Build durable Python AI agents on Conductor. Agents can use local Python tools, wait for people, execute dynamic plans, and recover after process restarts because Conductor persists execution state.
pip install 'conductor-python[agents]'Requirements: Python 3.10+ and a Conductor server with an LLM provider configured server-side. Replace example model names with a model enabled on that server.
- Getting started — configure a server and run a basic agent.
- Deploy · Serve · Run · Plan — choose a runtime mode.
- Scheduling — manage deployed-agent schedules.
- Agents, tools, and multi-agent
- Guardrails, termination, callbacks
- Stateful agents, streaming and HITL, and structured output
- Runtime reference, control-plane reference, and API map
- Agent-definition fields and configuration contract
| Capability | Conductor agent runtime |
|---|---|
| Process recovery | Durable workflow state resumes from completed work. |
| Python tools | Tools run as independently scalable Conductor worker tasks. |
| Long-running work | Human approval, schedules, and events do not occupy application threads. |
| Dynamic execution | Plans become durable, inspectable sub-workflows. |
| Observability | Inputs, outputs, tool calls, retries, and status share one execution record. |