Knowledge retrieval API
for AI agents

Connect your unstructured data and give your agents accurate, cited context from your knowledge base via API or MCP.

Get started

View docs

Join the teams building the AI frontier

Trusted by category-defining startups and Fortune 500 enterprises

Join the teams building the AI frontier

Trusted by category-defining startups and Fortune 500 enterprises

Everything you need to give your AI agents context from unstructured knowledge

Every connector you need, already built

Pre-built connectors for web crawls, support tickets, code, chat threads, and more. Each one absorbs its API's quirks, so you never need to write data pipeline code again.

Explore connectors

Any scale of data, always up to date

Kapa detects and re-processes only what changed, so updates land in minutes and staying current never costs a full re-index.

Explore syncing

Retrieval that stays state-of-the-art

Chunking, embedding, hybrid search, reranking and evals - tuned continuously by our world-class research team for you. All of it behind one API call.

Explore agentic retrieval

cURL
curl -X POST \
  "https://api.kapa.ai/query/v1/projects/<YOUR_PROJECT_ID>/retrieval/" \
  -H "X-API-KEY: <YOUR_API_KEY>" \
  -d '{
    "query": "How do I configure authentication?"
  }'
cURL
curl -X POST \
  "https://api.kapa.ai/query/v1/projects/<YOUR_PROJECT_ID>/retrieval/" \
  -H "X-API-KEY: <YOUR_API_KEY>" \
  -d '{
    "query": "How do I configure authentication?"
  }'

Pruning cuts tokens by 68%

Pruning cuts tokens by 68%

Pruning off

Pruning off

100%

100%

Pruning on

Pruning on

32%

32%

Tokens kept

Tokens kept

Tokens removed

Tokens removed

Send only the context the agent needs

Give your agents the context that actually matters, Kapa prunes the rest. Accurate retrieval at scale for 68% fewer tokens.

Exploring pruning

Why engineers love Kapa

Rated 4.9/5 on G2

Y

Backed by Y Combinator

“We use Kapa to power self-serve AI agents on our docs, which cuts time-to-value dramatically.”

Jan Oberhauser

CEO · n8n

“Kapa is super easy to set up. As we expand, we’ll continue to find more integration points to bring the right context to our agents.”

Dana Lawson

CTO, Netlify

“Kapa lets us focus on building agents, not maintaining retrieval infrastructure.”

Sam Bhagwat

Sam Bhagwat

CEO, Mastra

“Thousands of complex sources across PDFs, versioned docs, and code. Kapa keeps it all in sync as we ship.”

Deidre Casey

AI Integration Manager, Nordic Semiconductor

“Kapa is key infrastructure for powering context in our user-facing agents.”

Daniel Hai

AI Product Manager, monday.com

“Kapa started as an agent on our docs. Now it’s the interface layer between our product and everyone.”

Matan Grady

Product Director, Port

Twice as accurate as alternatives. Proven in production.

2x

2x

more likely to find the right source than DIY retrieval and web search

Recall@5 on human-annotated questions from four public knowledge bases.

Explore benchmark

Recall@5

Kapa

DIY retrieval

Web search

Kapa

65%

Firecrawl + Pinecone

37%

Azure AI Foundry

35%

Exa

35%

Tavily

27%

Trusted by 200+ leading companies

Enterprise-grade security and controls

Talk to us

Zero data retention & PII masking

Security controls to limit data retention and PII processing for sensitive use cases.

SOC 2

SOC 2 & GDPR

Independently audited controls for security, availability, and confidentiality.

SSO & RBAC

Single sign-on and role-based access across the platform.

EU/US

Data regions

US and EU hosting available, so your knowledge stays where compliance needs it.

Everything you need to give your agents accurate retrieval, ready in minutes.

Get started for free. Connect your sources and get an API key or hosted MCP server to give your agents the context they need to do reliable work at scale.

Get started

Frequently asked questions

What is Kapa?

−

Kapa is an ingestion and retrieval system for your unstructured knowledge. Ingestion assembles a unified knowledge base from 20+ types of sources - documentation sites, PDFs, tickets, community threads, API specifications — and keeps it up to date as that content changes. Agentic retrieval searches across it to find what the agent needs, the moment it needs it. You hand Kapa to your agent as a search tool via MCP, or call it directly through the API. And for the cases where you do not want to build an agent at all, Kapa offers Prebuilt Agents for common use cases, out of the box.

What can I build with Kapa?

+

Why do agents need retrieval? Can’t I just put my docs in the context window?

+

How is this different from building retrieval in-house?

+

When would I use a web search API like Exa or Tavily instead?

+

Which knowledge sources can Kapa ingest?

+

How does Kapa keep the knowledge base up to date?

+

Does it work with my agent framework and model?

+

I just want a documentation assistant. Do I have to build an agent?

+

Is my data secure? Is it used for training?

+

How does pricing work?

+

Can Kapa run on-prem or in our own VPC?

+

Pricing

Documentation

Get started

Book a demo

Login

Login

Login