Menu
Use DeepAgents to build long-running task agents with a batteries-included harness for planning, tools, and workflow structure.
| name | Assemble production agent harnesses with DeepAgents |
| slug | assemble-production-agent-harnesses-with-deepagents |
| description | Use DeepAgents to build long-running task agents with a batteries-included harness for planning, tools, and workflow structure. |
| github_stars | 24135 |
| verification | security_reviewed |
| source | https://github.com/langchain-ai/deepagents |
| author | LangChain AI |
| publisher_type | open_source_project |
| category | Templates & Workflows |
| framework | Custom Agents |
| tool_ecosystem | {"github_repo":"langchain-ai/deepagents","github_stars":24135} |
Use DeepAgents to build long-running task agents with a batteries-included harness for planning, tools, and workflow structure.
DeepAgents, model provider credentials, workflow tools
Use the upstream install or setup path that matches your environment:
Requirements and caveats from upstream:
Basic usage or getting-started notes:
Shell access — run commands in your sandbox of choice
Human-in-the-loop — approve, edit, or reject tool calls before they run
from deepagents import create_deep_agent
Extracted from upstream docs: https://raw.githubusercontent.com/langchain-ai/deepagents/HEAD/README.md
Use Bisheng to assemble, evaluate, and publish enterprise RAG and agent workflows across internal data, models, and business users.
Use JetBrains Koog to define typed, fault-tolerant AI agents that run inside JVM, Kotlin, backend, mobile, or browser contexts.
Use Pipecat to define realtime voice and multimodal agent pipelines with transports, model providers, tools, and turn-taking tests.
Use Milvus to create vector collections, ingest embeddings, and serve filtered similarity search for RAG and agent retrieval workloads.
Define short Python project commands in pyproject.toml so agents and maintainers can run the same test, lint, docs, and release tasks without hunting through shell notes.
Routes engineering design, delivery, reliability, security, operations, and maintenance prompts to one native router skill backed by specialist guidance for Claude Code, Codex, Cursor, OpenCode, Copilot, and Gemini.
