query
domainstringFilter by domain
limitintMax 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"
GET/site

Get all context sections for a domain

domainstringrequiredDomain to retrieve
curl "http://localhost:8000/site?domain=stripe.com" \
  -H "x-proto-token: YOUR_TOKEN"
POST/submit

Submit a new domain to the index

domainstringrequiredDomain to register
ai_keystringAI provider key
ai_modelstringModel in provider/name format
curl -X POST http://localhost:8000/submit \
  -H "Content-Type: application/json" \
  -H "x-proto-token: YOUR_TOKEN" \
  -d '{"domain": "example.com"}'
POST/delete

Remove a domain from the index

domainstringrequiredDomain to delete
curl -X POST http://localhost:8000/delete \
  -H "Content-Type: application/json" \
  -H "x-proto-token: YOUR_TOKEN" \
  -d '{"domain": "example.com"}'
POST/batch

Multiple 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"}]}'
GET/stats

Index statistics

curl http://localhost:8000/stats \
  -H "x-proto-token: YOUR_TOKEN"
GET/health

Health check

curl http://localhost:8000/health

Authentication

All protected endpoints require the x-proto-token header. Tokens are generated during setup or login.

GET/auth/status

Check authentication status and mode

curl http://localhost:8000/auth/status
POST/auth/setup

Create admin account (first run only)

namestringrequiredAdmin name
emailstringrequiredAdmin email
passwordstringrequiredMin 8 characters
curl -X POST http://localhost:8000/auth/setup \
  -H "Content-Type: application/json" \
  -d '{"name": "Admin", "email": "[email protected]", "password": "securepass"}'
POST/auth/login

Sign in and receive session token

emailstringrequiredAccount email
passwordstringrequiredAccount password
curl -X POST http://localhost:8000/auth/login \
  -H "Content-Type: application/json" \
  -d '{"email": "[email protected]", "password": "securepass"}'
POST/auth/logout

Invalidate current session

curl -X POST http://localhost:8000/auth/logout \
  -H "x-proto-token: YOUR_TOKEN"

Supported AI Providers

Gemini

gemini/gemini-3-flash-preview

OpenAI

openai/gpt-4o-mini

OpenRouter

openrouter/google/gemini-3-flash-preview

Start in 30 seconds

Create 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.

yourdomain.com/context.txt
# 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
AI-powered

Generate your context.txt

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.

context.txt generator prompt
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