The official Python SDK for AgentX — build, chat with, and orchestrate AI agents in a few lines of code.
Contents
- Why AgentX
- Installation
- Authentication
- Quick start
- Working with agents
- Workforce (multi-agent orchestration)
- Agent Evaluations — LLM-as-a-judge, cosine / Jaccard similarity
- Links
Why AgentX
- Simple mental model —
Agent → Conversation → Message. - Chain-of-thought is built in, no extra plumbing.
- Bring any LLM — works across major open and closed-source vendors.
- Batteries included — voice (ASR/TTS), image generation, document/CSV/Excel/OCR, RAG with built-in re-ranking.
- MCP support — connect any Model Context Protocol server.
- Multi-agent orchestration — workforces of agents with a designated manager, across LLM vendors.
- Agent Evaluations — score any agent (LangChain, CrewAI, OpenAI, Anthropic, HTTP, …) with LLM-as-a-judge ratings plus optional cosine and Jaccard similarity metrics.
- A2A — Each agent can be published with agent-to-agent protocol compatible.
Installation
pip install --upgrade agentx-python
Requires Python 3.9 or newer.
Authentication
Get your API key at app.agentx.so, then either pass it inline or expose it as an environment variable.
# Option A — pass the key inline
from agentx import AgentX
client = AgentX(api_key="your-api-key-here")
# Option B — set AGENTX_API_KEY in your environment, then:
client = AgentX.from_env()
Quick start
from agentx import AgentX
client = AgentX.from_env()
# Pick an existing agent and chat with it
agent = client.list_agents()[0]
conversation = agent.new_conversation()
print(conversation.chat("Hello! What can you help me with?"))
That's it. The remaining sections show the same primitives in more detail.
Working with agents
List agents
agents = client.list_agents()
print(f"You have {len(agents)} agents")
Start a conversation
agent = client.get_agent(id="<agent-id>")
# Either resume an existing conversation…
existing = agent.list_conversations()
last = existing[-1]
for msg in last.list_messages():
print(msg)
# …or start a fresh one
conversation = agent.new_conversation()
Chat (streaming and non-streaming)
# Blocking — returns the full response once it's ready
response = conversation.chat("What is your name?")
print(response)
# Streaming — yields ChatResponse objects as the model produces them
for chunk in conversation.chat_stream("Hello, what is your name?"):
if chunk.text:
print(chunk.text, end="")
Each ChatResponse chunk exposes the agent's text and, where applicable, its cot (chain-of-thought) reasoning, along with any retrieved references and tasks.
Workforce (multi-agent orchestration)
A workforce is a team of agents coordinated by a designated manager agent. Workforces can mix LLM vendors and route work between specialists.
workforces = client.list_workforces()
workforce = workforces[0]
print(f"Workforce: {workforce.name}")
print(f"Manager: {workforce.manager.name}")
print(f"Agents: {[a.name for a in workforce.agents]}")
# Chat with the workforce — the manager decides which agent(s) to delegate to
conversation = workforce.new_conversation()
for chunk in workforce.chat_stream(conversation.id, "How can you help me with this project?"):
if chunk.text:
print(chunk.text, end="")
Custom agent evaluations
Evaluate any AI agent — LangChain, CrewAI, AutoGen, LlamaIndex, OpenAI, Anthropic, HTTP endpoints, or plain Python — using AgentX as the scoring and reporting backend. Includes optional cosine and Jaccard similarity metrics alongside LLM-graded ratings.
report = (
client.evaluations
.run(dataset_id="evds_…", subject={"kind": "custom_agent", "framework": "raw_python"})
.execute(my_agent_fn)
.finalize()
.analyze()
)
print(report.average_rating) # LLM-graded score, 0–10
print(report.cosine_similarity) # embedding cosine, 0–1 (None if not enabled)
print(report.jaccard_similarity) # token-set overlap, 0–1 (None if not enabled)
See EVALUATIONS.md for the full guide — dataset builder, framework adapters, similarity metrics, and the complete API reference.
Links
- Dashboard — app.agentx.so
- Website — agentx.so
- PyPI — agentx-python
- Evaluations docs — EVALUATIONS.md
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 agentx_python-0.5.1.tar.gz.
File metadata
- Download URL: agentx_python-0.5.1.tar.gz
- Upload date:
- Size: 43.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.25
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d8e311345244afcfe81ef2550ffb4a6f3489de746bf4687ae17e1932482d05ca
|
|
| MD5 |
7e66473b135a55096a850b4afe3afb92
|
|
| BLAKE2b-256 |
4096c9c15ea86fcdd88522cc3f38bce420c6a9bb30cb96048f12d08dfd7d1605
|
File details
Details for the file agentx_python-0.5.1-py3-none-any.whl.
File metadata
- Download URL: agentx_python-0.5.1-py3-none-any.whl
- Upload date:
- Size: 53.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.25
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
990352df684dd0a91b9f2420237efcf4ebddd2d8f7f47cc0f59f94803cbce537
|
|
| MD5 |
4df82be7921f3b60cc1967b9d4786411
|
|
| BLAKE2b-256 |
7a5226e5e094a2a78d09304c5444a630d2e1ec6c6a9c23922f474dbd619ebe48
|
