> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-toolre-1772123259-dfebfdb.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Comparison with OpenCode and Claude Agent SDK
> Compare LangChain Deep Agents with OpenCode and Claude Agent SDK to choose the right tool for your use case
This page helps you understand how [LangChain Deep Agents](/oss/python/deepagents/overview) compare to [OpenCode](https://opencode.ai/) and the [Claude Agent SDK](https://platform.anthropic.com/docs/en/agent-sdk/overview).
## Overview
| Aspect | **LangChain Deep Agents** | **OpenCode** | **Claude Agent SDK** |
| -------------------- | --------------------------------------------------- | ----------------------------------------------------------------------------------------- | -------------------------------------------------------- |
| **Primary use case** | Build production agents programmatically | Interactive coding agent in terminal, desktop, or IDE | Build production agents programmatically |
| **Model support** | Model-agnostic (Anthropic, OpenAI, and 100s others) | 75+ providers including local models (Ollama) | Claude models (Anthropic, Azure, Vertex AI, AWS Bedrock) |
| **License** | MIT | MIT | MIT (underlying Claude Code is proprietary) |
| **Architecture** | Python SDK, TypeScript SDK, and CLI | TypeScript SDK, standalone product (terminal-based interface, desktop app, IDE extension) | Python SDK, TypeScript SDK |
## Feature comparison
| Feature | **Deep Agents** | **OpenCode** | **Claude Agent SDK** |
| ------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| | Core tools |
| | | |
| File Read/Write/Edit | ✅ [`ls`, `read_file`, `write_file`, `edit_file`](/oss/python/python/deepagents/harness#virtual-filesystem-access) | ✅ [`list`, `read`, `write`, `edit`](https://opencode.ai/docs/tools/#built-in) | ✅ [Read, write, edit](https://platform.claude.com/docs/en/agent-sdk/overview#capabilities) |
| Shell Execution | ✅ [`execute`](/oss/python/python/deepagents/) | ✅ [`bash`](https://opencode.ai/docs/tools/#built-in) | ✅ [bash](https://platform.claude.com/docs/en/agent-sdk/overview#capabilities) |
| Glob/Grep | ✅ [`glob`, `grep`](/oss/python/python/deepagents/harness#virtual-filesystem-access) | ✅ [`glob`, `grep`](https://opencode.ai/docs/tools/#built-in) | ✅ [glob, grep](https://platform.claude.com/docs/en/agent-sdk/overview#capabilities) |
| Web Search | ✅ support for [third-party](/oss/python/deepagents/customization#tools) and [provider-native](/oss/python/integrations/chat/openai#web-search) | ✅ [`webfetch`, `websearch`](https://opencode.ai/docs/tools/#built-in) | ✅ [WebSearch, WebFetch](https://platform.claude.com/docs/en/agent-sdk/overview#capabilities) |
| Planning/Todos | ✅ [`write_todos`](/oss/python/deepagents/harness#planning-capabilities) | ✅ [Plan mode (read-only analysis)](https://opencode.ai/docs/agents/#use-plan) | ✅ [Todo lists](https://platform.claude.com/docs/en/agent-sdk/todo-tracking) |
| Subagents | ✅ [Subagents](/oss/python/deepagents/subagents) | ✅ [General and Explore agents](https://opencode.ai/docs/agents/#subagents) | ✅ [Subagents](https://platform.claude.com/docs/en/agent-sdk/subagents) |
| MCP Support | ✅ | ✅ [MCP](https://opencode.ai/docs/mcp-servers/) | ✅ [MCP](https://platform.claude.com/docs/en/agent-sdk/mcp) |
| Human-in-the-Loop | ✅ [Approve/edit/reject](/oss/python/deepagents/human-in-the-loop#decision-types) | ✅ [Allow/Ask/Deny](https://opencode.ai/docs/permissions/) | ✅ [Permission modes](https://platform.claude.com/docs/en/agent-sdk/permissions) |
| Skills System | ✅ [Skills](/oss/python/deepagents/skills) | ✅ [Skills](https://opencode.ai/docs/skills/) | ✅ [Skills](https://platform.claude.com/docs/en/agent-sdk/skills) |
| Long-term memory | ✅ [Memory Store](/oss/python/deepagents/long-term-memory) | ✅ [Rules](https://opencode.ai/docs/rules/) | ✅ [CLAUDE.md files](https://platform.claude.com/docs/en/agent-sdk/modifying-system-prompts#method-1-claude-md-files-project-level-instructions) |
| Streaming | ✅ [Streaming](/oss/python/deepagents/streaming/overview) | ✅ | ✅ [Streaming](https://platform.claude.com/docs/en/agent-sdk/streaming-output) |
| | Sandbox Integrations |
| | | |
| Agent runs in sandbox | ✅ [Can run in sandbox](/oss/python/python/deepagents/sandboxes#agent-in-sandbox-pattern) | ✅ [Can run in sandbox](https://opencode.ai/docs/#install) | ✅ [Can run in sandbox](https://platform.claude.com/docs/en/agent-sdk/hosting) |
| Agent runs operations in sandboxes | ✅ [Uses sandboxes as tools](/oss/python/deepagents/sandboxes#sandbox-as-tool-pattern) | ❌ | ❌ |
| | Architecture |
| | | |
| Composable Middleware | ✅ | [Plugins](https://opencode.ai/docs/plugins/) | [Hooks](https://platform.claude.com/docs/en/agent-sdk/hooks) |
| Pluggable Storage Backends | ✅ [backends](http://localhost:3000/oss/python/deepagents/backends) | ❌ | ❌ |
| Virtual Filesystems | ✅ [Virtual filesystem](/oss/python/deepagents/harness#virtual-filesystem-access) with pluggable backends | ❌ | ❌ |
| | State management |
| | | |
| Session Resume | ✅ | ✅ [Sessions](https://opencode.ai/docs/sdk/#sessions) | ✅ [Session management](https://platform.claude.com/docs/en/agent-sdk/sessions) |
| File Checkpointing | ✅ [Backends and checkpoints](/oss/python/deepagents/backends#built-in-backends) | ✅ (Git-based) | ✅ [File checkpointing](https://platform.claude.com/docs/en/agent-sdk/file-checkpointing) |
| Time Travel (state branching) | ✅ Full | ❌ | ✅ |
| | Observability |
| | | |
| Native Tracing | ✅ [LangSmith](/langsmith/home) | ❌ | ❌ |
## Notice a mistake?
We drafted this comparison on February 18th, 2026.
If you notice mistakes or changes in products, please [file an issue](https://github.com/langchain-ai/docs/issues).
***
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/deepagents/comparison.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.