{ "schemaVersion": "1.0", "item": { "slug": "mindcore", "name": "MindCore", "source": "tencent", "type": "skill", "category": "AI 智能", "sourceUrl": "https://clawhub.ai/fatcatMaoFei/mindcore", "canonicalUrl": "https://clawhub.ai/fatcatMaoFei/mindcore", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/mindcore", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mindcore", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "references/ARCHITECTURE.md", "references/CHANGELOG.md", "references/CUSTOMIZATION.md", "references/INTEGRATION.md", "references/README.md" ], "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/mindcore" }, "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/mindcore", "agentPageUrl": "https://openagent3.xyz/skills/mindcore/agent", "manifestUrl": "https://openagent3.xyz/skills/mindcore/agent.json", "briefUrl": "https://openagent3.xyz/skills/mindcore/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": "MindCore — Biomimetic Subconscious Engine", "body": "Give your AI agent autonomous thoughts, emotions, and spontaneous impulses." }, { "title": "What It Does", "body": "MindCore is a standalone background daemon that simulates a subconscious\nmind. It rolls dice every second, modeling the random emergence of thoughts\nlike \"I want milk tea\", \"I'm bored\", or \"I suddenly want to chat\".\n\nWhen a thought's probability accumulates past the firing threshold, the engine\noutputs a JSON signal telling your AI Agent: \"I have something to say.\"" }, { "title": "Architecture", "body": "Layer 0: Noise Generators (3000 nodes)\n ├── Pink Noise (1/f, long-range correlation)\n ├── Ornstein-Uhlenbeck (physiological baseline)\n ├── Hawkes Process (emotional chain reaction)\n └── Markov Chain (attention drift)\n ↓\nLayer 1: Sensor Layer (150 sensors)\n ├── Body State (hunger/fatigue/bio-rhythms)\n ├── Environment (time/weather/noise)\n └── Social Context (interaction/neglect)\n ↓\nLayer 2: Impulse Emergence (150 impulse nodes)\n ├── Synapse Matrix (sensor → impulse mapping)\n ├── Sigmoid Probability + Mood Modulation\n └── Dice Roll → Random Firing\n ↓\nLayer 3: Personality Gate (Softmax Sampling)\n ├── Learnable Personality Weights\n └── Short-Term Memory Topic Boost\n ↓\nLayer 4: Output Template → JSON signal" }, { "title": "Quick Start", "body": "# Install dependencies\npip install -r requirements.txt\n\n# Start the engine\npython main.py\n\nRequires Python 3.8+. On first run, automatically downloads all-MiniLM-L6-v2\nlocal NLP model (~80MB) for synapse matrix generation." }, { "title": "Key Features", "body": "150 Daily Impulses across 9 categories (food, social, entertainment, etc.)\nStochastic, Not Scheduled — Pink Noise + Hawkes Process + Sigmoid probability\nCircadian Rhythms — real clock-driven hunger/thirst/sleep cycles\nShort-Term Memory — 5-slot FIFO buffer with 2-hour exponential decay\nMood Baseline — continuous valence modulation of impulse probability\nTunable Frequency — single BURST_BASE_OFFSET parameter controls activity" }, { "title": "Integration", "body": "MindCore outputs standard JSON and is designed for OpenClaw\nbut compatible with any AI Agent framework that supports external signal injection.\n\nSee references/INTEGRATION.md for detailed integration guide." }, { "title": "File Structure", "body": "main.py — Entry point and engine loop\nengine/ — Core 5-layer pipeline implementation\nengine_supervisor.py — Process supervisor for daemon mode\ndata/ — Runtime data (sensor state, synapse matrix, memory)\njs_bridge/ — JavaScript bridge for OpenClaw integration" }, { "title": "License", "body": "AGPL-3.0 (commercial licensing available — contact zmliu0208@gmail.com)" } ], "body": "MindCore — Biomimetic Subconscious Engine\n\nGive your AI agent autonomous thoughts, emotions, and spontaneous impulses.\n\nWhat It Does\n\nMindCore is a standalone background daemon that simulates a subconscious mind. It rolls dice every second, modeling the random emergence of thoughts like \"I want milk tea\", \"I'm bored\", or \"I suddenly want to chat\".\n\nWhen a thought's probability accumulates past the firing threshold, the engine outputs a JSON signal telling your AI Agent: \"I have something to say.\"\n\nArchitecture\nLayer 0: Noise Generators (3000 nodes)\n ├── Pink Noise (1/f, long-range correlation)\n ├── Ornstein-Uhlenbeck (physiological baseline)\n ├── Hawkes Process (emotional chain reaction)\n └── Markov Chain (attention drift)\n ↓\nLayer 1: Sensor Layer (150 sensors)\n ├── Body State (hunger/fatigue/bio-rhythms)\n ├── Environment (time/weather/noise)\n └── Social Context (interaction/neglect)\n ↓\nLayer 2: Impulse Emergence (150 impulse nodes)\n ├── Synapse Matrix (sensor → impulse mapping)\n ├── Sigmoid Probability + Mood Modulation\n └── Dice Roll → Random Firing\n ↓\nLayer 3: Personality Gate (Softmax Sampling)\n ├── Learnable Personality Weights\n └── Short-Term Memory Topic Boost\n ↓\nLayer 4: Output Template → JSON signal\n\nQuick Start\n# Install dependencies\npip install -r requirements.txt\n\n# Start the engine\npython main.py\n\n\nRequires Python 3.8+. On first run, automatically downloads all-MiniLM-L6-v2 local NLP model (~80MB) for synapse matrix generation.\n\nKey Features\n150 Daily Impulses across 9 categories (food, social, entertainment, etc.)\nStochastic, Not Scheduled — Pink Noise + Hawkes Process + Sigmoid probability\nCircadian Rhythms — real clock-driven hunger/thirst/sleep cycles\nShort-Term Memory — 5-slot FIFO buffer with 2-hour exponential decay\nMood Baseline — continuous valence modulation of impulse probability\nTunable Frequency — single BURST_BASE_OFFSET parameter controls activity\nIntegration\n\nMindCore outputs standard JSON and is designed for OpenClaw but compatible with any AI Agent framework that supports external signal injection.\n\nSee references/INTEGRATION.md for detailed integration guide.\n\nFile Structure\nmain.py — Entry point and engine loop\nengine/ — Core 5-layer pipeline implementation\nengine_supervisor.py — Process supervisor for daemon mode\ndata/ — Runtime data (sensor state, synapse matrix, memory)\njs_bridge/ — JavaScript bridge for OpenClaw integration\nLicense\n\nAGPL-3.0 (commercial licensing available — contact zmliu0208@gmail.com)" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/fatcatMaoFei/mindcore", "publisherUrl": "https://clawhub.ai/fatcatMaoFei/mindcore", "owner": "fatcatMaoFei", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/mindcore", "downloadUrl": "https://openagent3.xyz/downloads/mindcore", "agentUrl": "https://openagent3.xyz/skills/mindcore/agent", "manifestUrl": "https://openagent3.xyz/skills/mindcore/agent.json", "briefUrl": "https://openagent3.xyz/skills/mindcore/agent.md" } }