Skip to content

The Bee Platform

One progressive system, seven tiers, real workflows.

Bee combines model access, workspace capabilities, retrieval, API compatibility, and deployment controls in one progressive system that scales from public access to sovereign deployment. The platform is governed: every shipped capability lands behind the eval harness, and every public claim links to verifiable evidence at /trust.

Community Evolution Protocol

When one Bee tier evolves, every Bee tier benefits.

Validated capabilities propagate through Bee’s governed-release pipeline. Every promoted adapter clears the eval harness before it serves a request, and the per-adapter validation record is published at /trust. Per-tier model cards live at huggingface.co/cuilabs; specific weights are governed (gated access via API; sovereign deployment via Enclave). The propagation loop activates per-tenant on the higher tiers, not on Bee Cell base.

Model cardshuggingface.co/cuilabs
  1. 1

    Train

    Domain capability is trained against governed data sources.

  2. 2

    Validate

    Eval harness gates the artefact; it must clear the score gate to ship.

  3. 3

    Publish

    Released to cuilabs/bee-hive-* with a published validation record.

  4. 4

    Deploy

    Tier upgrades land in production routing tier by tier as each clears review.

Training infrastructure

Multi-cloud training infrastructure.

Bee’s training pipeline runs across multiple cloud providers so domain capability lands without single-vendor lock-in. Each released artefact carries a published validation record. Specific compute placement for any individual deployment is contractual via the Enclave deployment manifest.

What customers see

  • A single OpenAI-compatible endpoint at /bee/chat/completions.
  • Per-tier capability gated by plan or contract.
  • Public release notes at /changelog; live engine status at /status.
  • Deployment options spanning shared cloud, private cloud, regulated, and sovereign — see the Intelligence Ladder.

In every editor you already use

An API key is the only integration step.

Bee speaks the OpenAI Chat Completions wire format. Anywhere you’d paste an OpenAI API key, paste a Bee API key instead — and switch the base URL. The Bee Intelligence Engineadds inline chat and domain-aware completions on top, but you don’t need it to use Bee in your editor.

Install for VS Code Setup guide

// universal config — works in Cursor, Windsurf, Continue, Zed

base_url: "https://bee.cuilabs.io/bee"
api_key: "$BEE_API_KEY"
model: "bee-comb"
  • VS CodeNative

    Native extension: Bee Intelligence Engine.

  • CursorOpenAI-compatible

    Settings → Models → Override OpenAI base URL.

  • WindsurfOpenAI-compatible

    Custom provider — paste Bee base URL and API key.

  • Continue.devOpenAI-compatible

    Add Bee as a provider in `~/.continue/config.json`.

  • ZedOpenAI-compatible

    OpenAI-compatible LLM provider in the assistant config.

  • JetBrains AI AssistantOpenAI-compatible

    Connect via OpenAI-compatible custom endpoint.

  • AiderCLI

    Run `aider --openai-api-base ... --openai-api-key ...`

  • Anything elseOpenAI-compatible

    If it accepts an OpenAI API key, it works with Bee.

Build with the platform

Start public. Scale sovereign.

Begin with Bee Cell, scale through the Intelligence Ladder, and move into high-assurance deployment when your requirements demand stronger governance, security, and control.

View Intelligence Ladder Talk to Sales