See Ctx in action

Your agent asked.
Ctx already knew.

Watch a live simulation of what happens when an AI agent calls Ctx — from the question to the correct answer, milliseconds later.

Agent conversation
Agent
What's our refund policy for annual plans?
Agent → Ctx
Calling ctx.getContext() to retrieve relevant policy docs…
Ctx
Retrieved 1 relevant snippet from billing-policies.md (score: 0.94)

"Annual plan subscribers may request a full refund within 14 days of renewal. After 14 days, prorated refunds are available for the unused months, processed within 5 business days."
Agent
Annual plan subscribers can request a full refund within 14 days of their renewal date. After that, prorated refunds are available for unused months and processed within 5 business days.
API payload
→ Request
{
  "query": "refund policy annual plans",
  "agentId": "agent_support_7f2a",
  "topK": 3,
  "minScore": 0.7
}
← Response 200 OK · 43ms
{
  "results": [
    {
      "source": "billing-policies.md",
      "score": 0.94,
      "text": "Annual plan subscribers
        may request a full refund
        within 14 days of renewal…"
    }
  ],
  "latencyMs": 43
}
Step 1 of 4
📁
Connect sources
Notion, GitHub,
Slack, custom API
ingest
ctx.
Ctx indexes
Chunks, embeds,
ranks by relevance
getContext()
🤖
Agent queries
Gets the right context,
answers correctly

One call. Your agent gets exactly what it needs — no prompt stuffing, no manual retrieval logic.

TypeScript
import { Ctx } from '@ctx-ai/sdk';

const ctx = new Ctx({ apiKey: process.env.CTX_API_KEY });

// In your agent tool handler:
const { results } = await ctx.getContext({
  query:   "refund policy for annual plans",
  agentId: "agent_support_7f2a",
  topK:    3,
});

// results[0].text → the relevant policy excerpt
// results[0].score → 0.94 (semantic relevance)
// results[0].source → "billing-policies.md"
Join waitlist → View on GitHub

Ready to give your agents
a memory?

Private beta. No config. Just context.

Join the waitlist →