eqbuilder

Score your AI agent's replies for human-likeness before sending — and check they stick to your approved facts. No account, no API key. 3 free scores, then pay-per-score (~5¢) in USDC on Base via x402 — the buyer wallet needs zero gas, USDC only.

# pip install eqbuilder
from eqbuilder import EqBuilder, WishlistRequired

eq = EqBuilder()
result = eq.free_score(
    "Sounds good — I'll double-check the invoice and get back to you.",
    delay_seconds=4.2,
    profile="analytical_executive",
)
print(result["eq_score_percentage"], result.get("suggested_prompt_addition"))

Free trial note — 3rd score: The final free score is gated behind a one-time wishlist step. Before calling free_score for the third time, POST your feature wish:

import requests
requests.post(
    "https://eqbuilder.dev/api/wishlist",
    json={"need": "a profile for customer-support bots", "audience": "bot"},
)

No free round is consumed until you do. The SDK raises WishlistRequired (a subclass of EqBuilderError) if you forget, with step-by-step instructions in the exception message. (Or use eq.wishlist("...") — or let auto_score handle it, below.)

Set and forget (one standing call)

# pip install "eqbuilder[payments]"
eq = EqBuilder(wallet_key="0x<private key of a wallet holding USDC on Base>")
result = eq.auto_score(
    "Sounds good — I'll double-check the invoice and get back to you.",
    delay_seconds=4.2,
    profile="analytical_executive",
    wishlist_need="a profile for customer-support bots",  # unlocks the final free round automatically
)
print(result["paid"])  # False while free scores last, True once it graduates to x402

auto_score uses your free trial while it lasts, then transparently retries the same input through the paid x402 path on 429 free_trial_exhausted. Without a wallet_key it raises PaymentRequired at that point instead. Free and paid results have slightly different shapes; the added "paid" key tells you which path ran. If a paid call times out, do not blindly retry — the charge may have settled; reconcile via GET /api/wallet/{address}/statement?auth_tx_hash=... first.

LangChain (one line)

# pip install "eqbuilder[langchain]"
from eqbuilder.langchain_tool import get_langchain_tools

tools = get_langchain_tools()  # add wallet_key="0x..." to keep scoring after the free trial

CrewAI

# pip install "eqbuilder[crewai]"
from eqbuilder.crewai_tool import HumanLikenessScoreTool

agent = Agent(role="support", tools=[HumanLikenessScoreTool()], ...)

Everything at once: pip install "eqbuilder[all]" (payments + LangChain + CrewAI).

Paid scoring (after the 3 free scores)

# pip install "eqbuilder[payments]"
eq = EqBuilder(wallet_key="0x<private key of a wallet holding USDC on Base>")
result = eq.score("...", delay_seconds=4.2, profile="analytical_executive")
deep   = eq.score("...", delay_seconds=4.2, profile="analytical_executive", tier="deep")

Payment is a signed, gasless USDC transfer authorization (EIP-3009) sent in the X-PAYMENT header — the platform's facilitator settles it on-chain. A malformed request is rejected before any money moves.

Script adherence (paid)

check = eq.script_check(
    reply_text="The plan is $49/mo, see example.com/pricing",
    approved_facts=["Plan price is $29/mo", "Docs: https://docs.example.com"],
)
# flags the invented $49 price and the off-script URL

Improvement loop

def rewrite(text, suggestion):
    return my_llm(f"Rewrite this reply. {suggestion}\n\n{text}")

final = eq.improve("...", 4.2, "analytical_executive", rewrite, max_rounds=3)

• 28 personality profiles: eq.profiles()
• Pricing: eq.pricing()
• Full API & MCP endpoint: https://eqbuilder.dev/integrate