{ "schemaVersion": "1.0", "item": { "slug": "openviking", "name": "OpenViking", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ZaynJarvis/openviking", "canonicalUrl": "https://clawhub.ai/ZaynJarvis/openviking", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/openviking", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openviking", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "scripts/init.sh", "skill.yaml" ], "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", "slug": "openviking", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-06T13:31:14.946Z", "expiresAt": "2026-05-13T13:31:14.946Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openviking", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openviking", "contentDisposition": "attachment; filename=\"openviking-1.0.3.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "openviking" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/openviking" }, "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/openviking", "agentPageUrl": "https://openagent3.xyz/skills/openviking/agent", "manifestUrl": "https://openagent3.xyz/skills/openviking/agent.json", "briefUrl": "https://openagent3.xyz/skills/openviking/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": "OpenViking - Context Database for AI Agents", "body": "OpenViking is ByteDance's open-source Context Database designed for AI Agents — a next-generation RAG system that replaces flat vector storage with a filesystem paradigm for managing memories, resources, and skills.\n\nKey Features:\n\nFilesystem paradigm: Organize context like files with URIs (viking://resources/...)\nTiered context (L0/L1/L2): Abstract → Overview → Full content, loaded on demand\nDirectory recursive retrieval: Better accuracy than flat vector search\nMCP server included: Full RAG pipeline via Model Context Protocol" }, { "title": "Quick Check: Is It Set Up?", "body": "test -f ~/code/openviking/examples/mcp-query/ov.conf && echo \"Ready\" || echo \"Needs setup\"\ncurl -s http://localhost:2033/mcp && echo \"Running\" || echo \"Not running\"" }, { "title": "If Not Set Up → Initialize", "body": "Run the init script (one-time):\n\nbash ~/.openclaw/skills/openviking-mcp/scripts/init.sh\n\nThis will:\n\nClone OpenViking from https://github.com/volcengine/OpenViking\nInstall dependencies with uv sync\nCreate ov.conf template\nPause for you to add API keys (embedding.dense.api_key, vlm.api_key)\n\nRequired: Volcengine/Ark API Keys\n\nConfig KeyPurposeembedding.dense.api_keySemantic search embeddingsvlm.api_keyLLM for answer generation\n\nGet keys from: https://console.volcengine.com/ark" }, { "title": "Start the Server", "body": "cd ~/code/openviking/examples/mcp-query\nuv run server.py\n\nOptions:\n\n--port 2033 - Listen port\n--host 127.0.0.1 - Bind address\n--data ./data - Data directory\n\nServer will be at: http://127.0.0.1:2033/mcp" }, { "title": "Connect to Claude", "body": "claude mcp add --transport http openviking http://localhost:2033/mcp\n\nOr add to ~/.mcp.json:\n\n{\n \"mcpServers\": {\n \"openviking\": {\n \"type\": \"http\",\n \"url\": \"http://localhost:2033/mcp\"\n }\n }\n}" }, { "title": "Tools Available", "body": "ToolDescriptionqueryFull RAG pipeline — search + LLM answersearchSemantic search only, returns docsadd_resourceAdd files, directories, or URLs" }, { "title": "Example Usage", "body": "Once connected via MCP:\n\n\"Query: What is OpenViking?\"\n\"Search: machine learning papers\"\n\"Add https://example.com/article to knowledge base\"\n\"Add ~/documents/report.pdf\"" }, { "title": "Troubleshooting", "body": "IssueFixPort in useuv run server.py --port 2034Auth errorsCheck API keys in ov.confServer not foundEnsure it's running: curl localhost:2033/mcp" }, { "title": "Files", "body": "ov.conf - Configuration (API keys, models)\ndata/ - Vector database storage\nserver.py - MCP server implementation" } ], "body": "OpenViking - Context Database for AI Agents\n\nOpenViking is ByteDance's open-source Context Database designed for AI Agents — a next-generation RAG system that replaces flat vector storage with a filesystem paradigm for managing memories, resources, and skills.\n\nKey Features:\n\nFilesystem paradigm: Organize context like files with URIs (viking://resources/...)\nTiered context (L0/L1/L2): Abstract → Overview → Full content, loaded on demand\nDirectory recursive retrieval: Better accuracy than flat vector search\nMCP server included: Full RAG pipeline via Model Context Protocol\nQuick Check: Is It Set Up?\ntest -f ~/code/openviking/examples/mcp-query/ov.conf && echo \"Ready\" || echo \"Needs setup\"\ncurl -s http://localhost:2033/mcp && echo \"Running\" || echo \"Not running\"\n\nIf Not Set Up → Initialize\n\nRun the init script (one-time):\n\nbash ~/.openclaw/skills/openviking-mcp/scripts/init.sh\n\n\nThis will:\n\nClone OpenViking from https://github.com/volcengine/OpenViking\nInstall dependencies with uv sync\nCreate ov.conf template\nPause for you to add API keys (embedding.dense.api_key, vlm.api_key)\n\nRequired: Volcengine/Ark API Keys\n\nConfig Key\tPurpose\nembedding.dense.api_key\tSemantic search embeddings\nvlm.api_key\tLLM for answer generation\n\nGet keys from: https://console.volcengine.com/ark\n\nStart the Server\ncd ~/code/openviking/examples/mcp-query\nuv run server.py\n\n\nOptions:\n\n--port 2033 - Listen port\n--host 127.0.0.1 - Bind address\n--data ./data - Data directory\n\nServer will be at: http://127.0.0.1:2033/mcp\n\nConnect to Claude\nclaude mcp add --transport http openviking http://localhost:2033/mcp\n\n\nOr add to ~/.mcp.json:\n\n{\n \"mcpServers\": {\n \"openviking\": {\n \"type\": \"http\",\n \"url\": \"http://localhost:2033/mcp\"\n }\n }\n}\n\nTools Available\nTool\tDescription\nquery\tFull RAG pipeline — search + LLM answer\nsearch\tSemantic search only, returns docs\nadd_resource\tAdd files, directories, or URLs\nExample Usage\n\nOnce connected via MCP:\n\n\"Query: What is OpenViking?\"\n\"Search: machine learning papers\"\n\"Add https://example.com/article to knowledge base\"\n\"Add ~/documents/report.pdf\"\n\nTroubleshooting\nIssue\tFix\nPort in use\tuv run server.py --port 2034\nAuth errors\tCheck API keys in ov.conf\nServer not found\tEnsure it's running: curl localhost:2033/mcp\nFiles\nov.conf - Configuration (API keys, models)\ndata/ - Vector database storage\nserver.py - MCP server implementation" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ZaynJarvis/openviking", "publisherUrl": "https://clawhub.ai/ZaynJarvis/openviking", "owner": "ZaynJarvis", "version": "1.0.3", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/openviking", "downloadUrl": "https://openagent3.xyz/downloads/openviking", "agentUrl": "https://openagent3.xyz/skills/openviking/agent", "manifestUrl": "https://openagent3.xyz/skills/openviking/agent.json", "briefUrl": "https://openagent3.xyz/skills/openviking/agent.md" } }