Skip to main content
Version: 2.0
🚀 SDK v2 is here

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.

Get started with v2Legacy (v1) docs

aiXplain Agents SDK

Build and deploy autonomous AI agents on production-grade infrastructure, instantly.

aiXplain Agents SDK gives developers Python and REST APIs to build, run, and deploy autonomous multi-step agents on AgenticOS with runtime tool selection, delegation, code tools, traces, and governance controls.

Build with a vendor-agnostic catalog of 900+ AI models, tools, and integrations, swap models without rewriting pipelines, and use SDK/API or aiXplain Studio on the same runtime and policies.

Why aiXplain for developers:

  • ✓ Autonomous runtime loop – Plan, call tools/models, reflect, and continue without fixed flowcharts.
  • ✓ Multi-agent execution – Delegate work to specialized agents at runtime.
  • ✓ Governance by default – Inspectors and policy controls execute 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.
  • ✓ Flexible deployment – Run serverless or on-prem (private).
Build and run an agent

Prerequisite: create an 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)
Start building
Knowledge agents

Ground responses in your docs and knowledge bases with RAG workflows.

Data agents

Query operational data sources and return structured answers from live tables.

Custom logic agents

Add Python tools and business logic to execute domain-specific actions.

Integration agents

Connect MCP and systems like Slack, Salesforce, and X.

Team agents

Coordinate specialized agents for multi-step, multi-role execution.

Governed agents

Enforce runtime quality and policy checks with inspectors and controls.