agentxai
A lightweight, but effective autonomous agent framework powered by X.AI's Grok model.
Features
- AgentX: An autonomous agent that can execute complex missions using provided tools
tools: List of callable functions the agent can use to complete its mission- can be another agent, assuming the agent lives in a function
mission: String describing the goal or task to accomplishexit_function: Optional callback function executed upon mission completion- default is a success bool
system_prompt: Customizable prompt to guide agent behavior (default: autonomous goal-focused agent)model: AI model selection (default: "grok-beta")enable_logging: Toggle detailed logging (default: False)max_steps: Maximum execution steps before termination (default: 10)
- XAI: A robust client for interacting with X.AI's Grok model and other supported AI models
- Model Selection: Choose from three AI models to power your agents
grok-beta: X.AI's Grok modelgpt-4o: OpenAI's GPT-4 optimized for performancegpt-4o-mini: A lightweight version of GPT-4 optimized for minimal resource usage
- Cost tracking and token usage monitoring
- Automatic retries and error handling
- JSON response validation
- Configurable logging
Model Selection
AgentXAI supports three AI models, each with different capabilities and cost structures. You can select the desired model when initializing AgentX or XAI.
Available Models
-
grok-beta
- Provider: X.AI
- Cost:
- Input Tokens: $5.00 per 1M tokens
- Output Tokens: $15.00 per 1M tokens
-
gpt-4o
- Provider: OpenAI
- Cost:
- Input Tokens: $2.50 per 1M tokens
- Output Tokens: $10.00 per 1M tokens
-
gpt-4o-mini
- Provider: OpenAI
- Cost:
- Input Tokens: $0.150 per 1M tokens
- Output Tokens: $0.600 per 1M tokens
Selecting a Model
When initializing AgentX or XAI, specify the model parameter to select the desired AI model.
Example: Initializing AgentX with gpt-4o-mini
example agent:
from agentX.agent_x import AgentX
def my_function(input: str) -> str:
"""
A simple example function that can be passed to AgentX as a tool.
Args:
input (str): The input string to process
Returns:
str: The unmodified input string
"""
# do something with input
return input
def exit_function(message: str) -> int:
"""
A simple example exit function that can be passed to AgentX.
Args:
message (str): A string containing a number to convert
Returns:
int: The string converted to an integer
"""
try:
return int(message)
except ValueError:
return -1
agent = AgentX(
model="grok-beta",
tools=[my_function],
mission="""
Do something with
#1 setup
- some useful details
#2 do something
- some details
#3 last thing to do
- some details
success criteria:
- that something is done
- it is done well
""",
exit_function=exit_function,
)
Installation
pip install agentxai
ENV Variables
XAI_API_KEY=
Metadata
Release files for agentxai 0.1.5
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 |
|---|---|---|---|---|
| agentxai-0.1.5.tar.gz | 10.0 kB | With provenance | Details for agentxai-0.1.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentxai-0.1.5-py3-none-any.whl | Python 3 | none | any | Details for agentxai-0.1.5-py3-none-any.whl |
Total release size: 20.9 kB
Release files / agentxai-0.1.5.tar.gz
| Download URL | agentxai-0.1.5.tar.gz |
|---|---|
| Size | 10.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
54f758281501742f370484063288136674619ecf5581bba8c4726f09bdcdc2cf
|
|
BLAKE2b-256 checksum How to use checksums |
b199afe64e15e4ca5dc8d57b13cf08d2d15e6b0016ed2c2cd32eee0fb3324cdd
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/5.1.1 CPython/3.12.7
|
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 Nov 26, 2024.
Transparency logRelease files / agentxai-0.1.5-py3-none-any.whl
| Download URL | agentxai-0.1.5-py3-none-any.whl |
|---|---|
| Size | 10.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
888af19e23a97ad2721bde31fb81158aeffd49787f0f49d620fa79da79793d9d
|
|
BLAKE2b-256 checksum How to use checksums |
0cb3edcfc877e8e87eff0dd26de10f0208895a5619cd63a3307ac69da8a69316
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/5.1.1 CPython/3.12.7
|
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 Nov 26, 2024.
Transparency logSecurity for agentxai 0.1.5
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.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for agentxai-0.1.5.tar.gz
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 Nov 26, 2024.
Transparency logA 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.