langchain-ai/deepagents
A Python agent harness built on LangGraph. It adds planning, sub-agents with their own context window, a file and shell layer, and automatic summarising of long threads. Any tool call can be set to wait for approval before it runs.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Python developers building long-running agents who need sub-agents and approval steps.
Not for
Someone who wants a finished coding app out of the box. It is a library you assemble, and the README says the model is trusted and safety belongs in the sandbox layer.
Repo
- Stars
- 31,248
- License
- MITUse it, change it, sell it, closed-source included. Keep the author's copyright notice.
- Maturity
- active
- Last push
- 2026-11-13
- Last checked
- 2026-11-14