{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-10-25T00:00:00Z",
  "id": "com.gtmstacker.registry/tool/agensh",
  "type": "tool",
  "slug": "agensh",
  "canonical_url": "https://gtmstacker.com/registry/tool/agensh/",
  "title": "Agensh (Microsoft Research multi-agent harness for coding agents)",
  "description": "MIT-licensed Microsoft Research harness that runs a team of coding agents as a peer organization: agents share a Gitea workspace, a Mattermost message bus and a shared-context board, with no lead agent assigning work. The research paper scales to 1,024 agents; the public release, open-sourced 2026-10-24, is a single-node Docker Compose setup that needs your own LLM upstream.",
  "category": "mcp-agents",
  "tags": [
    "mcp-agents",
    "ai-infrastructure",
    "coding-agents",
    "multi-agent",
    "agent-orchestration",
    "microsoft",
    "research",
    "self-hosted",
    "open-source"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "82d2ad69e3ec9b4325b88add68d909dcd3b11a392aa1bfd671e7989399f16137",
  "date_published": "2026-10-25T00:00:00Z",
  "date_modified": "2026-10-25T00:00:00Z",
  "source": {
    "name": "Microsoft just open-sourced Agensh, a multi-agent harness that runs up to 1,024 coding agents with no lead agent in charge",
    "url": "https://x.com/Marktechpost/status/2114200105108586623",
    "author": "Marktechpost"
  },
  "license": "MIT",
  "one_liner": "Agensh is Microsoft Research's MIT harness where many coding agents coordinate as peers over a shared repo, chat bus and board, with no lead agent.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_signal": "Free (MIT), no hosted tier; real cost is LLM inference for many concurrent agents plus the Docker host.",
  "pricing_model": "free",
  "who_its_for": "Engineering and GTM-engineering teams experimenting with many parallel coding agents on one large build, who can run Linux infrastructure and pay for heavy LLM inference.",
  "who_its_not_for": "Teams wanting a turnkey agent product: it needs Linux, systemd, cgroup v2, passwordless sudo and a Responses-API upstream with a 272k context window, and the public release is single-node only.",
  "aliases": [
    "microsoft/Agensh"
  ],
  "alternatives": [],
  "secondary_categories": [
    "ai-infrastructure",
    "workflow-automation"
  ],
  "last_verified": "2026-10-25",
  "evidence": {
    "claim_type": "vendor-claim",
    "source_id": "https://github.com/microsoft/Agensh",
    "note": "MIT per GitHub license API and README. Official microsoft org, not a fork; cross-linked with arXiv 2609.26781 and aka.ms/Agensh. As of 2026-10-25: 192 stars, 21 forks, last push 2026-10-23. Benchmark (Microsoft's own, not reproduced): 5 ProgramBench tasks, GPT-5.6-sol, mean pass rate 19.31% with 1 agent vs 28.78% with 128; Pandoc 33.89% to 55.06% at 1,024 agents."
  },
  "caveats": "Benchmark numbers are Microsoft Research's own claims. The 1,024-agent result was a research run; the public release is a single-node setup (REPRODUCE.md release differences). Fresh research release: one squashed commit so far. Inference cost scales with the number of concurrent agents.",
  "lead": "**Agensh** (`microsoft/Agensh`) is an **MIT**-licensed multi-agent harness from **Microsoft Research**. Instead of one lead agent handing out tasks, a team of coding agents works as peers: they share a **Gitea** workspace, talk over a **Mattermost** message bus, and keep shared context on a board service, with each agent running as a GitHub Copilot ACP session.",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 91,
      "text": "**Agensh** (`microsoft/Agensh`) is an **MIT**-licensed multi-agent harness from **Microsoft Research**. Instead of one lead agent handing out tasks, a team of coding agents works as peers: they share a **Gitea** workspace, talk over a **Mattermost** message bus, and keep shared context on a board service, with each agent running as a GitHub Copilot ACP session."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 476,
      "text": "multi-agent harness from **Microsoft Research**. Instead of one lead agent handing out tasks, a team of coding agents works as peers: they share a **Gitea** workspace, talk over a **Mattermost** message bus, and keep shared context on a board service, with each agent running as a GitHub Copilot ACP session.\n\n- SPDX **MIT**, confirmed by the GitHub license API (`license.spdx_id`) and the README (\"Code is licensed under the MIT License\").\n- Identity: official `microsoft` org, not a fork, not archived. The README cross-links the paper (arXiv 2609.26781, \"Agensh: Scaling Organizational Intelligence to 1,024 Agents\") and the project page aka.ms/Agensh. No sign of a lookalike repo.\n- Activity as of 2026-10-25 (GitHub API): **192 stars, 21 forks**. Repo created 2026-08-27; first commit \"Initial release of Agensh\" on 2026-10-22; last push 2026-10-23. README news line: open-sourced 2026-10-24.\n- Self-hosting: yes, but heavy. The public release is a single-node Docker Compose setup plus a standalone single-agent baseline. It needs Linux, Docker Engine with Compose v2, systemd, cgroup v2, passwordless sudo, and your own `LLM_UPSTREAM_TOKEN` for a Responses-API model with a 272k-token window.\n- Pricing: free software, no hosted tier. The cost is model inference across the concurrent agents plus the host.\n- **Vendor claim:** on the five hardest ProgramBench tasks (GPT-5.6-sol, six hours, no internet), mean test-pass rate rose from 19.31% with one agent to 28.78% with 128 agents. On Pandoc it went from 33.89% (1 agent) to 55.06% (1,024 agents). These are Microsoft Research's own numbers, not independently reproduced, and the 1,024-agent run is not what the public release ships.\n- Surfaced via an X post in the 2026-10-25 pull (the post itself returned HTTP 402 and was not used as evidence). Curated and verified in run `2026-10-25-registry-update-01` (step-3 verification, 2026-10-25)."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 207,
      "text": "are Microsoft Research's own numbers, not independently reproduced, and the 1,024-agent run is not what the public release ships. - Surfaced via an X post in the 2026-10-25 pull (the post itself returned HTTP 402 and was not used as evidence). Curated and verified in run `2026-10-25-registry-update-01` (step-3 verification, 2026-10-25).\n\nMost agent setups put one orchestrator in charge and the rest wait for instructions. Agensh tests the other shape: a flat team that coordinates through the same tools a human team uses, a repo, a chat channel and a shared board. For GTM engineering teams building internal tools with agents, it is a readable, MIT-licensed reference for that pattern. The honest read: this is a research harness, not a product. Expect real Linux setup work and a large inference bill before it pays off."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/agensh/index.md",
    "html": "https://gtmstacker.com/registry/tool/agensh/",
    "json": "https://gtmstacker.com/registry/tool/agensh/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/agensh/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/agensh/#software",
        "name": "Agensh (Microsoft Research multi-agent harness for coding agents)",
        "identifier": "io.github.microsoft/Agensh",
        "description": "MIT-licensed Microsoft Research harness that runs a team of coding agents as a peer organization: agents share a Gitea workspace, a Mattermost message bus and a shared-context board, with no lead agent assigning work. The research paper scales to 1,024 agents; the public release, open-sourced 2026-10-24, is a single-node Docker Compose setup that needs your own LLM upstream.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/agensh/",
        "datePublished": "2026-10-25T00:00:00Z",
        "dateModified": "2026-10-25T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "softwareHelp": "https://aka.ms/Agensh",
        "license": "https://spdx.org/licenses/MIT.html",
        "codeRepository": "https://github.com/microsoft/Agensh",
        "keywords": "mcp-agents, ai-infrastructure, workflow-automation, coding-agents, multi-agent, agent-orchestration, microsoft, research, self-hosted, open-source",
        "author": {
          "@type": "Organization",
          "name": "microsoft",
          "url": "https://github.com/microsoft",
          "sameAs": [
            "https://github.com/microsoft/Agensh",
            "https://aka.ms/Agensh"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        }
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/agensh/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "MCP Agents",
            "item": "https://gtmstacker.com/registry/category/mcp-agents/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "Agensh (Microsoft Research multi-agent harness for coding agents)",
            "item": "https://gtmstacker.com/registry/tool/agensh/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "io.github.microsoft/Agensh",
    "repository": {
      "url": "https://github.com/microsoft/Agensh",
      "source": "github"
    },
    "homepage": "https://aka.ms/Agensh"
  }
}