{
  "schemaVersion": "1.0",
  "item": {
    "slug": "lightningprox",
    "name": "Lightningprox",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/unixlamadev-spec/lightningprox",
    "canonicalUrl": "https://clawhub.ai/unixlamadev-spec/lightningprox",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/lightningprox",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lightningprox",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "lightningprox.json"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/lightningprox"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/lightningprox",
    "agentPageUrl": "https://openagent3.xyz/skills/lightningprox/agent",
    "manifestUrl": "https://openagent3.xyz/skills/lightningprox/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/lightningprox/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "LightningProx — Lightning-Native AI Gateway",
        "body": "Pay-per-use access to 19 AI models across 5 providers via Bitcoin Lightning micropayments. No API keys. No subscriptions. No accounts. Pay sats, get inference."
      },
      {
        "title": "When to Use",
        "body": "Accessing AI models without provider API keys\nAutonomous agent inference with Lightning payments\nComparing responses across multiple providers\nLow-cost inference via open models (Llama 4, Mistral, DeepSeek)\nVision tasks (Pixtral)\nCode generation (Codestral, Devstral)\nReasoning tasks (Magistral)"
      },
      {
        "title": "Supported Models (19 total)",
        "body": "ModelProviderTypeclaude-opus-4-5-20251101AnthropicChatgpt-4-turboOpenAIChatmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8Together.aiChatmeta-llama/Llama-3.3-70B-Instruct-TurboTogether.aiChatmeta-llama/Meta-Llama-3.1-70B-Instruct-TurboTogether.aiChatmistralai/Mixtral-8x7B-Instruct-v0.1Together.aiChatdeepseek-ai/DeepSeek-V3Together.aiChatmistral-large-latestMistralChatmistral-medium-latestMistralChatmistral-small-latestMistralChatopen-mistral-nemoMistralChatcodestral-latestMistralCodedevstral-latestMistralAgentic Codepixtral-large-latestMistralVisionmagistral-medium-latestMistralReasoninggemini-2.5-flashGoogleChatgemini-2.5-proGoogleChatgemini-3-flash-previewGoogleChatgemini-3-pro-previewGoogleChat"
      },
      {
        "title": "Option A — Spend Token (recommended for repeat use)",
        "body": "# 1. Top up at lightningprox.com/topup — pay Lightning invoice, get token\n# 2. Use token directly\ncurl -X POST https://lightningprox.com/v1/messages \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-Spend-Token: $LIGHTNINGPROX_SPEND_TOKEN\" \\\n  -d '{\n    \"model\": \"claude-opus-4-5-20251101\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}],\n    \"max_tokens\": 1000\n  }'"
      },
      {
        "title": "Option B — Pay per request",
        "body": "# 1. Send request without token → get invoice\ncurl -X POST https://lightningprox.com/v1/messages \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"model\": \"gemini-2.5-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}], \"max_tokens\": 100}'\n\n# 2. Pay the Lightning invoice returned\n# 3. Retry with X-Payment-Hash header"
      },
      {
        "title": "Drop-in OpenAI SDK Replacement",
        "body": "npm install lightningprox-openai\n\n// Before: import OpenAI from 'openai'\nimport OpenAI from 'lightningprox-openai'\nconst client = new OpenAI({ apiKey: process.env.LIGHTNINGPROX_SPEND_TOKEN })\n\n// Everything else stays identical:\nconst response = await client.chat.completions.create({\n  model: 'claude-opus-4-5-20251101',\n  messages: [{ role: 'user', content: 'Hello' }]\n})\n\nTwo lines change. Nothing else does."
      },
      {
        "title": "Check Available Models",
        "body": "curl https://lightningprox.com/api/capabilities"
      },
      {
        "title": "Security Manifest",
        "body": "PermissionScopeReasonNetworklightningprox.comAPI calls for AI inferenceEnv ReadLIGHTNINGPROX_SPEND_TOKENAuthentication for prepaid requests"
      },
      {
        "title": "Trust Statement",
        "body": "LightningProx is operated by LPX Digital Group LLC. Payment = authentication. No data stored beyond request logs. No accounts, no KYC. Operated at lightningprox.com."
      }
    ],
    "body": "LightningProx — Lightning-Native AI Gateway\n\nPay-per-use access to 19 AI models across 5 providers via Bitcoin Lightning micropayments. No API keys. No subscriptions. No accounts. Pay sats, get inference.\n\nWhen to Use\nAccessing AI models without provider API keys\nAutonomous agent inference with Lightning payments\nComparing responses across multiple providers\nLow-cost inference via open models (Llama 4, Mistral, DeepSeek)\nVision tasks (Pixtral)\nCode generation (Codestral, Devstral)\nReasoning tasks (Magistral)\nSupported Models (19 total)\nModel\tProvider\tType\nclaude-opus-4-5-20251101\tAnthropic\tChat\ngpt-4-turbo\tOpenAI\tChat\nmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8\tTogether.ai\tChat\nmeta-llama/Llama-3.3-70B-Instruct-Turbo\tTogether.ai\tChat\nmeta-llama/Meta-Llama-3.1-70B-Instruct-Turbo\tTogether.ai\tChat\nmistralai/Mixtral-8x7B-Instruct-v0.1\tTogether.ai\tChat\ndeepseek-ai/DeepSeek-V3\tTogether.ai\tChat\nmistral-large-latest\tMistral\tChat\nmistral-medium-latest\tMistral\tChat\nmistral-small-latest\tMistral\tChat\nopen-mistral-nemo\tMistral\tChat\ncodestral-latest\tMistral\tCode\ndevstral-latest\tMistral\tAgentic Code\npixtral-large-latest\tMistral\tVision\nmagistral-medium-latest\tMistral\tReasoning\ngemini-2.5-flash\tGoogle\tChat\ngemini-2.5-pro\tGoogle\tChat\ngemini-3-flash-preview\tGoogle\tChat\ngemini-3-pro-preview\tGoogle\tChat\nPayment Flow\nOption A — Spend Token (recommended for repeat use)\n# 1. Top up at lightningprox.com/topup — pay Lightning invoice, get token\n# 2. Use token directly\ncurl -X POST https://lightningprox.com/v1/messages \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-Spend-Token: $LIGHTNINGPROX_SPEND_TOKEN\" \\\n  -d '{\n    \"model\": \"claude-opus-4-5-20251101\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}],\n    \"max_tokens\": 1000\n  }'\n\nOption B — Pay per request\n# 1. Send request without token → get invoice\ncurl -X POST https://lightningprox.com/v1/messages \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"model\": \"gemini-2.5-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}], \"max_tokens\": 100}'\n\n# 2. Pay the Lightning invoice returned\n# 3. Retry with X-Payment-Hash header\n\nDrop-in OpenAI SDK Replacement\nnpm install lightningprox-openai\n\n// Before: import OpenAI from 'openai'\nimport OpenAI from 'lightningprox-openai'\nconst client = new OpenAI({ apiKey: process.env.LIGHTNINGPROX_SPEND_TOKEN })\n\n// Everything else stays identical:\nconst response = await client.chat.completions.create({\n  model: 'claude-opus-4-5-20251101',\n  messages: [{ role: 'user', content: 'Hello' }]\n})\n\n\nTwo lines change. Nothing else does.\n\nCheck Available Models\ncurl https://lightningprox.com/api/capabilities\n\nSecurity Manifest\nPermission\tScope\tReason\nNetwork\tlightningprox.com\tAPI calls for AI inference\nEnv Read\tLIGHTNINGPROX_SPEND_TOKEN\tAuthentication for prepaid requests\nTrust Statement\n\nLightningProx is operated by LPX Digital Group LLC. Payment = authentication. No data stored beyond request logs. No accounts, no KYC. Operated at lightningprox.com."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/unixlamadev-spec/lightningprox",
    "publisherUrl": "https://clawhub.ai/unixlamadev-spec/lightningprox",
    "owner": "unixlamadev-spec",
    "version": "1.3.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/lightningprox",
    "downloadUrl": "https://openagent3.xyz/downloads/lightningprox",
    "agentUrl": "https://openagent3.xyz/skills/lightningprox/agent",
    "manifestUrl": "https://openagent3.xyz/skills/lightningprox/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/lightningprox/agent.md"
  }
}