{ "schemaVersion": "1.0", "item": { "slug": "lily-memory", "name": "Lily Memory Plugin", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/kevinodell/lily-memory", "canonicalUrl": "https://clawhub.ai/kevinodell/lily-memory", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/lily-memory", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=lily-memory", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "CHANGELOG.md", "README.md", "SKILL.md", "index.js", "lib/budget.js", "lib/capture.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/lily-memory" }, "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/lily-memory", "agentPageUrl": "https://openagent3.xyz/skills/lily-memory/agent", "manifestUrl": "https://openagent3.xyz/skills/lily-memory/agent.json", "briefUrl": "https://openagent3.xyz/skills/lily-memory/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": "Lily Memory", "body": "Persistent memory plugin for OpenClaw agents. Gives your agent long-term memory that survives session resets, compaction, and restarts." }, { "title": "What It Does", "body": "Auto-recall: Injects relevant memories as context before each LLM turn\nAuto-capture: Extracts facts from conversations and stores them automatically\nHybrid search: SQLite FTS5 keyword search + Ollama vector cosine similarity\nStuck detection: Detects topic repetition and nudges the agent to break loops\nMemory consolidation: Deduplicates entries on startup\nDynamic entities: Config-driven allowlist + runtime tool to add entities\nGraceful degradation: Works without Ollama (keyword-only mode)\nMinimal dependencies: Uses better-sqlite3 for secure parameterized queries + native fetch" }, { "title": "Requirements", "body": "Node.js 18+ (for native fetch)\nbetter-sqlite3 npm package (installed via npm install)\nOptional: Ollama with nomic-embed-text model for semantic search" }, { "title": "Quick Start", "body": "Install the plugin to your extensions directory\nAdd to your openclaw.json:\n\n{\n \"plugins\": {\n \"slots\": { \"memory\": \"lily-memory\" },\n \"entries\": {\n \"lily-memory\": {\n \"enabled\": true,\n \"config\": {\n \"dbPath\": \"~/.openclaw/memory/decisions.db\",\n \"entities\": [\"config\", \"system\"]\n }\n }\n }\n }\n}\n\nRestart the gateway: openclaw gateway restart" }, { "title": "Tools", "body": "ToolDescriptionmemory_searchFTS5 keyword search across all factsmemory_entityLook up all facts for a specific entitymemory_storeSave a fact to persistent memorymemory_semantic_searchVector similarity search via Ollamamemory_add_entityRegister a new entity at runtime" }, { "title": "Configuration", "body": "OptionTypeDefaultDescriptiondbPathstring~/.openclaw/memory/decisions.dbSQLite database pathautoRecallbooleantrueInject memories before each turnautoCapturebooleantrueExtract facts from responsesmaxRecallResultsnumber10Max memories per turnmaxCapturePerTurnnumber5Max facts per responsestuckDetectionbooleantrueTopic repetition detectionvectorSearchbooleantrueOllama semantic searchollamaUrlstringhttp://localhost:11434Ollama endpointembeddingModelstringnomic-embed-textEmbedding modelconsolidationbooleantrueDedup on startupvectorSimilarityThresholdnumber0.5Min cosine similarityentitiesarray[]Additional entity names" }, { "title": "Architecture", "body": "Recall flow: Extract keywords from message -> FTS5 + vector search -> merge and deduplicate -> inject as context\n\nCapture flow: Regex scan for entity: key = value patterns -> validate entity against allowlist -> store to SQLite -> async embed via Ollama\n\nStuck detection: Track top 5 content words per response -> Jaccard similarity -> if 3+ consecutive >60% overlap, inject Reflexion nudge" }, { "title": "License", "body": "MIT" } ], "body": "Lily Memory\n\nPersistent memory plugin for OpenClaw agents. Gives your agent long-term memory that survives session resets, compaction, and restarts.\n\nWhat It Does\nAuto-recall: Injects relevant memories as context before each LLM turn\nAuto-capture: Extracts facts from conversations and stores them automatically\nHybrid search: SQLite FTS5 keyword search + Ollama vector cosine similarity\nStuck detection: Detects topic repetition and nudges the agent to break loops\nMemory consolidation: Deduplicates entries on startup\nDynamic entities: Config-driven allowlist + runtime tool to add entities\nGraceful degradation: Works without Ollama (keyword-only mode)\nMinimal dependencies: Uses better-sqlite3 for secure parameterized queries + native fetch\nRequirements\nNode.js 18+ (for native fetch)\nbetter-sqlite3 npm package (installed via npm install)\nOptional: Ollama with nomic-embed-text model for semantic search\nQuick Start\nInstall the plugin to your extensions directory\nAdd to your openclaw.json:\n{\n \"plugins\": {\n \"slots\": { \"memory\": \"lily-memory\" },\n \"entries\": {\n \"lily-memory\": {\n \"enabled\": true,\n \"config\": {\n \"dbPath\": \"~/.openclaw/memory/decisions.db\",\n \"entities\": [\"config\", \"system\"]\n }\n }\n }\n }\n}\n\nRestart the gateway: openclaw gateway restart\nTools\nTool\tDescription\nmemory_search\tFTS5 keyword search across all facts\nmemory_entity\tLook up all facts for a specific entity\nmemory_store\tSave a fact to persistent memory\nmemory_semantic_search\tVector similarity search via Ollama\nmemory_add_entity\tRegister a new entity at runtime\nConfiguration\nOption\tType\tDefault\tDescription\ndbPath\tstring\t~/.openclaw/memory/decisions.db\tSQLite database path\nautoRecall\tboolean\ttrue\tInject memories before each turn\nautoCapture\tboolean\ttrue\tExtract facts from responses\nmaxRecallResults\tnumber\t10\tMax memories per turn\nmaxCapturePerTurn\tnumber\t5\tMax facts per response\nstuckDetection\tboolean\ttrue\tTopic repetition detection\nvectorSearch\tboolean\ttrue\tOllama semantic search\nollamaUrl\tstring\thttp://localhost:11434\tOllama endpoint\nembeddingModel\tstring\tnomic-embed-text\tEmbedding model\nconsolidation\tboolean\ttrue\tDedup on startup\nvectorSimilarityThreshold\tnumber\t0.5\tMin cosine similarity\nentities\tarray\t[]\tAdditional entity names\nArchitecture\n\nRecall flow: Extract keywords from message -> FTS5 + vector search -> merge and deduplicate -> inject as context\n\nCapture flow: Regex scan for entity: key = value patterns -> validate entity against allowlist -> store to SQLite -> async embed via Ollama\n\nStuck detection: Track top 5 content words per response -> Jaccard similarity -> if 3+ consecutive >60% overlap, inject Reflexion nudge\n\nLicense\n\nMIT" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/kevinodell/lily-memory", "publisherUrl": "https://clawhub.ai/kevinodell/lily-memory", "owner": "kevinodell", "version": "5.2.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/lily-memory", "downloadUrl": "https://openagent3.xyz/downloads/lily-memory", "agentUrl": "https://openagent3.xyz/skills/lily-memory/agent", "manifestUrl": "https://openagent3.xyz/skills/lily-memory/agent.json", "briefUrl": "https://openagent3.xyz/skills/lily-memory/agent.md" } }