{ "schemaVersion": "1.0", "item": { "slug": "memory-qdrant", "name": "OpenClaw Memory Qdrant", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/zuiho-kai/memory-qdrant", "canonicalUrl": "https://clawhub.ai/zuiho-kai/memory-qdrant", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/memory-qdrant", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=memory-qdrant", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CHANGELOG.md", "index.js", "openclaw.plugin.json", "package-lock.json", "package.json", "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. 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/memory-qdrant" }, "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/memory-qdrant", "agentPageUrl": "https://openagent3.xyz/skills/memory-qdrant/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-qdrant/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-qdrant/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": "memory-qdrant", "body": "Use when you need your OpenClaw agent to remember and recall information across conversations using semantic search.\n\nLocal semantic memory plugin powered by Qdrant vector database and Transformers.js embeddings. Zero configuration, fully local, no API keys required." }, { "title": "Features", "body": "Semantic search with local Transformers.js embeddings\nIn-memory mode (zero config) or persistent Qdrant storage\nOptional auto-capture of conversation context (opt-in, disabled by default)\nContext-aware memory recall\nFully local, no API keys or external services required" }, { "title": "Installation", "body": "clawhub install memory-qdrant\n\nFirst-time setup: This plugin downloads a 25MB embedding model from Hugging Face on first run and may require build tools for native dependencies (sharp, onnxruntime). See README for detailed installation requirements." }, { "title": "Configuration", "body": "Enable in your OpenClaw config:\n\n{\n \"plugins\": {\n \"memory-qdrant\": {\n \"enabled\": true\n }\n }\n}\n\nOptions:\n\nautoCapture (default: false) - Auto-record conversations. Note: trigger patterns include email/phone regex, so enabling this may capture PII.\nautoRecall (default: true) - Auto-inject relevant memories\nqdrantUrl (optional) - External Qdrant server (leave empty for in-memory)" }, { "title": "Usage", "body": "Three tools available:\n\nmemory_store - Save information\n\nmemory_store({\n text: \"User prefers Opus for complex tasks\",\n category: \"preference\"\n})\n\nmemory_search - Find relevant memories\n\nmemory_search({\n query: \"workflow preferences\",\n limit: 5\n})\n\nmemory_forget - Delete memories\n\nmemory_forget({ memoryId: \"uuid\" })\n// or\nmemory_forget({ query: \"text to forget\" })" }, { "title": "Privacy & Security", "body": "In-memory mode (default): Data cleared on restart\nQdrant mode: Data sent to configured server (use trusted servers only)\nNetwork: Downloads ~25MB model from Hugging Face on first run\nautoCapture: Disabled by default for privacy. Trigger patterns match emails and phone-like numbers, so enabling autoCapture can capture PII." }, { "title": "Technical Details", "body": "Vector DB: Qdrant (in-memory or external)\nEmbeddings: Xenova/all-MiniLM-L6-v2 (local)\nModule: ES6 with factory function pattern" }, { "title": "Links", "body": "GitHub: https://github.com/zuiho-kai/openclaw-memory-qdrant\nIssues: https://github.com/zuiho-kai/openclaw-memory-qdrant/issues" } ], "body": "memory-qdrant\n\nUse when you need your OpenClaw agent to remember and recall information across conversations using semantic search.\n\nLocal semantic memory plugin powered by Qdrant vector database and Transformers.js embeddings. Zero configuration, fully local, no API keys required.\n\nFeatures\nSemantic search with local Transformers.js embeddings\nIn-memory mode (zero config) or persistent Qdrant storage\nOptional auto-capture of conversation context (opt-in, disabled by default)\nContext-aware memory recall\nFully local, no API keys or external services required\nInstallation\nclawhub install memory-qdrant\n\n\nFirst-time setup: This plugin downloads a 25MB embedding model from Hugging Face on first run and may require build tools for native dependencies (sharp, onnxruntime). See README for detailed installation requirements.\n\nConfiguration\n\nEnable in your OpenClaw config:\n\n{\n \"plugins\": {\n \"memory-qdrant\": {\n \"enabled\": true\n }\n }\n}\n\n\nOptions:\n\nautoCapture (default: false) - Auto-record conversations. Note: trigger patterns include email/phone regex, so enabling this may capture PII.\nautoRecall (default: true) - Auto-inject relevant memories\nqdrantUrl (optional) - External Qdrant server (leave empty for in-memory)\nUsage\n\nThree tools available:\n\nmemory_store - Save information\n\nmemory_store({\n text: \"User prefers Opus for complex tasks\",\n category: \"preference\"\n})\n\n\nmemory_search - Find relevant memories\n\nmemory_search({\n query: \"workflow preferences\",\n limit: 5\n})\n\n\nmemory_forget - Delete memories\n\nmemory_forget({ memoryId: \"uuid\" })\n// or\nmemory_forget({ query: \"text to forget\" })\n\nPrivacy & Security\nIn-memory mode (default): Data cleared on restart\nQdrant mode: Data sent to configured server (use trusted servers only)\nNetwork: Downloads ~25MB model from Hugging Face on first run\nautoCapture: Disabled by default for privacy. Trigger patterns match emails and phone-like numbers, so enabling autoCapture can capture PII.\nTechnical Details\nVector DB: Qdrant (in-memory or external)\nEmbeddings: Xenova/all-MiniLM-L6-v2 (local)\nModule: ES6 with factory function pattern\nLinks\nGitHub: https://github.com/zuiho-kai/openclaw-memory-qdrant\nIssues: https://github.com/zuiho-kai/openclaw-memory-qdrant/issues" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/zuiho-kai/memory-qdrant", "publisherUrl": "https://clawhub.ai/zuiho-kai/memory-qdrant", "owner": "zuiho-kai", "version": "1.0.10", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/memory-qdrant", "downloadUrl": "https://openagent3.xyz/downloads/memory-qdrant", "agentUrl": "https://openagent3.xyz/skills/memory-qdrant/agent", "manifestUrl": "https://openagent3.xyz/skills/memory-qdrant/agent.json", "briefUrl": "https://openagent3.xyz/skills/memory-qdrant/agent.md" } }