Quickstart

Install

pip install vrin

npm install -g @vrin/cli

Requires Python 3.9+.

Get an API key

export VRIN_API_KEY=vrin_live_your_api_key

Or create one from the CLI:

vrin auth login you@example.com
vrin auth create-key --name "my-project"

Insert knowledge

CLI
Python
curl

vrin insert "ACME Corp reported $50M revenue in Q4 2025, up 23% YoY. CEO Jane Smith attributed growth to enterprise." --title "ACME Q4"

from vrin import VRINClient

client = VRINClient(api_key="vrin_live_your_api_key")
client.insert(
    "ACME Corp reported $50M revenue in Q4 2025, up 23% year-over-year. "
    "CEO Jane Smith attributed growth to the enterprise segment.",
    title="ACME Q4 2025 Earnings"
)

curl -X POST https://api.vrin.cloud/insert \
  -H "Authorization: Bearer vrin_live_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"content": "ACME Corp reported $50M revenue in Q4 2025...", "title": "ACME Q4"}'

VRIN automatically chunks the text, extracts structured facts, and indexes everything in the knowledge graph.

Query

CLI
Python
curl

vrin query "What is ACME's revenue?"

result = client.query("What is ACME's revenue?")
print(result["summary"])

curl -X POST https://api.vrin.cloud/query \
  -H "Authorization: Bearer vrin_live_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"query": "What is ACME revenue?"}'

Stream responses

vrin query "Summarize ACME's Q4 performance" --stream

for token in client.query("Summarize ACME's Q4 performance", stream=True):
    print(token, end="", flush=True)

Upload files

vrin upload ./earnings_report.pdf

client.upload_file("earnings_report.pdf")

Bulk insert

Insert many documents at once from a JSON file:

vrin bulk-insert ./papers.json --tag research

Multi-turn conversations

vrin query "What was ACME's Q4 revenue?" --json
# Note the session_id in the response

vrin query "How does that compare to Q3?" --session-id "sess_abc123"

client.start_conversation()
r1 = client.continue_conversation("What was ACME's Q4 revenue?")
r2 = client.continue_conversation("How does that compare to Q3?")
client.end_conversation()

For AI agents

VRIN is designed to be called by AI agents. When stdout is not a TTY (piped or called programmatically), output is automatically JSON. Use vrin --describe to get a machine-readable schema of all commands.

# Auto-discovery for agents
vrin --describe

# Programmatic usage (always JSON)
vrin query "What is ACME's revenue?" --json
vrin facts "ACME" --json

Next steps

CLI reference : full command documentation
Query options : response modes, depth levels, model overrides
Knowledge management : async jobs, knowledge graph, tags

Get Started

MCP Server

CLI

Python SDK

TypeScript SDK

Concepts

Guides

Install

Get an API key

Insert knowledge

Query

Stream responses

Upload files

Bulk insert

Multi-turn conversations

For AI agents

Next steps

​Install

​Get an API key

​Insert knowledge

​Query

​Stream responses

​Upload files

​Bulk insert

​Multi-turn conversations

​For AI agents

​Next steps

Install

Get an API key

Insert knowledge

Query

Stream responses

Upload files

Bulk insert

Multi-turn conversations

For AI agents

Next steps