OpenAI: a-practical-guide-to-building-agents.pdf
openai/openai-agents-python: A lightweight, powerful framework for multi-agent workflows @GitHub
openai/agents.md: AGENTS.md — a simple, open format for guiding coding agents
The OpenAI Agents SDK enables you to build agentic AI apps in a lightweight, easy-to-use package with very few abstractions. It's a production-ready upgrade of our previous experimentation for agents, Swarm. The Agents SDK has a very small set of primitives:
- Agents, which are LLMs equipped with instructions and tools
- Handoffs, which allow agents to delegate to other agents for specific tasks
- Guardrails, which enable validation of agent inputs and outputs
- Sessions, which automatically maintains conversation history across agent runs
Examples - OpenAI Agents SDK python
openai-agents-js/examples at main · openai/openai-agents-js JavaScript
- Multi-Agent Workflows: Compose and orchestrate multiple agents in a single workflow.
- Tool Integration: Seamlessly call tools/functions from within agent responses.
- Handoffs: Transfer control between agents dynamically during a run.
- Structured Outputs: Support for both plain text and schema-validated structured outputs.
- Streaming Responses: Stream agent outputs and events in real time.
- Tracing & Debugging: Built-in tracing for visualizing and debugging agent runs.
- Guardrails: Input and output validation for safety and reliability.
- Parallelization: Run agents or tool calls in parallel and aggregate results.
- Human-in-the-Loop: Integrate human approval or intervention into workflows.
- Realtime Voice Agents: Build realtime voice agents using WebRTC or WebSockets
- Local MCP Server Support: Give an Agent access to a locally running MCP server to provide tools
- Separate optimized browser package: Dedicated package meant to run in the browser for Realtime agents.
- Broader model support: Use non-OpenAI models through the Vercel AI SDK adapter
- Long running functions: Suspend an agent loop to execute a long-running function and revive it later
- Voice pipeline: Chain text-based agents using speech-to-text and text-to-speech into a voice agent
OpenAI @GitHub search "Agents"
No comments:
Post a Comment