Deep Agents
Open-source agent harness for long-running tasks that handles planning, context management and multi-agent orchestration, with planning tools, parallel subagents, a virtual filesystem for memory and any model provider.
Find alternatives to Deep Agents
What it does
- Agent orchestration
Sources
- Pricing
-
Official documentation · 18 Oct 2026
"Deep Agents is an open source agent harness"; no price is listed.
- Description
-
Official documentation · 18 Oct 2026
"Deep Agents is an open source agent harness built for long-running tasks. It handles planning, context management, and multi-agent orchestration for complex work like research and coding."
- What it does
-
Official documentation · 18 Oct 2026
"Planning tools let agents decompose tasks"; "Spawn subagents for independent subtasks, each with isolated context"; "Virtual filesystem stores system prompts, skills, and long-term memory".
- Sold within
-
Official documentation · 18 Oct 2026
Open-source harness with "Start building" and "Read the docs"; no plan, parent offering or price is involved.
- Name
-
Official documentation · 18 Oct 2026
Page heading "deepagents: Build agents for complex, multi-step tasks"; "Deep Agents is an open source agent harness".
- URL
-
Official documentation · 18 Oct 2026
The product's own page, titled "Deep Agents: Open Source Agent Harness | LangChain".
- Deployment
-
Official documentation · 18 Oct 2026
An open-source harness the developer runs in their own code: "Use any model provider, manage state, and add human-in-the-loop when you need it."
- Interfaces
-
Official documentation · 18 Oct 2026
Referred to as the "Deep Agents SDK" on the dcode page; "Tracing and deployment work natively with LangSmith".
- Modalities
-
Official documentation · 18 Oct 2026
Agents for "research, coding, and multi-step workflows".
- Intended for
-
Official documentation · 18 Oct 2026
"Deep Agents is a batteries-included, general purpose agent harness" for "Agents are taking on increasingly complex work".
Also from LangChain
-
LangChain Developer tool
Open-source framework for composing language-model calls, tools and retrieval into applications.
-
LangGraph Developer tool
Open-source library for building agents as explicit graphs of steps and state.
-
LangSmith Platform
Traces, evaluates and monitors language-model applications in development and production.
-
LangSmith Context Hub Agent platform
Versions and deploys prompts and agent context. Part of the LangSmith platform (categorized under 'No-Code Agents', 'Observability', 'Evaluation' or 'Deployment infrastructure' depending on the module).
-
LangSmith Deployment Agent platform
Deploys and operates production agents. Part of the LangSmith platform (categorized under 'No-Code Agents', 'Observability', 'Evaluation' or 'Deployment infrastructure' depending on the module).
-
LangSmith Engine Agent platform
Analyzes agent traces and recommends fixes. Part of the LangSmith platform (categorized under 'No-Code Agents', 'Observability', 'Evaluation' or 'Deployment infrastructure' depending on the module); also red-teams agents for issues not yet seen in production.
-
LangSmith Fleet Agent platform
No-code agent building, deployment into Slack/Teams/Gmail, and human-in-the-loop approval controls. Part of the LangSmith platform (categorized under 'No-Code Agents', 'Observability', 'Evaluation' or 'Deployment infrastructure' depending on the module).
-
LangSmith LLM Gateway Agent platform
Governs model calls and spending across providers. Part of the LangSmith platform (categorized under 'No-Code Agents', 'Observability', 'Evaluation' or 'Deployment infrastructure' depending on the module).
-
LangSmith Sandboxes Agent platform
Runs agent-generated code in isolated virtual machines. Part of the LangSmith platform (categorized under 'No-Code Agents', 'Observability', 'Evaluation' or 'Deployment infrastructure' depending on the module).
-
LangSmith Chat Application
LangSmith Chat analyzes application traces, threads, prompts and evaluations; also answers natural-language questions to understand agent performance, debug issues and analyze user sentiment.
-
LangSmith Evaluation Agent platform
LangSmith's evaluation service for agents: run evaluations on curated datasets to compare agent versions and catch regressions, score live traffic with online evaluators, collect human feedback in annotation queues and optimise prompts in a playground.
-
dcode Developer tool
Open-source terminal coding agent built on the Deep Agents SDK that works with the user's own model and lets them control the agent harness, memory, skills, hooks and how code execution is approved, traced and run.
Open LangChain in the directory
Something wrong here? Send a correction — quote this product id: langchain-deep-agents.