v2 introduces a redesigned API with simplified agent creation, improved async execution, and first-class support for multi-agent workflows. If you're starting a new project, we recommend v2.
aiXplain SDK
Build, deploy, and govern autonomous AI agents on production-grade infrastructure.
aiXplain SDK gives developers Python and REST APIs to build, run, and deploy autonomous agents on AgenticOS — with runtime tool invocation, multi-agent delegation, code execution, execution traces, and governance on every run. Access a vendor-agnostic catalog of 900+ models, tools, and integrations.
Why aiXplain for developers:
- ✓ Autonomous runtime loop – Plan, call tools/models, reflect, and continue without fixed flowcharts.
- ✓ Multi-agent execution – Delegate work to specialized subagents at runtime.
- ✓ Governance by default – Runtime access and policy enforcement on every run.
- ✓ Production observability – Use validation traces and run telemetry for debugging and operations.
- ✓ Model and tool portability – Swap assets without rewriting application glue code.
- ✓ MCP-native access – Connect MCP clients to 900+ aiXplain-hosted assets with one PAYG API key.
- ✓ Flexible deployment – Cloud (serverless) or onprem. See Sovereignty.
Prerequisite: create a PAYG API key .
from aixplain import Aixplain
aix = Aixplain(api_key="YOUR_API_KEY")
agent = aix.Agent(
name="Research agent",
description="Answers questions with cited web findings.",
instructions="Use web search when needed and keep answers concise.",
tools=[aix.Tool.get("tavily/tavily-web-search/tavily")],
# Default model is GPT 5.2; override with llm="YOUR_MODEL_ID"
).save()
print(agent.run("Summarize the latest AgenticOS release updates.").data.output)
Ground responses in your docs and knowledge bases with RAG workflows.
Query operational data sources and return structured answers from live tables.
Add Python tools and business logic to execute domain-specific actions.
Connect to MCP servers and services like Slack, Salesforce, and more.
Coordinate specialized agents for multi-step, multi-role execution.
Enforce runtime quality and policy checks with inspectors and controls.
aiXplain Marketplace now extends 900+ models and tools with aiXplain-hosted MCP endpoints, allowing external clients to access selected tools, integrations, and model assets with a single PAYG API key.