Skip to content
SPECIFICTION
Get listed

dcode

langchain.com

macOSLinux
Visit langchain.com
Spec score 7.3 #89 of 103 in AI Coding Assistants

Spec sheet

Purpose
It is intended for teams that want control over the model, tools, memory, approvals, and execution environment behind a coding agent.Read 12 Oct 2026 · langchain.com
Product
dcode is an open-source terminal coding agent built on the Deep Agents SDK.Read 12 Oct 2026 · langchain.com
Intended users
The maker describes dcode as suited to teams that want an inspectable, configurable coding agent with control over its model, tools, memory, approvals, and execution environment.Read 12 Oct 2026 · langchain.com
Integrations
The documentation says OpenAI, Anthropic, and Google are available out of the box; web search uses Tavily, and external tools can be loaded from MCP servers.Read 12 Oct 2026 · docs.langchain.com
Headquarters
San Francisco, California, United StatesRead 28 Sep 2026 · langchain.com
Founded
LangChain says its co-founders started the company in early 2023.Read 12 Oct 2026 · langchain.com
Company
LangChain says it is headquartered in San Francisco, with offices in New York, Boston, and Amsterdam.Read 12 Oct 2026 · langchain.com
Maker
LangChain says it is headquartered in San Francisco, started as a company in early 2023, and has offices in New York, Boston, and Amsterdam.Read 12 Oct 2026 · langchain.com
Agent customization
Users can configure models, plugins, memory, skills, middleware, hooks, and agents.Read 12 Oct 2026 · langchain.com
Authentication
dcode uses bring-your-own-key authentication, with provider keys supplied as environment variables or through a team's secrets workflow.Read 12 Oct 2026 · langchain.com
Capabilities
Documented capabilities include remote sandboxes, goals and rubrics, subagents, persistent memory, human approval controls, custom skills, MCP tools, and LangSmith tracing.Read 12 Oct 2026 · docs.langchain.com
Chat assistance
YesRead 22 Sep 2026 · langchain.com
Code approval
The agent proposes changes with diffs for approval before modifying files.Read 12 Oct 2026 · docs.langchain.com
Coding agent
YesRead 22 Sep 2026 · langchain.com
Customization
Users can customize the agent with plugins, memory, skills, middleware, hooks, agents, and configuration profiles.Read 12 Oct 2026 · langchain.com
Execution controls
The agent proposes changes with diffs for approval before modifying files, and human approval can be required for sensitive tool operations.Read 12 Oct 2026 · docs.langchain.com
Input limit
The maximum piped input size is 10 MiB.Read 12 Oct 2026 · docs.langchain.com
Model providers
It works with OpenAI, Anthropic, Google, and compatible APIs, and users can switch providers or models.Read 12 Oct 2026 · docs.langchain.com
Model support
It works with OpenAI, Anthropic, and OpenAI-compatible or Anthropic-compatible APIs, and supports switching models or providers.Read 12 Oct 2026 · langchain.com
Non-interactive input limit
The maximum piped input size in non-interactive mode is 10 MiB.Read 12 Oct 2026 · docs.langchain.com
Shell execution limit
Shell execution is disabled by default in non-interactive mode and can be enabled with an allow-list; allowing all commands permits arbitrary shell execution without human confirmation.Read 12 Oct 2026 · docs.langchain.com
Supported IDEs
ZedRead 22 Sep 2026 · langchain.com
Terminal access
YesRead 22 Sep 2026 · langchain.com
Tracing and governance
Connecting LangSmith can expose prompts, model responses, tool calls, errors, and token usage, while LangSmith and LLM Gateway provide cost policies, secrets redaction, and PII detection.Read 12 Oct 2026 · langchain.com
Usage modes
It supports interactive sessions and non-interactive tasks, including piped input for automation.Read 12 Oct 2026 · docs.langchain.com
Windows support
Deep Agents Code is not officially supported on Windows; Windows users can try it under WSL.Read 12 Oct 2026 · docs.langchain.com

Where Specifiction places it

Alternatives to dcodeAll alternatives →