by langchain-ai · AI 工具 · ★ 29.6k
The batteries-included agent harness. Deep Agents is an agent harness. An opinionated, ready-to-run agent out of the box. Instead of wiring up prompts, tools, and context management yourself, you get a working agent immediately and customize what you need. What's included: Planning — for task breakdown and progress tracking Filesystem — , , , , , for reading and writing context Shell access — for running commands (with sandboxing) Sub-agents — for delegating work with isolated context windows Smart defaults — Prompts that teach the model how to use these tools effectively Context management —...
| Stars | 29,594 |
| Forks | 4,159 |
| Language | Python |
| Category | AI 工具 |
| License | MIT |
| Quality Score | 68.0522975889757/100 |
| Open Issues | 200 |
| Last Updated | 2026-09-20 |
| Created | 2025-07-27 |
| Platforms | python |
| Est. Tokens | ~7479k |
Explore other popular ai 工具 tools:
deepagents is Python & TypeScript agent harness built with LangChain and LangGraph. Equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - well-equipped to handle complex agentic . It is categorized as a AI 工具 with 29.6k GitHub stars.
deepagents is primarily written in Python. It covers topics such as ai, deepagents, langchain.
You can find installation instructions and usage details in the deepagents GitHub repository at github.com/langchain-ai/deepagents. The project has 29.6k stars and 4159 forks, indicating an active community.
deepagents is released under the MIT license, making it free to use and modify according to the license terms.