Ship
intelligence.
Docs in. Agent deployed.
Question
Answer
Source
97%+
retrieval accuracy across BEIR benchmarks
<300us
p50 search latency at 1M vectors
5min
to first agent deploy
3
templates ready to use
Available today
Everything an agent needs. Nothing it doesn't.
Five primitives. Zero boilerplate. Your agent ships with RAG, tools, and memory out of the box.
Agent Runtime
ReAct loop with automatic tool dispatch. Define instructions, register tools, call agent.run(). Schift handles the rest.
import { Agent } from '@schift-io/sdk' const agent = new Agent({ name: 'support-bot', instructions: 'Answer from the knowledge base.', tools: [searchDocs], model: 'gpt-4.1-nano', }) const result = await agent.run('How do I reset?')
Built-in RAG
Upload docs, search by meaning, get answers with citations. OCR, chunking, embedding, and reranking — all managed.
import { RAG } from '@schift-io/sdk' const rag = new RAG({ bucket: 'support-docs', topK: 5, }) await rag.upload(['manual.pdf', 'faq.docx']) const results = await rag.search('password reset')
Tool Calling
Register any async function as a tool. Type-safe parameters, automatic validation, error recovery. Works with OpenAI and Anthropic formats.
import type { AgentTool } from '@schift-io/sdk' export const collectLead: AgentTool = { name: 'collect_lead', description: 'Collect visitor contact info', parameters: { type: 'object', properties: { email: { type: 'string' } }, }, handler: async ({ email }) => saveLead(email), }
Any LLM, One Endpoint
GPT, Claude, Gemini — switch models without changing code. OpenAI-compatible routing with automatic fallback.
const agent = new Agent({ model: 'gpt-4.1-nano', // swap to 'claude-sonnet-4-6' // or 'gemini-2.5-flash' // — zero code change needed }) // Automatic fallback if primary model fails const result = await agent.run('Summarize this contract')
Start from a template. Ship faster.
Production-ready agent templates. Pick one, customize, deploy.
Scaffold. Build. Deploy.
Scaffold your agent
npx create-schift — pick a template, enter your API key. You get a working agent project in seconds.
$ npx create-schift@latest Upload your data
Push documents via SDK or dashboard. Schift handles OCR, chunking, and embedding. Your agent can search them instantly.
await rag.upload(['manual.pdf', 'faq.docx']) Deploy to production
npm run dev for local testing. schift deploy when ready. Your agent is live with built-in monitoring and logging.
$ schift deploy Code. Or Cloud.
Write your agent for full control, or use Schift Cloud to skip the infrastructure.
Schift SDK
npx create-schift, connect your data, deploy your agent. Public TypeScript SDK + use-case templates (Schift Cloud API key required).
Schift Cloud
Managed RAG pipeline, embedding, vector search, LLM routing, observability. Zero infrastructure.
Agents for every use case.
Live Demo
Try it yourself
Search Schift docs for pricing, features, and setup. No signup required.
Search Schift docs for pricing, features, integrations, and setup.
Try searching
Schift Public Bucket
Search Korean law. Right now.
1,600+ statutes, precedents, admin rules. No upload needed.
Type a query to see matching laws
2.3x faster than FAISS.
3.3x better tail latency.
Same HNSW algorithm, same machine, same vectors. Schift SQ8 delivers sub-300us p50 with 3.3x tighter p99 than FAISS -- at 4x less memory, with persistence, knowledge graphs, and compaction included.
3.3x better tail latency, 2.3x higher throughput
Schift SQ8 p99 is 502us vs FAISS 1,653us at 1M vectors, using 4x less memory. Unlike pure in-memory libraries, Schift includes disk persistence, WAL crash recovery, knowledge graph search, and live compaction.
74K
vectors/sec projection
4x
memory savings (SQ8)
0
re-embedding needed
Apple Silicon, single-thread search, same machine. HNSW M=32, efConstruction=200, efSearch=50. Full benchmark source available on GitHub.
Millions of vectors.
Zero re-embedding.
Already running OpenAI or Gemini in production? Benchmark your retrieval, inspect a dry-run, and cut over when recovery is proven. Your database stays online.
100%
retrieval on 104K production docs
50
docs to adapt to your domain
78%
storage savings with compression
Expand after migration
Schift DB
Managed vector storage. Retrieval and migration in one runtime.
Schift API
Collections, routing, benchmarks. Control plane for canonical space.
Schift Projection
Migration runtime. Domain-adapted with as few as 50 documents.
Need help migrating?
Our team handles the full migration from your existing database to Schift — schema mapping, data transfer, and verification included.
Pricing
One plan. Whole RAG platform.
Four tiers, usage-based overage when it matters. Annual saves 20%, Wallet adds +30% bonus credits (no BYOK required).
Free
1 GB · 25K search · 100 pages · 10 collections
Starter
5 GB · 200K search · 500 pages · BYOK · unlimited collections
Pro
30 GB · 2M search · 3K pages · BYOK · full overage
Enterprise
PII / SSO / CMEK / SIEM / on-prem / SLA
Overage
search $1/1K · exec $3/1M · storage $0.30/GB · ingest $0.006/page · LLM +10% · web $0.02/query
Deploy your first agent
in 5 minutes.
Free tier included. No credit card required.
Need help getting started?