{
  "schema_version": "openagent.resource.v1",
  "id": "res_odysseus",
  "slug": "odysseus",
  "status": "published",
  "identity": {
    "name": "Odysseus",
    "one_liner": "Self-hosted AI workspace for chat, autonomous agents, deep research, email, documents, and more — local-first, privacy-first, no telemetry.",
    "short_description": "Odysseus is a self-hosted AI workspace that unifies chat, autonomous agents, deep research, email triage, document editing, calendar, notes, memory, and model serving into a single local-first interface. It runs on your own hardware against your own endpoints — no telemetry, no cloud dependency, and full data privacy."
  },
  "classification": {
    "resource_type": "agent",
    "primary_category": "agents",
    "subcategories": [
      "self-hosted",
      "workspace",
      "local-first",
      "privacy",
      "mcp"
    ]
  },
  "positioning": {
    "why_it_matters": "Odysseus matters because it offers a rare combination: a full-featured AI workspace that runs entirely on your own hardware. Most AI tools push you toward a hosted subscription — Odysseus gives you chat, agents, research, email, documents, and model management in one self-contained package, all while keeping your data local.",
    "best_for": [
      "Developers who want a self-hosted all-in-one AI workspace with full data privacy",
      "Users who run local models and need a polished UI for chat, agents, and tools",
      "Teams evaluating self-hosted alternatives to cloud AI workspaces like ChatGPT or Claude"
    ],
    "not_for": [
      "Users who prefer managed cloud services with no self-hosting overhead",
      "Non-technical users unwilling to manage Docker or Python runtimes"
    ],
    "use_cases": [
      "self-hosted-ai",
      "developer-workflow"
    ],
    "target_audience": [
      "developer",
      "agent_builder"
    ],
    "maturity": "active"
  },
  "decision_signals": {
    "deployment_modes": [
      "self_hosted",
      "cloud"
    ],
    "open_source": true,
    "local_first": false,
    "self_hostable": true,
    "has_api": false,
    "has_gui": false,
    "supports_mcp": true,
    "supports_docker": false
  },
  "facts": {
    "license": "MIT",
    "pricing_model": "open_source",
    "github_stars": 36300,
    "github_forks": 4300,
    "github_repo_full_name": "pewdiepie-archdaemon/odysseus",
    "last_verified_at": "2026-06-03"
  },
  "capabilities": {
    "core_capabilities": [
      "mcp",
      "workflow-orchestration"
    ],
    "interfaces": [
      "repo"
    ]
  },
  "links": {
    "primary_url": "https://github.com/pewdiepie-archdaemon/odysseus",
    "items": [
      {
        "type": "github",
        "label": "GitHub",
        "url": "https://github.com/pewdiepie-archdaemon/odysseus"
      },
      {
        "type": "homepage",
        "label": "Homepage",
        "url": "https://pewdiepie-archdaemon.github.io/odysseus/"
      }
    ]
  },
  "media": {
    "thumbnail_url": "https://github.com/pewdiepie-archdaemon.png",
    "og_image_url": "https://github.com/pewdiepie-archdaemon.png",
    "thumbnail_brief": {
      "resource_type": "agent",
      "visual_motif": "clean workspace dashboard with connected tool icons and local-first indicator",
      "background_style": "minimal App Store editorial card using restrained blue accent",
      "title_overlay": "Odysseus",
      "subtitle": "Self-hosted AI workspace",
      "avoid": [
        "busy benchmark poster",
        "unverified logos",
        "marketing-heavy screenshots"
      ]
    }
  },
  "tags": {
    "category": [
      "agent",
      "open-source"
    ],
    "capability": [
      "mcp",
      "workflow-orchestration"
    ],
    "constraint": [
      "open-source",
      "self-hosted",
      "mcp-compatible"
    ],
    "scenario": [
      "self-hosted-ai",
      "developer-workflow"
    ]
  },
  "relationships": {},
  "machine_readable": {
    "canonical_url": "https://www.openagent.bot/agents/odysseus",
    "json_url": "https://www.openagent.bot/agents/odysseus.json",
    "markdown_url": "https://www.openagent.bot/agents/odysseus.md"
  },
  "seo": {
    "title": "Odysseus: AI Agent — Self-hosted AI workspace for chat, autonomous agents, deep research, email, d...",
    "description": "Odysseus is an open-source AI agent. Self-hosted AI workspace for chat, autonomous agents, deep research, email, documents, and more — local-first, privacy-first, no telemetry.. 了解 Odysseus 是什么、适合谁、怎么用。包含官方链接、开源状态和替代方案。"
  },
  "editorial": {
    "featured_reason": "One of the most comprehensive self-hosted AI workspaces, combining chat, agents, deep research, email, documents, and model management in a single local-first package.",
    "trust_note": "Verified from source links and project metadata.",
    "core_strengths": [
      {
        "title": "All-in-one self-hosted workspace",
        "description": "Odysseus combines chat, autonomous agents, deep research, email triage, document editing, calendar, notes, memory, model serving, and more in a single application.",
        "why_it_matters": "Most AI tools require stitching together multiple services. Odysseus gives you everything in one local-first package without sending data to the cloud."
      },
      {
        "title": "Local-first with privacy by default",
        "description": "Runs entirely on your hardware against your own model endpoints. No telemetry, no cloud dependency, and no third-party access to your conversations or data.",
        "why_it_matters": "Privacy is the default architecture, not an afterthought or a premium feature."
      },
      {
        "title": "Agent loop built on opencode with MCP",
        "description": "Odysseus's agent system is built on opencode, with full MCP tool support, web browsing, file access, shell commands, and persistent memory.",
        "why_it_matters": "The agent isn't just a chat wrapper — it can take real actions, use tools, and evolve its own skills over time."
      }
    ],
    "use_case_notes": [
      {
        "title": "All-in-one local AI workspace",
        "description": "Run chat, agents, email, documents, and calendar from a single self-hosted dashboard connected to your own models."
      },
      {
        "title": "Autonomous agent workflows",
        "description": "Give the agent tools (MCP, shell, files, web) and let it plan and execute multi-step tasks autonomously."
      },
      {
        "title": "Local model management and serving",
        "description": "Use the Cookbook to scan your hardware, discover suitable models, download them, and serve them — all from the UI."
      },
      {
        "title": "Privacy-preserving email assistant",
        "description": "Connect your IMAP/SMTP accounts for AI-powered email triage, summaries, and draft replies — without sending email data to third-party services."
      }
    ],
    "compare_notes": [
      {
        "title": "Choose Odysseus for a complete self-hosted workspace",
        "summary": "ChatGPT and Claude offer polished hosted experiences. Odysseus gives you the same breadth of features — chat, agents, research, tools — but runs entirely on your own hardware with no telemetry.",
        "against": "cloud AI workspaces"
      },
      {
        "title": "Choose Odysseus for breadth over specialization",
        "summary": "Dedicated coding agents like Aider or OpenHands go deeper on code tasks. Odysseus is broader — it handles email, calendar, documents, and model management alongside agent capabilities.",
        "against": "single-purpose tools"
      }
    ],
    "getting_started": [
      {
        "label": "Open the GitHub repository",
        "url": "https://github.com/pewdiepie-archdaemon/odysseus",
        "type": "github"
      },
      {
        "label": "Visit the official site",
        "url": "https://pewdiepie-archdaemon.github.io/odysseus/",
        "type": "homepage"
      }
    ],
    "command_line": [
      {
        "label": "Install with Docker (recommended)",
        "command": "git clone https://github.com/pewdiepie-archdaemon/odysseus.git && cd odysseus && docker compose up -d --build",
        "description": "Clone the repository and start Odysseus with Docker. Open http://localhost:7000 when containers are healthy."
      },
      {
        "label": "Install natively on Linux/macOS",
        "command": "git clone https://github.com/pewdiepie-archdaemon/odysseus.git && cd odysseus && python3 -m venv venv && source venv/bin/activate && pip install -r requirements.txt && python setup.py && python -m uvicorn app:app --host 127.0.0.1 --port 7000",
        "description": "Native install requires Python 3.11+. The Cookbook feature also needs tmux for background model operations."
      },
      {
        "label": "Apple Silicon (GPU-accelerated)",
        "command": "git clone https://github.com/pewdiepie-archdaemon/odysseus.git && cd odysseus && ./start-macos.sh",
        "description": "Docker on macOS cannot use Metal GPU. Use the native script for GPU-accelerated model serving on M-series Macs."
      }
    ],
    "seo_article": {
      "intro": "Odysseus is a self-hosted AI workspace that brings together chat, autonomous agents, deep research, email management, document editing, calendar, notes, memory, and model serving into one local-first application. It runs entirely on your hardware against your own endpoints.",
      "what_it_is": "Odysseus is an open agent resource to evaluate by action surface: what software it can operate, which tools or browser steps it touches, and how much supervision it needs before it can run real work.",
      "why_it_matters": "The self-hosted AI space has many single-purpose tools — a chat UI here, an agent framework there, a model server somewhere else. Odysseus combines them into a cohesive workspace, making it practical to run your entire AI stack locally without stitching together disparate services.",
      "how_it_works": "Start with one safe workflow for Odysseus. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation.",
      "use_cases": [
        {
          "title": "Local AI workspace for daily workflows",
          "description": "Use Odysseus as your daily driver for chat, research, email, documents, and calendar — all connected to your own local or API-hosted models."
        },
        {
          "title": "Autonomous task execution with MCP tools",
          "description": "Give the agent access to MCP servers, shell, files, and web search. Let it plan and execute multi-step tasks while you supervise."
        },
        {
          "title": "Private email assistant",
          "description": "Connect IMAP/SMTP accounts for AI-powered summarization, auto-tagging, spam triage, and draft replies — all processed locally."
        },
        {
          "title": "Model discovery and serving",
          "description": "Use the Cookbook to scan hardware, browse 270+ catalogued models by VRAM fit score, download, and serve them — all from the UI."
        }
      ],
      "alternatives": [
        {
          "title": "Use Odysseus for breadth; dedicated tools for depth",
          "summary": "Aider, OpenHands, and Claude Code are more focused on coding. Odysseus offers a broader workspace — email, documents, calendar, model serving — alongside agent capabilities.",
          "against": "specialized agents"
        },
        {
          "title": "Use cloud workspaces for zero-setup convenience",
          "summary": "ChatGPT and Claude require no setup and offer polished hosted experiences. Odysseus requires Docker or Python setup but keeps all data local with no telemetry.",
          "against": "ChatGPT / Claude"
        }
      ],
      "getting_started": [
        {
          "label": "Read the README",
          "url": "https://github.com/pewdiepie-archdaemon/odysseus",
          "type": "github"
        },
        {
          "label": "Visit the official site",
          "url": "https://pewdiepie-archdaemon.github.io/odysseus/",
          "type": "homepage"
        }
      ],
      "faq": [
        {
          "question": "What should I check before using Odysseus?",
          "answer": "Start with one safe workflow for Odysseus. Inspect official setup instructions, required credentials, execution logs, approval points, and failure recovery before expanding from a sandbox task into production automation."
        },
        {
          "question": "Is Odysseus open source?",
          "answer": "Odysseus is listed with MIT based on the official source links in this profile. Re-check the repository, model card, or docs before production use."
        },
        {
          "question": "Who should evaluate Odysseus?",
          "answer": "Odysseus is most worth evaluating for developers who want a self-hosted all-in-one AI workspace with full data privacy."
        },
        {
          "question": "Does Odysseus require a GPU?",
          "answer": "No. Odysseus connects to any LLM endpoint — local or remote. The Cookbook model serving is optional and GPU-dependent. You can use it with API providers like OpenAI, Anthropic, or OpenRouter without any local GPU."
        },
        {
          "question": "How does Odysseus compare to running separate tools?",
          "answer": "Odysseus combines chat, agents, deep research, email, documents, calendar, and model management into one application. The tradeoff is breadth over specialization — dedicated tools may go deeper on specific tasks."
        }
      ]
    }
  },
  "timestamps": {
    "created_at": "2026-06-03T00:00:00.000Z",
    "updated_at": "2026-06-03T00:00:00.000Z",
    "published_at": "2026-06-03T00:00:00.000Z"
  }
}