sifter-ai/sifter
defined records, queryable in natural language from Claude, ChatGPT, Gemini, or any MCP client.
Ask AI about sifter-ai/sifter
Powered by Claude Β· Grounded in docs
I know everything about sifter-ai/sifter. Ask me about installation, configuration, usage, or troubleshooting.
0/500
Reviews
Documentation
Sifter
Structure any document. Query it like a database. Build on top via API.
Open-source document intelligence engine β schema-driven extraction, NL query, MCP server, Python and TypeScript SDKs. Self-hostable under MIT.

Why not RAG?
RAG is built for retrieval β find me chunks similar to this query. It breaks on homogeneous collections like invoices, contracts, or receipts where every document looks alike and the question is an aggregation, not a search.

Sifter's approach: extract structured fields once (client, date, total), store them as typed records, query with real filters and aggregations. The answer is exact and reproducible β because it's a database query, not a similarity search.
Quickstart
git clone https://github.com/sifter-ai/sifter
cd sifter/code
cp server/.env.example server/.env.local # set SIFTER_DEFAULT_API_KEY (required)
docker compose up -d
Open http://localhost:3000 β create a sift, upload documents, query results.
Python SDK
pip install sifter-ai
from sifter import Sifter
s = Sifter(api_key="sk-...")
sift = s.create_sift("Invoices", "client name, date, total amount")
sift.upload("./invoices/")
sift.wait()
for record in sift.records():
print(record["extracted_data"])
# {"client": "Acme Corp", "date": "2024-01-15", "total_amount": 1500.0}
TypeScript SDK
npm install @sifter-ai/sdk
import { Sifter } from "@sifter-ai/sdk";
const client = new Sifter({ apiKey: "sk-..." });
const sift = await client.createSift("Invoices", "client, date, total amount");
await sift.upload("./invoices/");
await sift.wait();
const records = await sift.records();
console.log(records);
MCP server (Claude Desktop / Cursor / AI agents)
{
"mcpServers": {
"sifter": {
"command": "uvx",
"args": ["sifter-mcp", "--base-url", "http://localhost:8000"],
"env": { "SIFTER_API_KEY": "sk-dev" }
}
}
}
Then ask Claude: "What's the total unpaid across all invoices from last quarter?"
Want a remote MCP URL without running a local server? β Sifter Cloud
What's included
- Schema-driven extraction β describe what to extract in natural language; schema is inferred automatically and exported as Pydantic / TypeScript types
- NL query β ask questions in plain language; Sifter generates inspectable MongoDB aggregation pipelines
- MCP server β stdio transport, read + write tools, zero custom integration code
- REST API + SDKs β full OpenAPI spec, typed clients for Python and TypeScript
- Webhooks β HMAC-signed HTTP callbacks on every extraction event
- Spec-driven dashboards β short NL spec β auto-generated board (KPI, breakdown, table, time series)
- CLI β
sifter extract,sifter records,sifter siftsfor terminal workflows and CI - Self-hostable β Docker Compose, bring your own MongoDB and LLM API key
Don't want to run infrastructure?
Sifter Cloud is the managed version β no Mongo, no ops, remote MCP endpoint, Google Drive and email ingress. Free tier available.
Docs
Full documentation at docs.sifter.run β quickstart, SDK reference, MCP guide, cookbook, self-hosting.
License
MIT β see LICENSE.
Created by Bruno Fortunato.
