bee-sdk 0.3.0

Official Python client + MCP server for the Bee Intelligence Engine — domain-specialized LoRA-routed LLM by CUI Labs.

bee-sdk

Official Python client + MCP server for the Bee Intelligence Engine — a domain-specialized LLM by CUI Labs routing per-domain LoRA adapters over a verified open-weight base.

SDK version: 0.3.0 — adds per-call/BEE_MODEL model-tier selection (bee-cell … bee-swarm; access follows your key's plan) and MCP tool annotations.

Includes a hosted Model Context Protocol server: pip install bee-sdk then run bee-mcp (stdio) to expose Bee's 11 domain tools to Claude Desktop, Cursor, VS Code, Zed, and Windsurf. See bee.cuilabs.io/docs/mcp.

Status: functional sync + async client (stdlib + optional httpx). The SDK targets the Bee /chat/completions API contract on production via the public gateway https://bee.cuilabs.io/bee — this is the default and it is where API-key auth, plan / per-tier allowance enforcement and usage metering happen. Do not point BEE_API_URL at the raw Modal app URL: that bypasses billing and a bee_sk_ key is rejected there (the backend only trusts Supabase JWTs / the static BEE_API_KEYS env, not customer-issued keys). Override BEE_API_URL only for a self-hosted Bee Enclave or staging.

Install

Install from PyPI (canonical):

pip install bee-sdk          # sync client (stdlib only — zero deps)
pip install bee-sdk[async]   # async client (adds httpx)

Install + quickstart on the marketing site: bee.cuilabs.io/docs/sdks.

Quick start

from bee_sdk import Bee

bee = Bee()  # reads BEE_API_URL + BEE_API_KEY from env
print(bee.chat("Explain Shor's algorithm at NISQ depth", domain="quantum"))

Streaming

for chunk in bee.chat_stream("Write a Rust fibonacci function", domain="programming"):
    print(chunk, end="", flush=True)

Async

import asyncio
from bee_sdk import AsyncBee

async def main():
    client = AsyncBee()
    text = await client.chat("Audit this contract for re-entrancy", domain="blockchain")
    print(text)

asyncio.run(main())

Multi-turn

from bee_sdk import Bee, ChatMessage

bee = Bee()
resp = bee.chat_messages(
    [
        ChatMessage(role="system", content="You are a senior security auditor."),
        ChatMessage(role="user", content="Review this nginx config for hardening gaps:\n\n..."),
    ],
    domain="cybersecurity",
    max_tokens=1024,
)
print(resp.content)
print(resp.usage, resp.interaction_id)

Feedback loop

resp = bee.chat_messages([...], domain="ai")
if user_likes_answer:
    bee.feedback(resp.interaction_id, rating="up")

Domains

The domain= parameter selects which LoRA adapter Bee routes through. Tier-1 domains:

domain	what it's tuned for
general	balanced, no specialization
programming	code generation, refactoring, debugging
ai	ML/AI papers, training, evaluation
cybersecurity	threat modelling, audits, defensive analysis
quantum	NISQ-aware quantum computing, Qiskit
fintech	payments, risk, compliance
blockchain	smart contract audits, protocol design
infrastructure	systems, networking, devops
research	literature review, paper critique
business	strategy, GTM, ops

Adapters live at cuilabs/bee-cell on branches <domain>-<UTC-timestamp>.

Environment variables

var	purpose
BEE_API_URL	Endpoint override. Defaults to the public gateway https://bee.cuilabs.io/bee (where auth + billing + metering run). Set this only for a self-hosted Bee Enclave or a staging environment — never the raw Modal app URL (that bypasses billing and rejects bee_sk_ keys).
BEE_API_KEY	Bearer token (also accepts BEE_PORTAL_API_KEY)

Errors

from bee_sdk import BeeAPIError, RateLimitError, BeeError

try:
    bee.chat("...", domain="quantum")
except RateLimitError as e:        # 429 after retries
    ...
except BeeAPIError as e:           # other HTTP errors
    print(e.status, e.body)
except BeeError:                   # network / timeout
    ...

The sync client retries 429/5xx with exponential backoff (max 4 attempts).

Versioning

bee-sdk follows the Bee API surface in bee/server.py. Breaking API changes bump the minor version pre-1.0; the SDK is currently 0.1.1 and the API is v1.

License

Apache-2.0 © 2026 CUI Labs (Pte.) Ltd.