deepagents
deepagents copied to clipboard
langchain-ai
Code mount: ``` import os from runloop_api_client import Runloop from runloop_api_client.types import LaunchParameters client = Runloop() # API Key is automatically loaded from "RUNLOOP_API_KEY" environment variable devbox = client.devboxes.create( environment_variables={"GH_TOKEN":...
Add ability to pass a prompt as a command-line argument that executes on entering interactive mode. Usage: deepagents "create hello.py" deepagents --agent mybot "review the last commit" deepagents --auto-approve "add...
Add ability to switch between OpenAI and Anthropic models during a session with the /model slash command. Model choice is persisted in config.json and restored in future sessions. Changes: -...
Hi, is there a way to show what the main agent and its sub-agents are doing? Specifically, I'd like to know which tool is being used and what it's doing....
ImportError: cannot import name 'ToolCallRequest' from 'langchain.agents.middleware.types' Python:3.12.6
* Partial implementation of an ACP adapter * Not expected to be complete for a while
I s it possible to get each agent name of a middleware? I'm setting `name` for each agent, and in the middleware using `before_model` and `after_model`, but only reciving information...
We want to give sub agents access to system tools like read , write and list files. What is best way to do that ?
Currently, I have found that the frequency of this issue occurring on write todo is quite high. ```python │ │ AIMessage( │ │ │ content='', │ │ │ additional_kwargs={}, │...
Implements Claude's native text editor tool as an alternative to the standard FilesystemMiddleware. This provides exact compatibility with Claude's `text_editor_20250728` -- https://docs.claude.com/en/docs/agents-and-tools/tool-use/text-editor-tool Key features: - Single command-based tool: str_replace_based_edit_tool -...
