LangChain Deep Agents CLI lands as terminal agent

// 78d agoOPENSOURCE RELEASE

LangChain Deep Agents CLI lands as terminal agent

LangChain's Deep Agents CLI is an open-source terminal coding agent built on the Deep Agents SDK. It brings model switching, lifecycle hooks, persistent memory, MCP tools, custom skills, subagents, and approval-gated code execution into a Claude Code-style workflow.

// ANALYSIS

This feels like LangChain's open-source answer to Claude Code, but with a more explicit bet on model neutrality and inspectable, file-backed state.

–Model switching is first-class, with OpenAI, Anthropic, and Google support out of the box and more providers available as extras.
–Memory lives in files under `~/.deepagents/...`, so project conventions are auditable instead of trapped in hidden state.
–Skills, MCP tools, and custom subagents turn the CLI into a composable harness, not just a prompt wrapper.
–Approval controls and sandboxes matter because this agent can edit files and run shell commands.
–The tradeoff is surface area: a more powerful terminal agent also means more setup and policy decisions than a closed one-off tool.

// TAGS

deep-agents-clicliagentai-codingmcpopen-sourcesdk

DISCOVERED

78d ago

2026-03-23

PUBLISHED

78d ago

2026-03-23

RELEVANCE

9/ 10

AUTHOR

Income stream surfers

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE37m ago

Netlify launches an official plugin in the Cursor marketplace to provide AI models with native context on Netlify functions, databases, and deploys.

Netlify has released an official integration in the Cursor Marketplace, bringing developer-focused capabilities directly into the Cursor IDE. The plugin includes 13 skills and 27 rules to give Cursor's AI models precise context regarding Netlify's features, such as functions, edge functions, Blobs, Database, caching, the AI Gateway, CLI, and deployments.

MODEL40m ago

Anthropic launches Claude Fable 5

Anthropic has released Claude Fable 5, its most powerful public model designed specifically for complex, long-running agentic tasks. The model features built-in safety classifiers that automatically reroute sensitive requests in cybersecurity, biology, or chemistry to Claude Opus 4.8.

OPEN SOURCE52m ago

Developer Av1dlive releases Agentic Stack, an open-source portable memory and loop-based workflow framework that replicates the autonomous setup used by the creator of Claude Code.

Agentic Stack is an open-source framework designed to provide a portable memory-and-skills layer for AI coding agents. Inspired by Boris Cherny's (creator of Claude Code) philosophy of shifting from prompt engineering to 'loop engineering,' Agentic Stack establishes a local `.agent/` directory that stores agent context, skills, and protocols. This allows developers to maintain consistent agent behaviors, shared memory, and automatic learning patterns across multiple developer platforms—such as Claude Code, Cursor, Windsurf, and custom DIY Python loops—without suffering from 'tool amnesia' when switching environments.