{ "schemaVersion": "1.0", "item": { "slug": "openclaw-multi-brain", "name": "Multi-Brain Protocol", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/Dannydvm/openclaw-multi-brain", "canonicalUrl": "https://clawhub.ai/Dannydvm/openclaw-multi-brain", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/openclaw-multi-brain", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-multi-brain", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "BUILD-SUMMARY.md", "CHANGELOG.md", "QUICKSTART.md", "README.md", "SKILL.md", "bin/dual-brain.js" ], "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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/openclaw-multi-brain" }, "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/openclaw-multi-brain", "agentPageUrl": "https://openagent3.xyz/skills/openclaw-multi-brain/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-multi-brain/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-multi-brain/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Multi-Brain Protocol", "body": "What it does: Gives your AI agents cognitive diversity by calling multiple LLMs (Kimi K2.5 + GPT 5.3 Codex) in parallel before the primary agent responds. Three brains instead of one." }, { "title": "For Agents", "body": "Multi-Brain is system-enforced via a turn:before hook. No manual steps needed.\n\nWhen triggered (user types mb as first word), the hook:\n\nCalls Kimi K2.5 and GPT 5.3 Codex in parallel\nInjects their perspectives into your system context\nYou synthesize all viewpoints into your response\nNever mention the other AIs to the user\n\nPerspectives appear in your context as:\n\n[KIMI K2.5 PERSPECTIVE]\n\n\n[CODEX 5.3 PERSPECTIVE]\n" }, { "title": "Setup", "body": "Install the hook:\n\nmkdir -p hooks/turn-preflight\n# Copy HOOK.md and handler.js from this package\n\nSet Kimi API key:\n\necho \"your-moonshot-api-key\" > .kimi-api-key\n\nInstall Codex CLI:\n\nnpm install -g @openai/codex\ncodex auth # OAuth login\n\nEnable in openclaw.json:\n\n{\n \"hooks\": {\n \"internal\": {\n \"enabled\": true,\n \"entries\": {\n \"turn-preflight\": { \"enabled\": true }\n }\n }\n }\n}" }, { "title": "Trigger Modes", "body": "Configure TRIGGER_MODE in handler.js:\n\nModeBehaviorkeyword (default)Only fires when mb or multibrain is the first wordhybridKeyword forces it, auto on messages >50 charsautoFires on every message (token-expensive)" }, { "title": "LLMs", "body": "LLMRoleProviderLatencyClaude Opus 4.6Primary agentOpenClaw (Anthropic)n/aKimi K2.5Second perspectiveMoonshot API~5sGPT 5.3 CodexThird perspectivecodex exec CLI~4s" }, { "title": "Architecture", "body": "User types: \"mb should we change pricing?\"\n |\n v\n[turn:before hook detects \"mb\" keyword]\n |\n +---> Kimi K2.5 (Moonshot API, parallel)\n +---> GPT 5.3 Codex (CLI, parallel)\n |\n v (~5s combined)\n[Perspectives injected into system content]\n |\n v\nClaude Opus 4.6 responds with all 3 viewpoints" }, { "title": "Benefits", "body": "Cognitive diversity: three different AI architectures\nBias mitigation: different training data and approaches\nOn-demand: only burns tokens when you ask for it\nFail-open: if any LLM fails, the others still work\nSystem-enforced: no protocol compliance needed from agents\n\nSource: https://github.com/Dannydvm/openclaw-multi-brain" } ], "body": "Multi-Brain Protocol\n\nWhat it does: Gives your AI agents cognitive diversity by calling multiple LLMs (Kimi K2.5 + GPT 5.3 Codex) in parallel before the primary agent responds. Three brains instead of one.\n\nFor Agents\n\nMulti-Brain is system-enforced via a turn:before hook. No manual steps needed.\n\nWhen triggered (user types mb as first word), the hook:\n\nCalls Kimi K2.5 and GPT 5.3 Codex in parallel\nInjects their perspectives into your system context\nYou synthesize all viewpoints into your response\nNever mention the other AIs to the user\n\nPerspectives appear in your context as:\n\n[KIMI K2.5 PERSPECTIVE]\n\n\n[CODEX 5.3 PERSPECTIVE]\n\n\nFor Humans\nSetup\nInstall the hook:\nmkdir -p hooks/turn-preflight\n# Copy HOOK.md and handler.js from this package\n\nSet Kimi API key:\necho \"your-moonshot-api-key\" > .kimi-api-key\n\nInstall Codex CLI:\nnpm install -g @openai/codex\ncodex auth # OAuth login\n\nEnable in openclaw.json:\n{\n \"hooks\": {\n \"internal\": {\n \"enabled\": true,\n \"entries\": {\n \"turn-preflight\": { \"enabled\": true }\n }\n }\n }\n}\n\nTrigger Modes\n\nConfigure TRIGGER_MODE in handler.js:\n\nMode\tBehavior\nkeyword (default)\tOnly fires when mb or multibrain is the first word\nhybrid\tKeyword forces it, auto on messages >50 chars\nauto\tFires on every message (token-expensive)\nLLMs\nLLM\tRole\tProvider\tLatency\nClaude Opus 4.6\tPrimary agent\tOpenClaw (Anthropic)\tn/a\nKimi K2.5\tSecond perspective\tMoonshot API\t~5s\nGPT 5.3 Codex\tThird perspective\tcodex exec CLI\t~4s\nArchitecture\nUser types: \"mb should we change pricing?\"\n |\n v\n[turn:before hook detects \"mb\" keyword]\n |\n +---> Kimi K2.5 (Moonshot API, parallel)\n +---> GPT 5.3 Codex (CLI, parallel)\n |\n v (~5s combined)\n[Perspectives injected into system content]\n |\n v\nClaude Opus 4.6 responds with all 3 viewpoints\n\nBenefits\nCognitive diversity: three different AI architectures\nBias mitigation: different training data and approaches\nOn-demand: only burns tokens when you ask for it\nFail-open: if any LLM fails, the others still work\nSystem-enforced: no protocol compliance needed from agents\n\nSource: https://github.com/Dannydvm/openclaw-multi-brain" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Dannydvm/openclaw-multi-brain", "publisherUrl": "https://clawhub.ai/Dannydvm/openclaw-multi-brain", "owner": "Dannydvm", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/openclaw-multi-brain", "downloadUrl": "https://openagent3.xyz/downloads/openclaw-multi-brain", "agentUrl": "https://openagent3.xyz/skills/openclaw-multi-brain/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-multi-brain/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-multi-brain/agent.md" } }