{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-09-22T00:00:00Z",
  "id": "com.gtmstacker.registry/tool/strands-harness-sdk",
  "type": "tool",
  "slug": "strands-harness-sdk",
  "canonical_url": "https://gtmstacker.com/registry/tool/strands-harness-sdk/",
  "title": "Strands harness-sdk",
  "description": "Apache-2.0 SDK (Python and TypeScript) from the AWS-backed Strands Agents project for building AI-agent harnesses that run in-process, with no hosted control plane. It is model-agnostic — first-class Amazon Bedrock plus Anthropic, OpenAI and Gemini, and local models via Ollama — so an agent you build stays portable across providers and can run entirely on your own hardware instead of being tied to one vendor's runtime.",
  "category": "ai-infrastructure",
  "tags": [
    "ai-infrastructure",
    "mcp-agents",
    "self-hostable",
    "agent-framework",
    "developer-tooling"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "244ed60c36c0badf878dd5aecf27bbf8ae257b29e55aa7df2bbeb9b2436ba4bb",
  "date_published": "2026-09-22T00:00:00Z",
  "date_modified": "2026-09-22T00:00:00Z",
  "source": {
    "name": "github · strands-agents/harness-sdk",
    "url": "https://github.com/strands-agents/harness-sdk"
  },
  "license": "Apache-2.0",
  "one_liner": "Strands harness-sdk is an Apache-2.0 SDK for building in-process AI-agent harnesses that run model-agnostic across Bedrock, Anthropic, OpenAI and local Ollama.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_model": "free",
  "who_its_for": "An AI-native or RevOps engineer building production agents who wants them portable across any model and cloud — and runnable locally — rather than locked to a single provider's hosted agent runtime.",
  "aliases": [
    "strands-harness-sdk",
    "Strands Harness",
    "harness-sdk"
  ],
  "alternatives": [
    "deepseek-harness",
    "harnessrouter"
  ],
  "secondary_categories": [
    "mcp-agents",
    "workflow-automation"
  ],
  "last_verified": "2026-09-22",
  "evidence": {
    "claim_type": "mixed",
    "source_id": "https://github.com/strands-agents/harness-sdk",
    "note": "Apache-2.0 (LICENSE verified), ~7,540 stars, ~2,743 commits, created 2025-05-14, pushed 2026-09-22; runs in-process with no hosted control plane; model-agnostic with first-class Bedrock and support for Anthropic/OpenAI/Gemini plus local Ollama (WebFetch 2026-09-22, strands-agents org). Framing correction: it is the AWS-backed strands-agents org (Bedrock is first-class), not literally an 'aws/' GitHub org; 'runs on a local model' is true specifically via Ollama."
  },
  "caveats": "AWS-associated via the Strands project and first-class Bedrock, but it is the strands-agents org, not the official aws/ namespace — call it AWS-backed, not 'AWS released.' Local-model support is through Ollama; other local runtimes are on you. It is a builder's SDK, so value depends on you writing the harness.",
  "lead": "Apache-2.0 SDK (Python and TypeScript) from the AWS-backed Strands Agents project for building AI-agent harnesses that run in-process, with no hosted control plane. It is model-agnostic — first-class Amazon Bedrock plus Anthropic, OpenAI and Gemini, and local models via Ollama — so an agent you build stays portable across providers…",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 106,
      "text": "Apache-2.0 SDK (Python and TypeScript) from the AWS-backed Strands Agents project for building AI-agent harnesses that run in-process, with no hosted control plane. It is model-agnostic — first-class Amazon Bedrock plus Anthropic, OpenAI and Gemini, and local models via Ollama — so an agent you build stays portable across providers and can run entirely on your own hardware instead of being tied to one vendor's runtime."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 221,
      "text": "run in-process, with no hosted control plane. It is model-agnostic — first-class Amazon Bedrock plus Anthropic, OpenAI and Gemini, and local models via Ollama — so an agent you build stays portable across providers and can run entirely on your own hardware instead of being tied to one vendor's runtime.\n\n- Apache-2.0 (LICENSE independently verified), ~7.5K stars, ~2,743 commits, created 2025-05-14, pushed 2026-09-22; in-process execution, no hosted control plane; first-class Bedrock plus Anthropic/OpenAI/Gemini and local Ollama (WebFetch 2026-09-22, github.com/strands-agents/harness-sdk).\n- Surfaced in both the 2026-09-22 X viral-posts brief (\"AWS open-sourced an agent harness you can run with a local model\") and the studio discovery lane; cross-pull corroborated.\n- Curated from the GTM Stacker signal registry (2026-09-22 pass); license independently verified 2026-09-22."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 286,
      "text": "plus Anthropic/OpenAI/Gemini and local Ollama (WebFetch 2026-09-22, github.com/strands-agents/harness-sdk). - Surfaced in both the 2026-09-22 X viral-posts brief (\"AWS open-sourced an agent harness you can run with a local model\") and the studio discovery lane; cross-pull corroborated. - Curated from the GTM Stacker signal registry (2026-09-22 pass); license independently verified 2026-09-22.\n\nThe quiet tax on agent infrastructure is the runtime lock-in: build on a hosted control plane and your agents assume that provider's models, quotas and availability. harness-sdk is the portable answer — an in-process SDK where the harness is yours, the model is a swap, and the same agent can point at Bedrock in production or Ollama on a laptop. For a team standardizing how it ships agents and wanting an escape hatch from any single vendor, that portability plus Apache-2.0 is worth the build cost. The honest read: it is AWS-backed (the strands-agents org, Bedrock first-class), not the official aws/ org, and \"local model\" means Ollama specifically. It is a builder's kit, not a turnkey product — the leverage is in what you assemble on it."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/strands-harness-sdk/index.md",
    "html": "https://gtmstacker.com/registry/tool/strands-harness-sdk/",
    "json": "https://gtmstacker.com/registry/tool/strands-harness-sdk/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/strands-harness-sdk/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/strands-harness-sdk/#software",
        "name": "Strands harness-sdk",
        "identifier": "io.github.strands-agents/harness-sdk",
        "description": "Apache-2.0 SDK (Python and TypeScript) from the AWS-backed Strands Agents project for building AI-agent harnesses that run in-process, with no hosted control plane. It is model-agnostic — first-class Amazon Bedrock plus Anthropic, OpenAI and Gemini, and local models via Ollama — so an agent you build stays portable across providers and can run entirely on your own hardware instead of being tied to one vendor's runtime.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/strands-harness-sdk/",
        "datePublished": "2026-09-22T00:00:00Z",
        "dateModified": "2026-09-22T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "license": "https://spdx.org/licenses/Apache-2.0.html",
        "codeRepository": "https://github.com/strands-agents/harness-sdk",
        "keywords": "ai-infrastructure, mcp-agents, workflow-automation, self-hostable, agent-framework, developer-tooling",
        "author": {
          "@type": "Organization",
          "name": "strands-agents",
          "url": "https://github.com/strands-agents",
          "sameAs": [
            "https://github.com/strands-agents/harness-sdk"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        },
        "isSimilarTo": [
          {
            "@type": "SoftwareApplication",
            "name": "DeepSeek Harness (dsh)",
            "url": "https://gtmstacker.com/registry/tool/deepseek-harness/",
            "applicationCategory": "DeveloperApplication",
            "offers": {
              "@type": "Offer",
              "price": 0,
              "priceCurrency": "USD"
            }
          },
          {
            "@type": "SoftwareApplication",
            "name": "HarnessRouter",
            "url": "https://gtmstacker.com/registry/tool/harnessrouter/",
            "applicationCategory": "DeveloperApplication",
            "offers": {
              "@type": "Offer",
              "price": 0,
              "priceCurrency": "USD"
            }
          }
        ]
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/strands-harness-sdk/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "AI Infrastructure",
            "item": "https://gtmstacker.com/registry/category/ai-infrastructure/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "Strands harness-sdk",
            "item": "https://gtmstacker.com/registry/tool/strands-harness-sdk/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "io.github.strands-agents/harness-sdk",
    "repository": {
      "url": "https://github.com/strands-agents/harness-sdk",
      "source": "github"
    }
  }
}