{
  "schemaVersion": "1.0",
  "item": {
    "slug": "aura-openclaw",
    "name": "Aura for OpenClaw",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/AuralithInc/aura-openclaw",
    "canonicalUrl": "https://clawhub.ai/AuralithInc/aura-openclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/aura-openclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=aura-openclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "scripts/compile.py",
      "scripts/memory.py",
      "scripts/query.py"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/aura-openclaw"
    },
    "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/aura-openclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/aura-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/aura-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/aura-openclaw/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": "Aura for OpenClaw",
        "body": "Persistent memory and instant knowledge retrieval for your OpenClaw agent. Compile 60+ file formats into queryable .aura archives and give your agent a 3-tier memory that survives sessions, compaction, and restarts.\n\nMemory OS v2.1 (auralith-aura>=0.2.2): Enhanced with temporal decay scoring, noise filtering, deduplication, bloom filters, SimHash fuzzy matching, and tiered priority scoring — zero RAM overhead."
      },
      {
        "title": "Setup",
        "body": "pip install auralith-aura\n\nFor full document support (PDFs, DOCX, etc.):\n\npip install 'aura-core[all]'"
      },
      {
        "title": "Learn an entire codebase",
        "body": "You: Learn my project in ~/repos/api-service\nAgent: 🔥 Compiling ~/repos/api-service...\n       ✅ Compiled 847 files → api-service.aura\n       Indexed: Python (312), TypeScript (201), YAML (44), Markdown (73), JSON (217)\n\nYou: How does the auth middleware handle token refresh?\nAgent: Based on src/middleware/auth.ts (lines 45-89), the auth middleware\n       intercepts expired JWTs by checking the `exp` claim. When expired,\n       it calls `refreshTokenService.rotate()` which issues a new access\n       token and sets it via the `X-Refreshed-Token` response header.\n       The original request is then replayed with the new token."
      },
      {
        "title": "Compile legal docs with PII masking",
        "body": "You: Learn everything in ~/legal but mask any personal info\nAgent: 🔥 Compiling with PII masking enabled...\n       ✅ Compiled → legal.aura\n       Masked: 23 emails, 8 phone numbers, 4 SSNs\n\nYou: What are the termination conditions in the Series A agreement?\nAgent: Per series_a_term_sheet.pdf, Section 7.2 — the agreement may be\n       terminated by either party with 30 days written notice if:\n       (a) material breach remains uncured after 15 business days,\n       (b) insolvency or bankruptcy filing, or\n       (c) failure to meet the minimum revenue threshold in Schedule B..."
      },
      {
        "title": "Remember facts across sessions",
        "body": "You: Remember that our production database is on us-east-1, the staging\n     API key rotates every 30 days, and I prefer verbose error logs.\n\nAgent: ✅ Written to /fact:\n       • Production DB region: us-east-1\n       • Staging API key rotation: 30-day cycle\n       • Preference: verbose error logging\n\n--- next day, new session ---\n\nYou: Set up the deployment config for staging\nAgent: I remember your staging API key rotates every 30 days — I'll add\n       a reminder comment in the config. Also setting error logging to\n       verbose per your preference. Targeting us-east-1 since that's\n       where your production DB lives..."
      },
      {
        "title": "Track decisions across a long project",
        "body": "You: We decided to use PostgreSQL over MongoDB for the user service,\n     and the team agreed on GraphQL for the public API.\n\nAgent: ✅ Written to /episodic:\n       • Architecture decision: PostgreSQL for user service (over MongoDB)\n       • API decision: GraphQL for public-facing API\n\n--- two weeks later ---\n\nYou: Wait, should we use MongoDB for the new analytics service?\nAgent: Based on your earlier decision log — you chose PostgreSQL over\n       MongoDB for the user service citing ACID compliance needs. The\n       analytics service has different requirements (write-heavy, schema\n       flexibility), so MongoDB could make sense here. Want me to draft\n       a comparison?"
      },
      {
        "title": "Compile a Knowledge Base",
        "body": "When the user asks you to \"learn\", \"compile\", \"index\", or \"remember\" files from a directory:\n\npython {SKILL_DIR}/scripts/compile.py <input_directory> <output_file>\n\nOptions:\n\n# Mask PII before compilation\npython {SKILL_DIR}/scripts/compile.py ./data knowledge.aura --pii-mask\n\n# Filter low-quality content\npython {SKILL_DIR}/scripts/compile.py ./data knowledge.aura --min-quality 0.3"
      },
      {
        "title": "Query the Knowledge Base",
        "body": "python {SKILL_DIR}/scripts/query.py knowledge.aura \"search query here\""
      },
      {
        "title": "Agent Memory",
        "body": "Write to memory tiers:\n\npython {SKILL_DIR}/scripts/memory.py write pad \"scratch note\"\npython {SKILL_DIR}/scripts/memory.py write fact \"verified information\"\npython {SKILL_DIR}/scripts/memory.py write episodic \"session event\"\n\nSearch and manage memory:\n\npython {SKILL_DIR}/scripts/memory.py query \"search query\"\npython {SKILL_DIR}/scripts/memory.py list\npython {SKILL_DIR}/scripts/memory.py usage\npython {SKILL_DIR}/scripts/memory.py prune --before 2026-01-01\npython {SKILL_DIR}/scripts/memory.py end-session"
      },
      {
        "title": "Memory Tiers",
        "body": "TierWhat It StoresLifecycle/padWorking notes, scratch space, in-progress thinkingTransient — cleared between sessions/episodicSession transcripts, decisions, conversation historyAuto-archived — retained for reference/factVerified facts, user preferences, learned rulesPersistent — survives indefinitely"
      },
      {
        "title": "Supported File Types",
        "body": "Documents: PDF, DOCX, DOC, RTF, ODT, EPUB, TXT, HTML, PPTX, EML\nData: CSV, TSV, XLSX, XLS, Parquet, JSON, JSONL, YAML, TOML\nCode: Python, JavaScript, TypeScript, Rust, Go, Java, C/C++, and 20+ more\nMarkup: Markdown (.md), reStructuredText, LaTeX"
      },
      {
        "title": "External Endpoints",
        "body": "URLData SentNoneNone\n\nThis skill makes zero network requests. All processing is local."
      },
      {
        "title": "Data Provenance & Trust",
        "body": "Every memory entry stores source (agent/user/system), namespace, timestamp, session_id, and a unique entry_id. Nothing is inferred or synthesized — memory contains only what was explicitly written. No hidden embeddings, no derived data.\n\nmemory.show_usage()                              # Inspect what's stored per tier\nmemory.prune_shards(before_date=\"2026-01-01\")    # Prune by date\nmemory.prune_shards(shard_ids=[\"specific_id\"])   # Delete specific shards\n# Or delete ~/.aura/memory/ to wipe everything"
      },
      {
        "title": "Security & Privacy",
        "body": "No data leaves your machine. All compilation and memory operations run locally.\nThe .aura format uses safetensors (no pickle) — no arbitrary code execution risk.\nMemory files are stored locally at ~/.aura/memory/.\nNo environment variables or API keys are required.\nNo telemetry, analytics, or usage reporting."
      },
      {
        "title": "Model Invocation Note",
        "body": "This skill is autonomously invoked by the agent as part of its normal operation. The agent decides when to compile documents and manage memory based on user requests. You can disable autonomous invocation in your OpenClaw settings."
      },
      {
        "title": "Trust Statement",
        "body": "By using this skill, no data is sent to any external service. All processing happens on your local machine. Only install this skill if you trust Auralith Inc.. Source code for the compiler and RAG components is available on GitHub."
      },
      {
        "title": "Notes",
        "body": "Memory OS provides instant writes and background compilation to durable shards.\nCompiler and RAG components are open source (Apache 2.0). Memory OS is proprietary, free to use.\nFor emphasis weighting and training features, see OMNI Platform."
      }
    ],
    "body": "Aura for OpenClaw\n\nPersistent memory and instant knowledge retrieval for your OpenClaw agent. Compile 60+ file formats into queryable .aura archives and give your agent a 3-tier memory that survives sessions, compaction, and restarts.\n\nMemory OS v2.1 (auralith-aura>=0.2.2): Enhanced with temporal decay scoring, noise filtering, deduplication, bloom filters, SimHash fuzzy matching, and tiered priority scoring — zero RAM overhead.\n\nSetup\npip install auralith-aura\n\n\nFor full document support (PDFs, DOCX, etc.):\n\npip install 'aura-core[all]'\n\nWhat It Looks Like\nLearn an entire codebase\nYou: Learn my project in ~/repos/api-service\nAgent: 🔥 Compiling ~/repos/api-service...\n       ✅ Compiled 847 files → api-service.aura\n       Indexed: Python (312), TypeScript (201), YAML (44), Markdown (73), JSON (217)\n\nYou: How does the auth middleware handle token refresh?\nAgent: Based on src/middleware/auth.ts (lines 45-89), the auth middleware\n       intercepts expired JWTs by checking the `exp` claim. When expired,\n       it calls `refreshTokenService.rotate()` which issues a new access\n       token and sets it via the `X-Refreshed-Token` response header.\n       The original request is then replayed with the new token.\n\nCompile legal docs with PII masking\nYou: Learn everything in ~/legal but mask any personal info\nAgent: 🔥 Compiling with PII masking enabled...\n       ✅ Compiled → legal.aura\n       Masked: 23 emails, 8 phone numbers, 4 SSNs\n\nYou: What are the termination conditions in the Series A agreement?\nAgent: Per series_a_term_sheet.pdf, Section 7.2 — the agreement may be\n       terminated by either party with 30 days written notice if:\n       (a) material breach remains uncured after 15 business days,\n       (b) insolvency or bankruptcy filing, or\n       (c) failure to meet the minimum revenue threshold in Schedule B...\n\nRemember facts across sessions\nYou: Remember that our production database is on us-east-1, the staging\n     API key rotates every 30 days, and I prefer verbose error logs.\n\nAgent: ✅ Written to /fact:\n       • Production DB region: us-east-1\n       • Staging API key rotation: 30-day cycle\n       • Preference: verbose error logging\n\n--- next day, new session ---\n\nYou: Set up the deployment config for staging\nAgent: I remember your staging API key rotates every 30 days — I'll add\n       a reminder comment in the config. Also setting error logging to\n       verbose per your preference. Targeting us-east-1 since that's\n       where your production DB lives...\n\nTrack decisions across a long project\nYou: We decided to use PostgreSQL over MongoDB for the user service,\n     and the team agreed on GraphQL for the public API.\n\nAgent: ✅ Written to /episodic:\n       • Architecture decision: PostgreSQL for user service (over MongoDB)\n       • API decision: GraphQL for public-facing API\n\n--- two weeks later ---\n\nYou: Wait, should we use MongoDB for the new analytics service?\nAgent: Based on your earlier decision log — you chose PostgreSQL over\n       MongoDB for the user service citing ACID compliance needs. The\n       analytics service has different requirements (write-heavy, schema\n       flexibility), so MongoDB could make sense here. Want me to draft\n       a comparison?\n\nCommands\nCompile a Knowledge Base\n\nWhen the user asks you to \"learn\", \"compile\", \"index\", or \"remember\" files from a directory:\n\npython {SKILL_DIR}/scripts/compile.py <input_directory> <output_file>\n\n\nOptions:\n\n# Mask PII before compilation\npython {SKILL_DIR}/scripts/compile.py ./data knowledge.aura --pii-mask\n\n# Filter low-quality content\npython {SKILL_DIR}/scripts/compile.py ./data knowledge.aura --min-quality 0.3\n\nQuery the Knowledge Base\npython {SKILL_DIR}/scripts/query.py knowledge.aura \"search query here\"\n\nAgent Memory\n\nWrite to memory tiers:\n\npython {SKILL_DIR}/scripts/memory.py write pad \"scratch note\"\npython {SKILL_DIR}/scripts/memory.py write fact \"verified information\"\npython {SKILL_DIR}/scripts/memory.py write episodic \"session event\"\n\n\nSearch and manage memory:\n\npython {SKILL_DIR}/scripts/memory.py query \"search query\"\npython {SKILL_DIR}/scripts/memory.py list\npython {SKILL_DIR}/scripts/memory.py usage\npython {SKILL_DIR}/scripts/memory.py prune --before 2026-01-01\npython {SKILL_DIR}/scripts/memory.py end-session\n\nMemory Tiers\nTier\tWhat It Stores\tLifecycle\n/pad\tWorking notes, scratch space, in-progress thinking\tTransient — cleared between sessions\n/episodic\tSession transcripts, decisions, conversation history\tAuto-archived — retained for reference\n/fact\tVerified facts, user preferences, learned rules\tPersistent — survives indefinitely\nSupported File Types\n\nDocuments: PDF, DOCX, DOC, RTF, ODT, EPUB, TXT, HTML, PPTX, EML Data: CSV, TSV, XLSX, XLS, Parquet, JSON, JSONL, YAML, TOML Code: Python, JavaScript, TypeScript, Rust, Go, Java, C/C++, and 20+ more Markup: Markdown (.md), reStructuredText, LaTeX\n\nExternal Endpoints\nURL\tData Sent\nNone\tNone\n\nThis skill makes zero network requests. All processing is local.\n\nData Provenance & Trust\n\nEvery memory entry stores source (agent/user/system), namespace, timestamp, session_id, and a unique entry_id. Nothing is inferred or synthesized — memory contains only what was explicitly written. No hidden embeddings, no derived data.\n\nmemory.show_usage()                              # Inspect what's stored per tier\nmemory.prune_shards(before_date=\"2026-01-01\")    # Prune by date\nmemory.prune_shards(shard_ids=[\"specific_id\"])   # Delete specific shards\n# Or delete ~/.aura/memory/ to wipe everything\n\nSecurity & Privacy\nNo data leaves your machine. All compilation and memory operations run locally.\nThe .aura format uses safetensors (no pickle) — no arbitrary code execution risk.\nMemory files are stored locally at ~/.aura/memory/.\nNo environment variables or API keys are required.\nNo telemetry, analytics, or usage reporting.\nModel Invocation Note\n\nThis skill is autonomously invoked by the agent as part of its normal operation. The agent decides when to compile documents and manage memory based on user requests. You can disable autonomous invocation in your OpenClaw settings.\n\nTrust Statement\n\nBy using this skill, no data is sent to any external service. All processing happens on your local machine. Only install this skill if you trust Auralith Inc.. Source code for the compiler and RAG components is available on GitHub.\n\nNotes\nMemory OS provides instant writes and background compilation to durable shards.\nCompiler and RAG components are open source (Apache 2.0). Memory OS is proprietary, free to use.\nFor emphasis weighting and training features, see OMNI Platform."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/AuralithInc/aura-openclaw",
    "publisherUrl": "https://clawhub.ai/AuralithInc/aura-openclaw",
    "owner": "AuralithInc",
    "version": "0.1.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/aura-openclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/aura-openclaw",
    "agentUrl": "https://openagent3.xyz/skills/aura-openclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/aura-openclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/aura-openclaw/agent.md"
  }
}