Hybrid Deployment

Your vectors, your infrastructure. Our processing.

Keep your data on your own infrastructure while leveraging our advanced code intelligence. Code passes through for processing but is never stored.

Ephemeral processing DPA included Usage-based pricing
How It Works

Simple architecture, maximum control.

You run the collector and vector database. We handle the intelligent processing.

Your Infrastructure

Runs on your servers

Collector (open source)
Qdrant (vectors)
Your code repos

RepoEngine Cloud

Managed by us

AST parsing
Embedding generation
Code intelligence
1

Collector scans

Your collector reads code from your repos

2

API processes

Code sent to our API, processed in memory

3

Vectors returned

Only embeddings returned, code discarded

4

Store locally

Vectors stored in your Qdrant instance

Hybrid Pricing

Usage-based pricing. Pay for what you process.

Monthly quotas for chunks processed and queries. Upgrade anytime as your codebase grows.

Starter

Small teams, single repo

$199 / month
Chunks/month 10,000
Queries/month 1,000
Overage (chunks) $0.02
Overage (queries) $0.05
  • Open source collector
  • API access
  • Email support
Popular

Pro

Growing teams, multiple repos

$499 / month
Chunks/month 50,000
Queries/month 5,000
Overage (chunks) $0.015
Overage (queries) $0.04
  • Everything in Starter
  • Priority API access
  • Slack support

Business

Large teams, org-wide

$1,499 / month
Chunks/month 200,000
Queries/month 20,000
Overage (chunks) $0.01
Overage (queries) $0.03
  • Everything in Pro
  • DPA included
  • Dedicated support

Enterprise

Custom scale, custom needs

Custom
Chunks/month 1M+
Queries/month 100K+
Overage (chunks) Negotiated
Overage (queries) Negotiated
  • Everything in Business
  • Custom SLA
  • Security review
Contact Sales

What's a chunk?

A chunk is a semantic unit of code—typically a function, class, or logical block. Our AST-based parser intelligently splits your code so each chunk maintains context and meaning. A typical 10,000 line codebase might have 500-1,000 chunks.

What's Included

Everything you need for secure deployment.

Open Source Collector

Python package you install on your infrastructure. Scan repos, send to API, store vectors locally. Fully auditable.

pip install repoengine-collector

Processing API

Send code chunks, receive vectors. AST parsing, semantic chunking, embedding generation—all handled by our API.

POST /api/v1/process/

Query Embedding

Convert search queries to vectors for semantic search against your local Qdrant instance.

POST /api/v1/embed/query/

Usage Dashboard

Track chunks processed, queries made, and quota usage. Real-time visibility into your consumption.

Legal Documentation

DPA, Terms of Service, Privacy Policy, and Security Whitepaper. Business tier and above.

Support

Email support for Starter. Slack channel for Pro. Dedicated support for Business and Enterprise.

FAQ

Common questions about hybrid deployment.

Is my code ever stored on your servers?

No. Code is processed in memory and immediately discarded after generating embeddings. We never write your source code to disk, database, or any persistent storage. Only the vector embeddings are returned to your collector, which stores them in your own Qdrant instance.

What infrastructure do I need to run?

You need to run two things: (1) the RepoEngine Collector (a Python package) and (2) a Qdrant instance for vector storage. Both can run on a single server, in Kubernetes, or as managed services. Qdrant Cloud is a good option if you don't want to self-host.

How do chunks map to my codebase size?

As a rough estimate: 1,000 lines of code = ~50-100 chunks. A medium-sized monorepo (100K lines) might have 5,000-10,000 chunks. The Pro tier (50K chunks/month) handles most growing teams. Re-indexing counts as new chunks, so plan accordingly if you re-index frequently.

Can I audit what data is sent to your API?

Yes. The collector is open source—you can inspect exactly what it sends. You can also enable debug logging to see every API request. For Business and Enterprise tiers, we provide detailed API audit logs.

What's the difference between hybrid and your cloud offering?

With our cloud offering, we handle everything—indexing, storage, and the web interface. With hybrid, you run the collector and vector database yourself, and only use our API for processing. Hybrid gives you more control over your data but requires more setup.

Do you offer a fully self-hosted option?

No. Our indexing algorithms are proprietary and we don't distribute them. The hybrid model is our solution for organizations that need data residency—your code and vectors stay on your infrastructure while leveraging our processing capabilities via API.

Ready for hybrid deployment?

Get started with a pilot or talk to our team about your specific requirements.

Contact Sales