LangChain tools for Cerebrus Pulse crypto intelligence API
Project description
LangChain Cerebrus Pulse
LangChain tools for Cerebrus Pulse — real-time crypto intelligence for AI agents.
Install
pip install langchain-cerebrus-pulse
Quick Start
from langchain_cerebrus_pulse import (
CerebrusPulseTool,
CerebrusSentimentTool,
CerebrusFundingTool,
CerebrusBundleTool,
CerebrusListCoinsTool,
CerebrusScreenerTool,
CerebrusOITool,
CerebrusSpreadTool,
CerebrusCorrelationTool,
)
# Add to your agent's tools
tools = [
CerebrusListCoinsTool(), # Free
CerebrusPulseTool(), # $0.02/query
CerebrusSentimentTool(), # $0.01/query
CerebrusFundingTool(), # $0.01/query
CerebrusBundleTool(), # $0.04/query
CerebrusScreenerTool(), # $0.04/query — scan all coins
CerebrusOITool(), # $0.01/query
CerebrusSpreadTool(), # $0.008/query
CerebrusCorrelationTool(), # $0.03/query
]
With a LangChain Agent
from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_cerebrus_pulse import CerebrusPulseTool, CerebrusBundleTool, CerebrusListCoinsTool
llm = ChatOpenAI(model="gpt-4o")
tools = [CerebrusListCoinsTool(), CerebrusPulseTool(), CerebrusBundleTool()]
prompt = ChatPromptTemplate.from_messages([
("system", "You are a crypto analyst with access to real-time Hyperliquid data via Cerebrus Pulse."),
("human", "{input}"),
("placeholder", "{agent_scratchpad}"),
])
agent = create_tool_calling_agent(llm, tools, prompt)
executor = AgentExecutor(agent=agent, tools=tools)
result = executor.invoke({"input": "What's the technical outlook for BTC and ETH?"})
print(result["output"])
Available Tools
| Tool | Cost | Description |
|---|---|---|
CerebrusListCoinsTool |
Free | List 30+ available Hyperliquid perpetuals |
CerebrusPulseTool |
$0.02 | Technical analysis (RSI, EMAs, Bollinger, trend, regime, confluence) |
CerebrusSentimentTool |
$0.01 | Market sentiment (fear/greed, momentum, funding bias) |
CerebrusFundingTool |
$0.01 | Funding rates with historical data |
CerebrusBundleTool |
$0.04 | All data combined (20% discount) |
CerebrusScreenerTool |
$0.04 | Scan 30+ coins: signals, trends, vol regime, confluence |
CerebrusOITool |
$0.01 | Open interest: delta, percentile, trend, divergence |
CerebrusSpreadTool |
$0.008 | Spread: slippage estimates at various sizes, liquidity score |
CerebrusCorrelationTool |
$0.03 | BTC-alt correlation matrix with regime classification |
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
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file langchain_cerebrus_pulse-0.2.0.tar.gz.
File metadata
- Download URL: langchain_cerebrus_pulse-0.2.0.tar.gz
- Upload date:
- Size: 4.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
42686a175243251fd35e1e5fb12562783d55feff05e13816f69fe7eb5bc766b7
|
|
| MD5 |
690a8f90ee23a143cc5cae852ac8f29a
|
|
| BLAKE2b-256 |
dc29661129d885f274497f301de2c457a30153c183d2c8673fb4e35ae084eb18
|
File details
Details for the file langchain_cerebrus_pulse-0.2.0-py3-none-any.whl.
File metadata
- Download URL: langchain_cerebrus_pulse-0.2.0-py3-none-any.whl
- Upload date:
- Size: 5.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
26f206a7623041f11c8c52c2553bcad83fc42a892c0d35a831c0b0de163335c7
|
|
| MD5 |
ef50f662c9149403def8d616192df743
|
|
| BLAKE2b-256 |
f5716fc4e162568a3e1d6fd446df78254db6992642cd5ab48d95b2fff9620f2f
|