░█████╗░███████╗██████╗░███████╗██████╗░██████╗░██╗░░░██╗░██████╗
██╔══██╗██╔════╝██╔══██╗██╔════╝██╔══██╗██╔══██╗██║░░░██║██╔════╝
██║░░╚═╝█████╗░░██████╔╝█████╗░░██████╦╝██████╔╝██║░░░██║╚█████╗░
██║░░██╗██╔══╝░░██╔══██╗██╔══╝░░██╔══██╗██╔══██╗██║░░░██║░╚═══██╗
╚█████╔╝███████╗██║░░██║███████╗██████╦╝██║░░██║╚██████╔╝██████╔╝
░╚════╝░╚══════╝╚═╝░░╚═╝╚══════╝╚═════╝░╚═╝░░╚═╝░╚═════╝░╚═════╝░
─────╮ ╭──╮ ╭──╮ ╭──╮ ╭──╮ ╭─────
│ │ │ │ │ │ │ │ │ │
─────╯────╯ ╰─────────╯ ╰────╯ ╰─────────╯ ╰────╯─────
██████╗░██╗░░░██╗██╗░░░░░░██████╗███████╗
██╔══██╗██║░░░██║██║░░░░░██╔════╝██╔════╝
██████╔╝██║░░░██║██║░░░░░╚█████╗░█████╗░░
██╔═══╝░██║░░░██║██║░░░░░░╚═══██╗██╔══╝░░
██║░░░░░╚██████╔╝███████╗██████╔╝███████╗
╚═╝░░░░░░╚═════╝░╚══════╝╚═════╝░╚══════╝
crypto intelligence for AI agents · x402 micropayments
LangChain Cerebrus Pulse
LangChain tools for Cerebrus Pulse — real-time crypto intelligence for AI agents. 50+ Hyperliquid perpetuals, paid per call in USDC over x402.
Install
pip install langchain-cerebrus-pulse # tools; paid ones report the price instead of paying
pip install "langchain-cerebrus-pulse[pay]" # + automatic payment in USDC on Base
pip install "langchain-cerebrus-pulse[svm]" # + automatic payment in USDC on Solana too
Requires langchain-core 1.x and the cerebrus-pulse SDK 0.4.
Quick Start
Build one CerebrusPulse client and hand it to every tool. With a wallet key it pays for paid tools automatically, and all tools share its spend limits.
import os
from cerebrus_pulse import CerebrusPulse
from langchain_cerebrus_pulse import (
CerebrusListCoinsTool,
CerebrusPulseTool,
CerebrusSentimentTool,
CerebrusFundingTool,
CerebrusBundleTool,
CerebrusScreenerTool,
CerebrusOITool,
CerebrusSpreadTool,
CerebrusCorrelationTool,
CerebrusLiquidationsTool,
CerebrusStressTool,
CerebrusCexDexTool,
CerebrusBasisTool,
CerebrusDepegTool,
)
# A dedicated, low-balance Base wallet holding a little USDC. Omit wallet_key
# and paid tools return the API's price and payee instead of data.
client = CerebrusPulse(
wallet_key=os.environ["CEREBRUS_WALLET_KEY"],
max_payment_usd="0.10", # most one call may cost
max_spend_usd="1.00", # most this client may spend in total
)
tools = [
tool(client=client)
for tool in (
CerebrusListCoinsTool, CerebrusPulseTool, CerebrusScreenerTool,
CerebrusLiquidationsTool, CerebrusStressTool, CerebrusCexDexTool,
CerebrusBasisTool, CerebrusDepegTool, CerebrusSentimentTool,
CerebrusFundingTool, CerebrusOITool, CerebrusSpreadTool,
CerebrusCorrelationTool, CerebrusBundleTool,
)
]
The spend limits also read CEREBRUS_MAX_PAYMENT_USD, CEREBRUS_MAX_SPEND_USD and CEREBRUS_ALLOWED_PAYTO; payments only go to the API's published payee. See the SDK README for Solana and the full list.
With a LangChain Agent
from langchain.agents import create_agent
agent = create_agent(
"openai:gpt-4o", # any chat model that supports tool calling
tools=tools,
system_prompt="You are a crypto analyst with access to real-time Hyperliquid data via Cerebrus Pulse.",
)
result = agent.invoke({
"messages": [
{"role": "user", "content": "Where are the BTC liquidation clusters and what's the cascade risk?"}
]
})
print(result["messages"][-1].content)
print(f"Spent: ${client.spent_usd}")
When a paid tool cannot pay, it returns JSON the model can read: {"error": ..., "payment_required": true, "price_usd": "0.03", "payment_terms": [...]}. A refusal by the spend limits adds a reason, and nothing is signed.
Available Tools (14)
Prices are indicative, per call, in USDC, as the API published them on 2026-09-24. The API sets the price: its 402 terms say what is charged, and the client's max_payment_usd caps what is paid.
| Tool | Price | Description |
|---|---|---|
CerebrusListCoinsTool |
Free | List 50+ available Hyperliquid perpetuals |
CerebrusPulseTool |
$0.025 | Technical analysis (RSI, EMAs, Bollinger, trend, regime, confluence) |
CerebrusScreenerTool |
$0.06 | Scan 50+ coins: signals, trends, vol regime, confluence |
CerebrusLiquidationsTool |
$0.03 | Liquidation heatmap by leverage tier with cascade risk |
CerebrusStressTool |
$0.02 | Cross-chain market stress index (8 chains) |
CerebrusCexDexTool |
$0.02 | CEX-DEX price divergence (Coinbase vs Chainlink/Uniswap) |
CerebrusBasisTool |
$0.02 | Chainlink basis: HL perp oracle vs Chainlink spot |
CerebrusDepegTool |
$0.01 | USDC collateral health via Chainlink oracle |
CerebrusSentimentTool |
$0.01 | Market sentiment as a bucketed label (very_bearish … very_bullish) |
CerebrusFundingTool |
$0.01 | Funding rate: current, average, min, max, annualized |
CerebrusOITool |
$0.015 | Open interest: delta, percentile, trend, divergence |
CerebrusSpreadTool |
$0.015 | Spread: slippage estimates at various sizes, liquidity score |
CerebrusCorrelationTool |
$0.05 | BTC-alt correlation matrix with regime classification |
CerebrusBundleTool |
$0.05 | Pulse, sentiment and funding in one call |
Links
Disclaimer
Cerebrus Pulse provides market data and technical indicators for informational purposes only. Nothing provided by these tools or the underlying API constitutes financial advice, investment advice, or trading advice. AI-generated analysis, signals, and sentiment labels are algorithmic outputs — not recommendations to buy, sell, or hold any asset. Cryptocurrency trading involves substantial risk of loss. You are solely responsible for your own trading decisions.
License
MIT
Release files for langchain-cerebrus-pulse 0.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| langchain_cerebrus_pulse-0.4.0.tar.gz | 12.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langchain_cerebrus_pulse-0.4.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 20.6 kB
Release files / langchain_cerebrus_pulse-0.4.0.tar.gz
| Download URL | langchain_cerebrus_pulse-0.4.0.tar.gz |
|---|---|
| Size | 12.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
42bf64944038a5b7542512254aaf2711fdb4ac66db649145ea7579be9557a2c6
|
|
BLAKE2b-256 checksum How to use checksums |
00050cfc88502c38ae1564fd9b6c05e258fb498113de778fa3780a21939bee49
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 26, 2026.
Transparency logRelease files / langchain_cerebrus_pulse-0.4.0-py3-none-any.whl
| Download URL | langchain_cerebrus_pulse-0.4.0-py3-none-any.whl |
|---|---|
| Size | 8.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f8fce479daa14539b959f590a6af1df450a1eb1da4904c882b6c14b8db539cb6
|
|
BLAKE2b-256 checksum How to use checksums |
cafc4996985bbe87cf4ceb5fcf0e201cdc03de17d8c7ddcbf964f0dc6033695e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 26, 2026.
Transparency log