Deep Agents 0.1.0 released
A major release adding reasoning controls, sandbox providers, and improvements to chat threading and job scheduling.
What changed in 0.1.0
- Requires Python 3.14 instead of earlier versions.
- Added /effort controls for reasoning and configurable verbosity for progress updates.
- NVIDIA OpenShell sandbox provider available via openshell extra.
- Discord guild mentions now reply in threads like Slack; Slack thread context improved to preserve participants and include bot replies.
- Skills can attach to scheduled jobs with automatic reloading; background subagent capacity and checkpoint backends are now configurable.
Check before you update
- deepagents-talon requires Python 3.14 (>=3.14,<3.15)
Summarised by AgentGid from LangChain's official release notes on GitHub, as reported there; read the original before relying on it. Price, status and release dates come from our daily data.
Deep Agents at a glance
| What it is | A batteries-included agent harness built on LangGraph, with planning, a virtual file system and sub-agents for long-running tasks. |
|---|---|
| Latest version | 0.2.4, Nov 2, 2026. This page is about an earlier release. |
| Release pace | 31 stable releases in the last 30 days; 0.1.0 came the same day as the previous one |
| Price | Free (OSS). Deep Agents is open source and free to use; you pay only for the models and infrastructure it runs on. (checked Oct 5, 2026) |
| Downloads, last 7 days | 2.5M up 15.2% |
| Gid Score | 56 #9 in Agent frameworks and SDKs |
