This agent implements the CodeAct idea (paper, tweet) that consolidates LLM agents’ actions into a unified code action space for both simplicity and performance.
The conceptual idea is illustrated below. At each turn, the agent can:
bash
commandPython
code with an interactive Python interpreter. This is simulated through bash
command, see plugin system below for more details.https://github.com/All-Hands-AI/OpenHands/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
Example of CodeActAgent with gpt-4-turbo-2024-04-09
performing a data science task (linear regression).
This agent implements the CodeAct idea (paper, tweet) that consolidates LLM agents’ actions into a unified code action space for both simplicity and performance.
The conceptual idea is illustrated below. At each turn, the agent can:
bash
commandPython
code with an interactive Python interpreter. This is simulated through bash
command, see plugin system below for more details.https://github.com/All-Hands-AI/OpenHands/assets/38853559/f592a192-e86c-4f48-ad31-d69282d5f6ac
Example of CodeActAgent with gpt-4-turbo-2024-04-09
performing a data science task (linear regression).