praisonaiagents
The lightweight core of PraisonAI: a Python SDK for AI agents, tools, memory and multi-agent workflows. Importing it loads no LLM library; dependencies load only when a feature needs them.
pip install praisonaiagents
export OPENAI_API_KEY="your-api-key" # or use a local model, below
An agent in three lines
from praisonaiagents import Agent
agent = Agent(instructions="You are a helpful assistant")
print(agent.start("Write a haiku about the sea"))
Give it a tool
Any typed Python function with a docstring is a tool.
from praisonaiagents import Agent
def get_weather(city: str) -> str:
"""Return the current weather for a city."""
return f"It is sunny and 22°C in {city}."
agent = Agent(instructions="Answer weather questions", tools=[get_weather])
print(agent.start("What's the weather in Paris?"))
Other models
Pass model=, for example model="gpt-4o-mini", model="anthropic/claude-sonnet-4-5" or a local model="ollama/llama3.2" (no API key). provider/model names are routed through litellm: pip install "praisonaiagents[llm]".
Learn more
- Documentation: Agents · Tools · Memory · Workflows
pip install praisonaiadds the terminal CLI, YAML agents, bots and the UI on top of this package.- Source and issues · MIT licence
Metadata
Release files for praisonaiagents 1.8.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| praisonaiagents-1.8.0.tar.gz | 2.6 MB | Without provenance | Details for praisonaiagents-1.8.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| praisonaiagents-1.8.0-py3-none-any.whl | Python 3 | none | any | Details for praisonaiagents-1.8.0-py3-none-any.whl |
Total release size: 5.6 MB
Release files / praisonaiagents-1.8.0.tar.gz
| Download URL | praisonaiagents-1.8.0.tar.gz |
|---|---|
| Size | 2.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
62ed63c9e2ca77ef6065b1718bbc2177e1a5c615dcf3b8126fa42486cec5081e
|
|
BLAKE2b-256 checksum How to use checksums |
21331168dd6c7a4609f6d9430908af05841ab5278f79cb7c0ee5e16dd95f1b66
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / praisonaiagents-1.8.0-py3-none-any.whl
| Download URL | praisonaiagents-1.8.0-py3-none-any.whl |
|---|---|
| Size | 3.0 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b1f424317428f56c09002399a6739d138d8bb569747cfa6235fa413d5e6c901c
|
|
BLAKE2b-256 checksum How to use checksums |
8fcfb2aa4cd3ca034783665cd88364cf7338915ead549856fbbde29a18b35421
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for praisonaiagents 1.8.0
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.