Skip to main content

🌌 Nebulous AI

Create AI agents for your own use case quickly.

AI agents are the future of automation and LLMs. Nebulous helps you create agents:

  • For your own business use case
  • In just 5 lines of code
  • By using the best agent algorithms

It's easy to learn and get started with. Ready to create your first agent in just 5 lines of code? Learn how.

1. Install Nebulous AI:

pip install nebulousai

2. Create an agent:

from nebulousai.core.planning import Planner
from nebulousai.core.brain import Brain
from nebulousai.agent import PlannerAgent
from nebulousai.all_tools import searchWikipediaTool

brain = Brain(brain_system_prompt="Answer questions by using Wikipedia as a source.")
planner = Planner(agent_goal="find obama's hobbies")

agent = PlannerAgent(name="wiki_agent",
              brain=brain,
              planner=planner)

agent.add_tool(searchWikipediaTool)

3. Let the agent plan a task and act on it:

result = agent.act()

>> {'tool_name': 'Wikipedia Search', 'arguments': {'search_term': 'Barack Obama'}}
Performed 'search_wikipedia'.
>> {'tool_name': 'Reason', 'arguments': {'input_text': 'What hobbies does Barack Obama enjoy?'}}
Performed 'reason'.

>> Result: Some of Barack Obama's favorite hobbies include playing basketball, reading, writing, and spending time outdoors. He is also known to be a fan of music and enjoys playing the guitar. Additionally, he has been seen golfing and has a passion for cooking and trying new foods.

Metadata

Release files for nebulousai 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for nebulousai 0.1.1
File Size Uploaded Provenance Actions
nebulousai-0.1.1.tar.gz 10.5 kB Without provenance Details for nebulousai-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for nebulousai 0.1.1
File Interpreter ABI Platform Actions
nebulousai-0.1.1-py3-none-any.whl Python 3 none any Details for nebulousai-0.1.1-py3-none-any.whl

Total release size: 23.9 kB

Release files / nebulousai-0.1.1.tar.gz

Download URL nebulousai-0.1.1.tar.gz
Size 10.5 kB
Tags Source
SHA-256 checksum
How to use checksums
8dced89a8c07cf8774f034fc1856429e51d9b0690a947c748140e3d96d6c179d
BLAKE2b-256 checksum
How to use checksums
9d1cfd4b6726bde1b2a89890e7171da77be3566350beb4949a23b31a878e5649
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.0 CPython/3.10.9

Release files / nebulousai-0.1.1-py3-none-any.whl

Download URL nebulousai-0.1.1-py3-none-any.whl
Size 13.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ed1523509ba8263c9efc67bb327c4ad64474502754f3f989995d88c341ea2873
BLAKE2b-256 checksum
How to use checksums
0163eacc2c96209995bbad75caa832dbd7d1d807efb0eeca01d4cce23ae26ba5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/5.1.0 CPython/3.10.9

Security for nebulousai 0.1.1

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page