AgentLens should integrate with common AI agent frameworks so developers can instrument their agents without modifying large parts of their code.
This issue focuses on creating lightweight wrappers for popular frameworks such as:
The goal is to allow AgentLens to capture events such as:
• tool calls
• model prompts
• model responses
• agent state changes
Example usage concept:
from agentlens import instrument
agent = instrument(langchain_agent)
agent.run("Find the best laptop under $1500")
Expected outcome
Running the agent automatically emits AgentLens events such as:
tool_call
model_prompt
model_response
state_update
These events should appear in the AgentLens event stream.
Tasks
- design framework wrapper interface
- implement LangChain integration
- implement AutoGen integration
- add example demos in the examples folder
Success criteria
A developer should be able to instrument an existing agent with one line of code.
AgentLens should integrate with common AI agent frameworks so developers can instrument their agents without modifying large parts of their code.
This issue focuses on creating lightweight wrappers for popular frameworks such as:
The goal is to allow AgentLens to capture events such as:
• tool calls
• model prompts
• model responses
• agent state changes
Example usage concept:
from agentlens import instrument
agent = instrument(langchain_agent)
agent.run("Find the best laptop under $1500")
Expected outcome
Running the agent automatically emits AgentLens events such as:
tool_call
model_prompt
model_response
state_update
These events should appear in the AgentLens event stream.
Tasks
Success criteria
A developer should be able to instrument an existing agent with one line of code.