Gateagent Python SDK
Track and analyze your AI agent's tool interactions with deep insights.
Installation
pip install gateagent
Example: Math Agent
Here is a complete example of how to use gateagent with a LangChain agent:
from langchain_openai import ChatOpenAI
from langchain.tools import tool
from langchain_core.prompts import ChatPromptTemplate
from langsmith import traceable
from gateagent import InteractionTracer
# 1. Initialize the Tracer
callbacks = [
InteractionTracer(
project_name="math-agent-playground",
# tenant_id is derived from API Key on backend
default_metadata={
"agent": "math-agent-v1",
"environment": "local",
},
)
]
# 2. Define Tools
@tool
def add_numbers(a: int, b: int) -> int:
"""Add two numbers."""
return a + b
tools = [add_numbers]
tool_map = {t.name: t for t in tools}
llm = ChatOpenAI(model="gpt-4o-mini", temperature=0).bind_tools(tools)
prompt = ChatPromptTemplate.from_messages([
("system", "You are a math assistant."),
("human", "{input}"),
])
chain = prompt | llm
# 3. Use in execution (with @traceable or directly in config)
@traceable(run_type="chain", name="math-agent")
def run(input_text: str):
response = chain.invoke(
{"input": input_text},
config={
"callbacks": callbacks,
"run_name": "math-agent-llm",
"metadata": {"agent": "math-agent-v1"},
},
)
if response.tool_calls:
# Pass callbacks to tool execution logic
tool_call = response.tool_calls[0]
return tool_map[tool_call["name"]].invoke(
tool_call["args"],
config={"callbacks": callbacks}
)
return response.content
Configuration
Set your API key via environment variable:
export GATEAGENT_API_KEY="your-api-key"
Or pass it to the Client explicitly if needed (advanced usage).
Metadata
Release files for gateagent 0.1.9
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 |
|---|---|---|---|---|
| gateagent-0.1.9.tar.gz | 4.8 kB | Without provenance | Details for gateagent-0.1.9.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| gateagent-0.1.9-py3-none-any.whl | Python 3 | none | any | Details for gateagent-0.1.9-py3-none-any.whl |
Total release size: 10.1 kB
Release files / gateagent-0.1.9.tar.gz
| Download URL | gateagent-0.1.9.tar.gz |
|---|---|
| Size | 4.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
03a79a09c1acbcad1c40be694d55d3705547ae0107aa3032cfd19157ad0c0090
|
|
BLAKE2b-256 checksum How to use checksums |
0ed88d37e694a55ccd1285d5ed019c8c84a7a56abb43ed4f497df4c34ebe29b7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Release files / gateagent-0.1.9-py3-none-any.whl
| Download URL | gateagent-0.1.9-py3-none-any.whl |
|---|---|
| Size | 5.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4dd94b5ff8fb10d60274b90748527289fd10cf4052995a8bef3bb9baace3a7d6
|
|
BLAKE2b-256 checksum How to use checksums |
94b84ae1859de559ac26ba5d193e8c771c3c42478e8c8152d62eb4b7953afebc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Security for gateagent 0.1.9
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.