About incredlabs
Rust-native data infrastructure for the AI era
Modern applications are increasingly built around models, embeddings, and agents — but the data layer most teams reach for was designed for a different world. Relational databases assume an application server translating objects into SQL; vector databases assume a fixed similarity-search API. We build the databases, memory stores, and data platforms that AI-native software actually needs: fast, embeddable, and open. incredlabs was formerly known as Skelf Research.
What we build
ORMDB
The database that speaks ORM natively
A relational database engine that understands your entities, relations, and constraints natively — no N+1 queries, no impedance mismatch. Fetch entire object graphs in a single round-trip.
Liath
The SQLite for AI agents
Programmable memory that agents query with sandboxed Lua. Instead of a fixed vector-search API, agents write their own retrieval, ranking, and filtering logic — safely.
More components of the platform are in active development. Browse the full product catalog or read the FAQ for how the pieces fit together.
Who it's for
incredlabs is built for the engineers shipping AI-native software: backend and full-stack developers
who want the database itself to speak ORM, and AI engineers and agent builders who have outgrown a
one-line semantic_search()
call and want programmable, sandboxed memory. If the data layer is fighting you, that's the problem
we exist to solve.
Our principles
Rust all the way down
Memory safety without a garbage collector and predictable performance, from embedded libraries to distributed servers.
Open source, no lock-in
MIT-licensed and developed in the open at github.com/incredlabs. Run locally, embed it, or deploy anywhere. Your data stays yours.
Built for the AI era
Vector search, embeddings, and agent memory are first-class primitives — not bolted on with extra services.
Get in touch
Questions, partnerships, or feedback? Email contact@incredlabs.com, message us, or open an issue on GitHub.