CrewAI LLM integration for JarvisClaw AI API (x402 USDC payments supported)
Project description
crewai-jarvisclaw
CrewAI integration for JarvisClaw AI API — 40+ models, pay with USDC.
Install
pip install crewai-jarvisclaw
Usage
With API Key
from crewai import Agent, Task, Crew
from crewai_jarvisclaw import JarvisClawLLM
llm = JarvisClawLLM(model="gpt-5.4", api_key="sk-...")
researcher = Agent(
role="Senior Researcher",
goal="Find cutting-edge AI developments",
backstory="Expert at finding and synthesizing information",
llm=llm,
)
task = Task(
description="Research the latest advances in AI agents",
expected_output="A summary of top 3 developments",
agent=researcher,
)
crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()
With x402 Wallet Payment (no account needed)
from crewai_jarvisclaw import JarvisClawLLM
# Pay per request with USDC — no signup required
llm = JarvisClawLLM(
model="anthropic/claude-sonnet-4.6",
wallet_private_key="0x...",
)
Alternative: Direct LiteLLM Config (no extra package)
Since CrewAI uses LiteLLM, you can also configure it directly:
from crewai import LLM
llm = LLM(
model="openai/gpt-5.4",
base_url="https://api.jarvisclaw.ai/v1",
api_key="sk-...",
)
The crewai-jarvisclaw package adds x402 wallet payment support and convenience methods on top.
Discover Models
from crewai_jarvisclaw import JarvisClawLLM
# No auth required
models = JarvisClawLLM.list_models()
free = JarvisClawLLM.free_models()
Project details
Release history Release notifications | RSS feed
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 crewai_jarvisclaw-0.1.0.tar.gz.
File metadata
- Download URL: crewai_jarvisclaw-0.1.0.tar.gz
- Upload date:
- Size: 2.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
57c61dc4b74a1468878a41f7bb802dcf7971bc33c920d244c5b0730303def9ea
|
|
| MD5 |
cbe34d0ab753f04dcf204f5d3683fcac
|
|
| BLAKE2b-256 |
5c23842e4df401712414f795a0be8411ad10ec77a65703a49f11797a99e2996c
|
File details
Details for the file crewai_jarvisclaw-0.1.0-py3-none-any.whl.
File metadata
- Download URL: crewai_jarvisclaw-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9dc74e91f98537b043bcc7ccfec119cf432c03678bc827fa40362c5454bd77c2
|
|
| MD5 |
940305828c5e07e3d484ae9c6f64b74a
|
|
| BLAKE2b-256 |
b145d30ade71b06509f8d470cc4daf82cb0a971317649d45b706e72e29962431
|