AgentSpec | Respan Docs

Open Agent Specification (Agent Spec) (pyagentspec) is Oracle’s open specification and Python SDK for defining and running agentic systems. It provides a portable way to describe agents, models, and workflows across runtimes. Respan gives you full observability over every spec execution, model call, and tool invocation — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai openinference-instrumentation-agentspec "pyagentspec[langgraph]"

Set environment variables

$ export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

OPENAI_API_KEY is used for LLM requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 from openinference.instrumentation.agentspec import AgentSpecInstrumentor
2 from pyagentspec.adapters.langgraph import AgentSpecLoader
3 from pyagentspec.agent import Agent
4 from pyagentspec.llms import OpenAiConfig
5 from respan import Respan
6 
7 respan = Respan(instrumentations=[AgentSpecInstrumentor()])
8 
9 agent = Agent(
10     name="haiku_assistant",
11     description="A helpful assistant that writes haikus.",
12     llm_config=OpenAiConfig(name="openai", model_id="gpt-4.1-nano"),
13     system_prompt="You are a helpful assistant. Respond only with a haiku.",
14 )
15 
16 langgraph_agent = AgentSpecLoader().load_component(agent)
17 
18 result = langgraph_agent.invoke(
19     input={"messages": [{"role": "user", "content": "Write a haiku about recursion."}]}
20 )
21 print(result["messages"][-1].content)
22 respan.flush()

View your trace

Open the Traces page to see your AgentSpec workflow with specification execution, tool calls, and LLM generations.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `AgentSpecInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

Set defaults at initialization — these apply to all spans.

1 from respan import Respan
2 from openinference.instrumentation.agentspec import AgentSpecInstrumentor
3 
4 respan = Respan(
5     instrumentations=[AgentSpecInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "agentspec-api", "version": "1.0.0"},
8 )

With propagate_attributes

Override per-request using a context scope.

1 from respan import Respan, propagate_attributes
2 from openinference.instrumentation.agentspec import AgentSpecInstrumentor
3 
4 respan = Respan(instrumentations=[AgentSpecInstrumentor()])
5 
6 def handle_request(user_id: str, message: str):
7     with propagate_attributes(
8         customer_identifier=user_id,
9         thread_identifier="conv_abc_123",
10         metadata={"plan": "pro"},
11     ):
12         result = langgraph_agent.invoke(
13             input={"messages": [{"role": "user", "content": message}]}
14         )
15         print(result["messages"][-1].content)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.