BeevR Labs

We open-source the hard parts.

Two of our engineering bets, in public. Same people, same standards as the work we ship for clients — only with the source open and the tests visible.

01

Nebula

Private AI for your knowledge — running entirely in your browser.

A local-first knowledge tool that runs retrieval-augmented generation over a real entity graph (GraphRAG), with on-device embeddings and an in-browser LLM. No server, no account, no install — nothing leaves the tab. Built for confidential, data-sensitive work where “just send it to the cloud” was never an option.

Privacy-preserving AILocal-first / on-device LLMWebGPU + WASMGraphRAGZero-install
430+ tests · live demo, no signup
02

Kite

An agent framework that treats the LLM as untrusted.

Production scaffolding for AI agents — safety kernels, circuit breakers, and hard boundaries drawn around a model you assume will misbehave. The difference between a demo that works once and an agent you can put in front of real users.

AI agentsAgentic systemsLLM safety & guardrailsProduction reliabilityOpen-source infra
Featured on Product Hunt

This is the engineering we do for ourselves. It’s also the engineering we do for you.

Book a scoping call →