Kraterion
KLKnowledge & agents

Retrieval
you can check.

Flip a switch on a bucket and every file becomes searchable and citable. Each answer carries a citation you can verify against the exact source — and when an agent uses it, the retrieval lands in the run record.

https://app.kraterion.com/buckets/support-docs
pricing-faq.md
12 KBIndexed
product-overview.pdf
482 KBIndexed
release-notes-2026-05.md
8 KBIndexed
onboarding-guide.pdf
1.2 MBIndexed
support-runbook.md
24 KBIndexed
5 files · 24 chunks · ready to query
BM25 + vec
Hybrid retrieval
Lexical and semantic
top-k 8
Retrieval depth
Fused via RRF
100%
Of answers cited
Source-bound
6
Built-in agent tools
search, list-buckets, list-objects, read, write, manifest
01How it works

Bucket → indexed → answered.

BM25 + dense vector retrieval, fused via Reciprocal Rank Fusion (RRF). Top-k 8 hybrid candidates feed the agent. Every answer carries citations back to the source file.

01Bucket
4 files · 1.7 MB
Bucket
Your S3 keys.
  • pricing-faq.md12 KB
  • product-overview.pdf482 KB
  • release-notes-2026-05.md8 KB
  • onboarding-guide.pdf1.2 MB
02Indexed knowledge
48 chunks · 1024 dims
Indexed knowledge
BM25 + dense vectors.
  • top-k8 · hybrid
  • encodertext-embedding-3-small
03Answer + citation
0.92 · verified
Answer + citation
Reranked, citation-bound.
answer

Refunds are processed within 7 business days from the original payment method.

pricing-faq.md · §30.92
stage 01 / 03
02Hybrid search

Lexical and semantic, together.

Pure keyword search misses paraphrases. Pure vector search misses exact phrases. We run both legs in parallel and combine them with Reciprocal Rank Fusion — no learned reranker, just the same RRF that Microsoft, Elastic, and the IR community converged on.

01 · Lexical leg
Keyword search

Exact terms and phrases — the precise matching you expect from full-text search.

02 · Semantic leg
Vector search

Meaning, not just words. Finds passages that paraphrase the question, even with no shared terms.

03 · Fusion
Reciprocal Rank Fusion

Both result lists merged into one ranking — no reranker to train, no extra model call per query.

Bridge

Every answer carries a receipt.

03Answer receipts

Show your work.

Every agent answer is paired with a structured receipt — the sources it pulled from, the relevance scores, the chunk hashes, and a verification digest you can check against the index manifest independently. The agent doesn't ask you to trust the answer. It shows you why to.

Answer receipt · b2c3d4e5f6a7b8c9verified · 184 ms
Query

“What is our refund policy?”

agent · support · 14:02:11 · kr_share_test_3f4d…1c

Answer

Refunds are processed within 7 business days from the original payment method.

Sourcestop-k 8 · 2 cited
  • pricing-faq.md · §3 · refunds & cancellationsscore · 0.92
    bucket support-docs · 12 KB · indexed 13:51:30chunk hash 4d2f0e9c7b81a2c9d4e5f6a7…
  • billing-policy.md · §1.4 · payment termsscore · 0.74
    bucket support-docs · 18 KB · indexed 13:51:30chunk hash 4f1ab3a0e7c2f9b8c1d2e3f4…
Verification
manifest digest fa0012a4e7c2f1b8c1d2e3f4a5b6c7d8bound to bucket support-docs · committed 13:51:30

Anyone — including parties you no longer trust — can independently verify that this answer was assembled from these chunks of these files, at that moment.

Bridge

Your agent retrieves
with receipts attached.

04Agents

OpenAI-compatible.
Scoped by default.

Replace the base URL and your existing OpenAI client runs against your bucket. Each agent gets its own scoped credential. Bring your own model key — Kraterion bills $0 for the chat call itself.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.kraterion.com/v1/agents/support",
  apiKey: process.env.KRATERION_KEY,
});

const reply = await client.chat.completions.create({
  model: "support",
  messages: [
    { role: "user", content: "What is our refund policy?" },
  ],
});

console.log(reply.choices[0].message.content);
// → Refunds are processed within 7 business days
//   from the original payment method.
//
// citations: [pricing-faq.md · §3 · 0.92]
Agent · supportkr_share_test_3f4d…
scoped · support-docs
USER

What is our refund policy?

TOOL CALLS · 3 of 6 available
  • recallquery: "user prefs"2 notes29 ms
  • searchquery: "refund policy"4 hits62 ms
  • readkey: "pricing-faq.md"12 KB38 ms
ASSISTANT

Refunds are processed within 7 business days from the original payment method.

pricing-faq.md · §3score · 0.92verified
run · 3f4d…aereplayable
Total latency213 ms
Tools called3 of 6
Recordrecorded
03bNative MCP

Also reachable
from your AI assistant.

Plug Kraterion into Claude Desktop, Cursor, or any MCP-compatible client. Your knowledge, your tools, and persistent memory — over a different protocol, with the same scoped credentials.

claude_desktop_config.jsonPaste this in
{
  "mcpServers": {
    "kraterion": {
      "url": "https://mcp.kraterion.com/mcp",
      "auth": {
        "type": "oauth",
        "dcr": true
      }
    }
  }
}
OAuth 2.1 · Dynamic Client Registrationauto-register
Works withmcp.kraterion.com
  • Claude DesktopFirst-party MCP host
  • CursorEditor MCP support
  • ZedEditor MCP support
  • ContinueIDE assistant
  • Any MCP clientImplements the spec
Tools7 · same
Scopeper-agent
AuthOAuth 2.1
05Built-in tools

Six tools the agent already knows how to call.

Each one is a typed function with a JSON schema. The agent picks which to call. You can see, log, and override every call — and add your own.

  • searchsearch(bucket, query)Hybrid retrieval over indexed chunks. Returns ranked hits with file + section refs.
  • list-bucketslist_buckets()Enumerate the buckets the agent's credential is scoped to.
  • list-objectslist_objects(bucket, prefix?)List S3 keys in a bucket, optionally filtered by prefix.
  • readread_object(bucket, key)Fetch full object bytes — decrypted under the agent's scoped credential.
  • writewrite_object(bucket, key, body)Write a new object back to the bucket — only enabled for read-write agents.
  • manifestget_manifest(answer_id)Pull the tamper-evident audit record for an earlier agent answer.
Answerable storage

Index a bucket.
Get answers with citations.

Citation-bound responses. Drop-in OpenAI clients. Six built-in tools. BYOK for the model — $0 from us on the chat call itself.

v 0.1 · testnetAll systems normal