{
  "project_id": "Hal0ai/hal0",
  "repo": "Hal0ai/hal0",
  "name": "hal0",
  "github_url": "https://github.com/Hal0ai/hal0",
  "homepage_url": "https://hal0.dev",
  "language": "Python",
  "license": "Apache-2.0",
  "project_kind": "project",
  "category": [
    "llm_gateway"
  ],
  "tags": [
    "ai",
    "amd-ryzen-ai",
    "fastapi",
    "homelab",
    "igpu",
    "inference",
    "llama-cpp",
    "llm",
    "npu",
    "openai-compatible",
    "rocm",
    "self-hosted",
    "strix-halo",
    "systemd",
    "vue"
  ],
  "description": "Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.",
  "overview": "Use Hal0ai/hal0 when the user needs a llm gateway project with docker, local, cloud deployment options.",
  "alternatives": [
    {
      "repo": "off-grid-ai/OGAD",
      "reason": "Same llm gateway intent with llm_gateway overlap."
    },
    {
      "repo": "Devansh-365/freellm",
      "reason": "Same llm gateway intent with llm_gateway overlap."
    },
    {
      "repo": "andreimerfu/pllm",
      "reason": "Same llm gateway intent with llm_gateway overlap."
    }
  ],
  "related": [
    {
      "repo": "MiXaiLL76/auto_ai_router",
      "reason": "Related to Hal0ai/hal0 through llm gateway category and docker deployment."
    },
    {
      "repo": "frieser/antigravity-proxy",
      "reason": "Related to Hal0ai/hal0 through llm gateway category and docker deployment."
    },
    {
      "repo": "andreimerfu/pllm",
      "reason": "Related to Hal0ai/hal0 through llm gateway category and docker deployment."
    },
    {
      "repo": "vllm-project/vllm",
      "reason": "Related to Hal0ai/hal0 through shared LLM provider dependency context."
    },
    {
      "repo": "Shaivpidadi/FreeRideV3",
      "reason": "Related to Hal0ai/hal0 through llm gateway category and local deployment."
    },
    {
      "repo": "openziti/llm-gateway",
      "reason": "Related to Hal0ai/hal0 through llm gateway category and local deployment."
    },
    {
      "repo": "openai/openai-openapi",
      "reason": "Related to Hal0ai/hal0 through llm gateway category and local deployment."
    },
    {
      "repo": "off-grid-ai/OGAD",
      "reason": "Related to Hal0ai/hal0 through llm gateway category and local deployment."
    }
  ],
  "dependencies": [
    "LLM provider"
  ],
  "deployments": [
    "docker",
    "local",
    "cloud"
  ],
  "difficulty": "beginner",
  "cloudflare_ready": false,
  "use_cases": [
    "route LLM requests",
    "standardize model provider access",
    "add gateway-level controls"
  ],
  "not_good_for": [
    "edge-only Cloudflare Workers deployment without adaptation"
  ],
  "classification": {
    "category": {
      "confidence": "medium",
      "evidence": [
        "Matched \"gateway\" in metadata."
      ]
    },
    "deployment": {
      "confidence": "medium",
      "evidence": [
        "Local usage is assumed for open source repositories unless contradicted."
      ]
    },
    "difficulty": {
      "confidence": "medium",
      "evidence": [
        "Repository has under 10k stars, so complexity is treated conservatively."
      ]
    },
    "cloudflare_ready": {
      "confidence": "high",
      "evidence": [
        "Runtime blocker: python, cuda, gpu.",
        "No Cloudflare deployment signal detected.",
        "No wrangler.toml found in inspected repository files."
      ]
    }
  },
  "quality_signals": {
    "stars": 65,
    "recent_commits": 100,
    "contributors": 2,
    "issue_response_time_hours": null,
    "release_frequency_180d": 51
  },
  "quality_signal_confidence": {
    "stars_30d_delta": "snapshot",
    "stars30d_window_days": 30,
    "commits_30d": "partial",
    "releases_180d": "complete",
    "contributors_90d": "complete"
  },
  "quality_score": 30,
  "agent_score": 63,
  "score": 78,
  "agent_score_breakdown": {
    "documentation": 90,
    "maintenance": 57,
    "deployment": 80,
    "popularity": 36,
    "community": 47
  },
  "git_top_score": 78,
  "git_top_score_breakdown": {
    "community": 66,
    "maintenance": 71,
    "documentation": 84,
    "stability": 100,
    "adoption": 48,
    "agent_readability": 100
  },
  "summary": {
    "tl_dr": "Use Hal0ai/hal0 when the user needs a llm gateway project with docker, local, cloud deployment options.",
    "purpose": "Use Hal0ai/hal0 when the user needs a llm gateway project with docker, local, cloud deployment options.",
    "install": "Run with Docker using the repository's container instructions.",
    "inputs": [
      "model requests",
      "routing config",
      "provider credentials"
    ],
    "outputs": [
      "proxied completions",
      "routed responses",
      "usage metrics"
    ],
    "good_for": [
      "route LLM requests",
      "standardize model provider access",
      "add gateway-level controls",
      "model routing",
      "provider abstraction",
      "LLM proxying"
    ],
    "not_good_for": [
      "edge-only Cloudflare Workers deployment without adaptation",
      "local-only inference",
      "non-LLM services"
    ],
    "deployment": [
      "docker",
      "local",
      "cloud"
    ],
    "alternatives": [
      {
        "repo": "off-grid-ai/OGAD",
        "reason": "Same llm gateway intent with llm_gateway overlap."
      },
      {
        "repo": "Devansh-365/freellm",
        "reason": "Same llm gateway intent with llm_gateway overlap."
      },
      {
        "repo": "andreimerfu/pllm",
        "reason": "Same llm gateway intent with llm_gateway overlap."
      }
    ]
  },
  "evidence": {
    "classification": {
      "category": {
        "confidence": "medium",
        "evidence": [
          "Matched \"gateway\" in metadata."
        ]
      },
      "deployment": {
        "confidence": "medium",
        "evidence": [
          "Local usage is assumed for open source repositories unless contradicted."
        ]
      },
      "difficulty": {
        "confidence": "medium",
        "evidence": [
          "Repository has under 10k stars, so complexity is treated conservatively."
        ]
      },
      "cloudflare_ready": {
        "confidence": "high",
        "evidence": [
          "Runtime blocker: python, cuda, gpu.",
          "No Cloudflare deployment signal detected.",
          "No wrangler.toml found in inspected repository files."
        ]
      }
    },
    "quality_signal_confidence": {
      "stars_30d_delta": "snapshot",
      "stars30d_window_days": 30,
      "commits_30d": "partial",
      "releases_180d": "complete",
      "contributors_90d": "complete"
    },
    "source_fields": [
      "project.description",
      "project.topics",
      "project.language",
      "project.license",
      "agent_card.summary_for_agent",
      "agent_card.use_cases",
      "agent_card.deployment",
      "agent_card.classification",
      "metrics"
    ],
    "caveats": [
      "edge-only Cloudflare Workers deployment without adaptation",
      "Partial or estimated quality signals: commits30d."
    ],
    "confidence_reason": "Evidence is incomplete; use this project as an exploration candidate until classification and quality signals are reviewed.",
    "last_verified_at": "2026-08-12T03:00:41.108Z"
  },
  "caveats": [
    "edge-only Cloudflare Workers deployment without adaptation",
    "Partial or estimated quality signals: commits30d."
  ],
  "confidence_reason": "Evidence is incomplete; use this project as an exploration candidate until classification and quality signals are reviewed.",
  "source_fields": [
    "project.description",
    "project.topics",
    "project.language",
    "project.license",
    "agent_card.summary_for_agent",
    "agent_card.use_cases",
    "agent_card.deployment",
    "agent_card.classification",
    "metrics"
  ],
  "last_verified_at": "2026-08-12T03:00:41.108Z",
  "knowledge": {
    "project": {
      "id": "Hal0ai/hal0",
      "owner": "Hal0ai",
      "name": "hal0",
      "full_name": "Hal0ai/hal0",
      "github_url": "https://github.com/Hal0ai/hal0",
      "homepage_url": "https://hal0.dev",
      "description": "Open-source self-hosted home AI inference platform for AMD Strix Halo — multi-backend slots, OpenAI-compatible gateway, Vue 3 + FastAPI + systemd.",
      "language": "Python",
      "topics": [
        "ai",
        "amd-ryzen-ai",
        "fastapi",
        "homelab",
        "igpu",
        "inference",
        "llama-cpp",
        "llm",
        "npu",
        "openai-compatible",
        "rocm",
        "self-hosted",
        "strix-halo",
        "systemd",
        "vue"
      ],
      "license": "Apache-2.0",
      "stars": 65,
      "forks": 6,
      "open_issues": 88,
      "default_branch": "main",
      "created_at": "2026-05-15T15:27:59Z",
      "updated_at": "2026-08-11T22:57:28Z",
      "pushed_at": "2026-08-12T02:51:32Z",
      "synced_at": "2026-08-12T03:00:41.108Z"
    },
    "agent_card": {
      "project_id": "Hal0ai/hal0",
      "project_kind": "project",
      "category": "llm_gateway",
      "difficulty": "beginner",
      "deployment": [
        "docker",
        "local",
        "cloud"
      ],
      "cloudflare_ready": false,
      "use_cases": [
        "route LLM requests",
        "standardize model provider access",
        "add gateway-level controls"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation"
      ],
      "alternatives": [
        {
          "project_id": "off-grid-ai/OGAD",
          "reason": "Same llm gateway intent with llm_gateway overlap."
        },
        {
          "project_id": "Devansh-365/freellm",
          "reason": "Same llm gateway intent with llm_gateway overlap."
        },
        {
          "project_id": "andreimerfu/pllm",
          "reason": "Same llm gateway intent with llm_gateway overlap."
        }
      ],
      "summary_for_agent": "Use Hal0ai/hal0 when the user needs a llm gateway project with docker, local, cloud deployment options.",
      "classification": {
        "category": {
          "confidence": "medium",
          "evidence": [
            "Matched \"gateway\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "medium",
          "evidence": [
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python, cuda, gpu.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "schema_version": "v1",
      "generated_at": "2026-08-12T03:00:41.108Z"
    },
    "metrics": {
      "project_id": "Hal0ai/hal0",
      "stars_30d_delta": 11,
      "commits_30d": 100,
      "releases_180d": 51,
      "contributors_90d": 2,
      "issue_first_response_median_hours": null,
      "recent_push_days": 0,
      "git_score": 30,
      "maintenance_score": 57,
      "signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 30,
        "commits_30d": "partial",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "calculated_at": "2026-08-12T03:00:41.108Z"
    }
  },
  "resolved_from": {
    "requested_id": "Hal0ai/hal0",
    "resolved_id": "Hal0ai/hal0",
    "resolution": "direct"
  },
  "metadata": {
    "source": "d1",
    "reason": "d1_query",
    "project_count": 1065,
    "generated_at": "2026-08-13T07:13:57.750Z",
    "snapshot_id": "d1:1065:2026-08-13T06:00:43.032Z",
    "latest_synced_at": "2026-08-13T06:00:43.032Z",
    "schema_version": "git-top.knowledge.v1",
    "loaded_project_limit": 2000,
    "truncated": false
  }
}