{ "schemaVersion": "1.0", "item": { "slug": "openclaw-memory-2", "name": "Openclaw Memories", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/arosstale/openclaw-memory-2", "canonicalUrl": "https://clawhub.ai/arosstale/openclaw-memory-2", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/openclaw-memory-2", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-memory-2", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ ".github/workflows/ci.yml", "README.md", "SKILL.md", "package.json", "pnpm-lock.yaml", "src/__tests__/integration.test.ts" ], "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-memory-2" }, "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-memory-2", "agentPageUrl": "https://openagent3.xyz/skills/openclaw-memory-2/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-memory-2/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-memory-2/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": "OpenClaw Memory System", "body": "Three components for agent memory:\n\nALMA — Evolves memory designs through mutation + evaluation (offline)\nObserver — Extracts structured facts from conversations via LLM API (requires API key)\nIndexer — Full-text search over workspace Markdown files (offline)" }, { "title": "Environment Variables", "body": "Observer requires one of:\n\nOPENAI_API_KEY\nANTHROPIC_API_KEY\nOr pass apiKey in config\n\nALMA and Indexer require no keys or network access." }, { "title": "ALMA (Algorithm Learning via Meta-learning Agents)", "body": "Proposes memory system designs, evaluates them, keeps the best. Uses gaussian mutation and simulated annealing to explore the design space.\n\nalma.propose() → design\nalma.evaluate(design.id, metrics) → score \nalma.best() → top design\nalma.top(5) → leaderboard" }, { "title": "Observer", "body": "Sends conversation history to an LLM, gets back structured facts:\n\nKind: world fact / biographical / opinion / observation\nPriority: high / medium / low\nEntities: mentioned people/places\nConfidence: 0.0–1.0 for opinions\n\nFails gracefully — returns empty array if LLM is unavailable." }, { "title": "Indexer", "body": "Chunks workspace Markdown files and indexes them for search:\n\nMEMORY.md — core facts\nmemory/YYYY-MM-DD.md — daily logs\nbank/entities/*.md — entity summaries\nbank/opinions.md — beliefs with confidence\n\nindexer.index() → count of chunks indexed\nindexer.search('query') → ranked results\nindexer.rebuild() → re-index from scratch" }, { "title": "Install", "body": "npm install @artale/openclaw-memory" }, { "title": "Limitations", "body": "Indexer uses an in-memory mock database, not real SQLite FTS5. Search works but ranking is simplified.\nObserver calls remote APIs — not offline. Only ALMA and Indexer work without network.\nNo dashboard — removed in v2 for simplicity." }, { "title": "Source", "body": "5 files, 578 lines, 0 runtime dependencies.\n\nhttps://github.com/arosstale/openclaw-memory" } ], "body": "OpenClaw Memory System\n\nThree components for agent memory:\n\nALMA — Evolves memory designs through mutation + evaluation (offline)\nObserver — Extracts structured facts from conversations via LLM API (requires API key)\nIndexer — Full-text search over workspace Markdown files (offline)\nEnvironment Variables\n\nObserver requires one of:\n\nOPENAI_API_KEY\nANTHROPIC_API_KEY\nOr pass apiKey in config\n\nALMA and Indexer require no keys or network access.\n\nHow It Works\nALMA (Algorithm Learning via Meta-learning Agents)\n\nProposes memory system designs, evaluates them, keeps the best. Uses gaussian mutation and simulated annealing to explore the design space.\n\nalma.propose() → design\nalma.evaluate(design.id, metrics) → score \nalma.best() → top design\nalma.top(5) → leaderboard\n\nObserver\n\nSends conversation history to an LLM, gets back structured facts:\n\nKind: world fact / biographical / opinion / observation\nPriority: high / medium / low\nEntities: mentioned people/places\nConfidence: 0.0–1.0 for opinions\n\nFails gracefully — returns empty array if LLM is unavailable.\n\nIndexer\n\nChunks workspace Markdown files and indexes them for search:\n\nMEMORY.md — core facts\nmemory/YYYY-MM-DD.md — daily logs\nbank/entities/*.md — entity summaries\nbank/opinions.md — beliefs with confidence\nindexer.index() → count of chunks indexed\nindexer.search('query') → ranked results\nindexer.rebuild() → re-index from scratch\n\nInstall\nnpm install @artale/openclaw-memory\n\nLimitations\nIndexer uses an in-memory mock database, not real SQLite FTS5. Search works but ranking is simplified.\nObserver calls remote APIs — not offline. Only ALMA and Indexer work without network.\nNo dashboard — removed in v2 for simplicity.\nSource\n\n5 files, 578 lines, 0 runtime dependencies.\n\nhttps://github.com/arosstale/openclaw-memory" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/arosstale/openclaw-memory-2", "publisherUrl": "https://clawhub.ai/arosstale/openclaw-memory-2", "owner": "arosstale", "version": "2.0.1", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/openclaw-memory-2", "downloadUrl": "https://openagent3.xyz/downloads/openclaw-memory-2", "agentUrl": "https://openagent3.xyz/skills/openclaw-memory-2/agent", "manifestUrl": "https://openagent3.xyz/skills/openclaw-memory-2/agent.json", "briefUrl": "https://openagent3.xyz/skills/openclaw-memory-2/agent.md" } }