{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-10-28T00:00:00Z",
  "id": "com.gtmstacker.registry/tool/design-agent",
  "type": "tool",
  "slug": "design-agent",
  "canonical_url": "https://gtmstacker.com/registry/tool/design-agent/",
  "title": "design-agent / Content Studio (LangChain's open-source on-brand design agent in Slack)",
  "description": "Apache-2.0 design agent from LangChain, called Content Studio inside the company: teammates ask in Slack and it produces on-brand graphics, ad resizes, LinkedIn cards, decks, charts and short videos from a brand pack kept as code. Built on Deep Agents; self-hostable with Docker Compose and your own model key, or deployed on LangChain's paid Managed Deep Agents. Replaces the design-request queue for routine marketing assets.",
  "category": "content-copywriting",
  "tags": [
    "content-copywriting",
    "marketing-ops",
    "mcp-agents",
    "design-agent",
    "brand-assets",
    "slack-bot",
    "deep-agents",
    "langchain",
    "self-hosted",
    "open-source"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "59d971685efece0e699fe1dbdbe8595bcf70311a42fadd4b85924dbfe15a7d30",
  "date_published": "2026-10-28T00:00:00Z",
  "date_modified": "2026-10-28T00:00:00Z",
  "source": {
    "name": "How we built Content Studio, an open-source design agent in Slack that makes on-brand videos, graphics and decks",
    "url": "https://x.com/LangChain/status/2115124503093121121",
    "author": "LangChain"
  },
  "license": "Apache-2.0",
  "one_liner": "LangChain's design-agent turns a Slack request into on-brand graphics, decks and short videos, so routine asset asks skip the design queue.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_signal": "Code free (Apache-2.0). You pay model spend with your own key and, optionally, LangChain Managed Deep Agents hosting (paid, public beta).",
  "pricing_model": "free",
  "who_its_for": "Lean marketing and GTM teams where sales, founders and others queue routine asset requests (ad resizes, social cards, charts, decks) and a technical owner can run Docker and model keys.",
  "who_its_not_for": "Teams without someone to host and maintain a Docker stack with a sandbox, or that need a mature, supported product; the repo is under two weeks old with two contributors.",
  "aliases": [
    "content studio",
    "langchain content studio",
    "langchain-ai/design-agent"
  ],
  "alternatives": [],
  "secondary_categories": [
    "marketing-ops",
    "mcp-agents"
  ],
  "last_verified": "2026-10-28",
  "evidence": {
    "claim_type": "mixed",
    "source_id": "https://github.com/langchain-ai/design-agent",
    "note": "Apache-2.0 per GitHub API spdx_id and LICENSE. Official langchain-ai org repo; README FAQ explains the Content Studio / design-agent naming. As of 2026-10-29: 232 stars, 30 forks, created 2026-10-18, 44 commits, 2 contributors. Usage figures (3,000+ assets since August, ~4.5M X views, 3 in 4 requests from outside marketing, ~$0.50 median request) are LangChain's own claims."
  },
  "caveats": "Early-stage: created 2026-10-18 with two contributors. Self-hosting means Docker Compose with Postgres and a sandbox image (Chromium, FFmpeg), plus model keys; optional OpenAI and ElevenLabs keys for images and voice. The default deploy path is LangChain's paid Managed Deep Agents. Usage and cost figures are vendor claims.",
  "lead": "**design-agent** (`langchain-ai/design-agent`) is an **Apache-2.0** design agent from **LangChain**. Inside LangChain and as a Slack app it is called **Content Studio**; the repo, package and CLI are named `design-agent` (the README FAQ explains the two names). Teammates ask for an asset in Slack and the agent produces on-brand graphics, ad…",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 154,
      "text": "**design-agent** (`langchain-ai/design-agent`) is an **Apache-2.0** design agent from **LangChain**. Inside LangChain and as a Slack app it is called **Content Studio**; the repo, package and CLI are named `design-agent` (the README FAQ explains the two names). Teammates ask for an asset in Slack and the agent produces on-brand graphics, ad resizes, LinkedIn cards, decks, charts and short launch videos, using a brand pack (tokens and fonts) stored as code. It is built on LangChain's Deep Agents, needs Python 3.11+, defaults to Claude Opus 5.5 and also supports OpenAI, Google and OpenAI-compatible endpoints."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 404,
      "text": "Slack and the agent produces on-brand graphics, ad resizes, LinkedIn cards, decks, charts and short launch videos, using a brand pack (tokens and fonts) stored as code. It is built on LangChain's Deep Agents, needs Python 3.11+, defaults to Claude Opus 5.5 and also supports OpenAI, Google and OpenAI-compatible endpoints.\n\n- SPDX **Apache-2.0**, confirmed by the GitHub license API and the LICENSE file; the README badge and FAQ agree.\n- Identity: official `langchain-ai` organization repo, linked from LangChain's blog and docs. Unrelated repos named \"content-studio\" exist on GitHub and are not this tool.\n- Activity as of 2026-10-29 (GitHub API): **232 stars, 30 forks**, not archived. Created 2026-10-18, last push 2026-10-27, 44 commits, 2 contributors.\n- Self-hosting: yes. `docs/self-hosting.md` describes a Docker Compose stack (HTTP API, Postgres, sandbox), an optional own Slack app in Socket Mode and a bring-your-own model key. A local demo with a scripted model runs with no API keys (Docker required).\n- Pricing: the code is free. Costs are model spend and, optionally, hosting on LangChain Managed Deep Agents (LangSmith Cloud, paid, public beta).\n- **Vendor claims:** \"3,000+ assets since August\", \"about 4.5M views on X\", \"three in four requests come from outside marketing\" and \"median request costs about 50 cents in model spend\" are LangChain's own figures.\n- Surfaced via LangChain's X post in the 2026-10-28 pull (the post returned HTTP 402; used for discovery only). Curated and verified in run `2026-10-28-registry-update-01` (step-3 verification, 2026-10-29 local; content date 2026-10-28)."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 188,
      "text": "come from outside marketing\" and \"median request costs about 50 cents in model spend\" are LangChain's own figures. - Surfaced via LangChain's X post in the 2026-10-28 pull (the post returned HTTP 402; used for discovery only). Curated and verified in run `2026-10-28-registry-update-01` (step-3 verification, 2026-10-29 local; content date 2026-10-28).\n\nIn a small company the person who needs a LinkedIn card or a resized ad is usually not the designer, so requests wait in a queue. design-agent lets anyone ask in Slack and get an asset that follows the brand pack, with model spend LangChain puts at about 50 cents a request. The tradeoff is ownership: someone has to host the stack, keep the brand pack current and review output before it ships."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/design-agent/index.md",
    "html": "https://gtmstacker.com/registry/tool/design-agent/",
    "json": "https://gtmstacker.com/registry/tool/design-agent/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/design-agent/server.json"
  },
  "jsonld": {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "WebSite",
        "@id": "https://gtmstacker.com/#website",
        "url": "https://gtmstacker.com/",
        "name": "GTM Stacker Agent Registry",
        "description": "A daily-updated, agent-native registry of open-source tool discoveries, tool updates, and curated news for the go-to-market / RevOps engineering niche. Machine-readable first: agents can discover, parse, page, and delta-sync it without scraping HTML.",
        "inLanguage": "en",
        "publisher": {
          "@id": "https://gtmstacker.com/#organization"
        }
      },
      {
        "@type": "Organization",
        "@id": "https://gtmstacker.com/#organization",
        "name": "GTM Stacker",
        "url": "https://gtmstacker.com",
        "description": "The growth-systems practice of Theo Popov: AI-native enrichment, outbound, content engines and internal tooling for startups and venture programs. Its agent-native media property, the GTM Stacker Agent Registry, maintains a daily-updated catalog of open-source go-to-market and RevOps tools that both people and AI engines can discover, compare, and cite.",
        "foundingDate": "2024-08",
        "knowsAbout": [
          "go-to-market engineering",
          "RevOps",
          "sales automation",
          "marketing operations",
          "open-source software",
          "AI agents"
        ],
        "founder": {
          "@type": "Person",
          "@id": "https://gtmstacker.com/#founder",
          "name": "Theo Popov",
          "jobTitle": "Growth Operations & GTM Systems",
          "url": "https://gtmstacker.com/about/",
          "sameAs": [
            "https://www.linkedin.com/in/theo-popov",
            "https://x.com/Theo_Popov",
            "https://github.com/theopopov"
          ],
          "worksFor": {
            "@id": "https://gtmstacker.com/#organization"
          }
        },
        "sameAs": [
          "https://www.linkedin.com/company/gtmstacker",
          "https://www.youtube.com/@gtmstacker",
          "https://www.instagram.com/gtmstacker/",
          "https://www.tiktok.com/@gtmstacker"
        ],
        "mainEntityOfPage": "https://gtmstacker.com/registry/about/"
      },
      {
        "@type": "SoftwareApplication",
        "@id": "https://gtmstacker.com/registry/tool/design-agent/#software",
        "name": "design-agent / Content Studio (LangChain's open-source on-brand design agent in Slack)",
        "identifier": "io.github.langchain-ai/design-agent",
        "description": "Apache-2.0 design agent from LangChain, called Content Studio inside the company: teammates ask in Slack and it produces on-brand graphics, ad resizes, LinkedIn cards, decks, charts and short videos from a brand pack kept as code. Built on Deep Agents; self-hostable with Docker Compose and your own model key, or deployed on LangChain's paid Managed Deep Agents. Replaces the design-request queue for routine marketing assets.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/design-agent/",
        "datePublished": "2026-10-28T00:00:00Z",
        "dateModified": "2026-10-28T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "license": "https://spdx.org/licenses/Apache-2.0.html",
        "codeRepository": "https://github.com/langchain-ai/design-agent",
        "keywords": "content-copywriting, marketing-ops, mcp-agents, design-agent, brand-assets, slack-bot, deep-agents, langchain, self-hosted, open-source",
        "author": {
          "@type": "Organization",
          "name": "langchain-ai",
          "url": "https://github.com/langchain-ai",
          "sameAs": [
            "https://github.com/langchain-ai/design-agent"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        }
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/design-agent/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "Content Copywriting",
            "item": "https://gtmstacker.com/registry/category/content-copywriting/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "design-agent / Content Studio (LangChain's open-source on-brand design agent in Slack)",
            "item": "https://gtmstacker.com/registry/tool/design-agent/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "io.github.langchain-ai/design-agent",
    "repository": {
      "url": "https://github.com/langchain-ai/design-agent",
      "source": "github"
    }
  }
}