{ "schemaVersion": "1.0", "item": { "slug": "mnemon", "name": "Mnemon Memory", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/Grivn/mnemon", "canonicalUrl": "https://clawhub.ai/Grivn/mnemon", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/mnemon", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=mnemon", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.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. 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", "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/mnemon" }, "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/mnemon", "agentPageUrl": "https://openagent3.xyz/skills/mnemon/agent", "manifestUrl": "https://openagent3.xyz/skills/mnemon/agent.json", "briefUrl": "https://openagent3.xyz/skills/mnemon/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": "1. Install the binary", "body": "Homebrew (macOS / Linux):\n\nbrew install mnemon-dev/tap/mnemon\n\nGo install:\n\ngo install github.com/mnemon-dev/mnemon@latest" }, { "title": "2. Set up OpenClaw integration", "body": "mnemon setup --target openclaw --yes\n\nThis single command deploys all components:\n\nSkill → ~/.openclaw/skills/mnemon/SKILL.md\nHook → ~/.openclaw/hooks/mnemon-prime/ (agent:bootstrap — injects behavioral guide)\nPlugin → ~/.openclaw/extensions/mnemon/ (remind, nudge, compact hooks)\nPrompts → ~/.mnemon/prompt/ (guide.md, skill.md)\n\nRestart the OpenClaw gateway to activate." }, { "title": "3. Customize (optional)", "body": "Edit ~/.mnemon/prompt/guide.md to tune recall/remember behavior.\n\nPlugin hooks are configured in ~/.openclaw/openclaw.json:\n\n{\n \"plugins\": {\n \"entries\": {\n \"mnemon\": {\n \"enabled\": true,\n \"config\": {\n \"remind\": true,\n \"nudge\": true,\n \"compact\": false\n }\n }\n }\n }\n}\n\nHookDefaultDescriptionremindonRecall relevant memories + remind agent on each messagenudgeonSuggest remember sub-agent after each replycompactoffSave key insights before context compaction" }, { "title": "4. Uninstall", "body": "mnemon setup --eject --target openclaw --yes" }, { "title": "Workflow", "body": "Remember: mnemon remember \"\" --cat --imp <1-5> --entities \"e1,e2\" --source agent\n\nDiff is built-in: duplicates skipped, conflicts auto-replaced.\nOutput includes action (added/updated/skipped), semantic_candidates, causal_candidates.\n\n\nLink (evaluate candidates from step 1 — use judgment, not mechanical rules):\n\nReview causal_candidates: does a genuine cause-effect relationship exist? causal_signal is regex-based and prone to false positives — only link if the memories are truly causally related.\nReview semantic_candidates: are these memories meaningfully related? High similarity alone is not sufficient — skip candidates that share keywords but discuss unrelated topics.\nSyntax: mnemon link --type --weight <0-1> [--meta '']\n\n\nRecall: mnemon recall \"\" --limit 10" }, { "title": "Commands", "body": "mnemon remember \"\" --cat --imp <1-5> --entities \"e1,e2\" --source agent\nmnemon link --type --weight <0-1> [--meta '']\nmnemon recall \"\" --limit 10\nmnemon search \"\" --limit 10\nmnemon forget \nmnemon related --edge causal\nmnemon gc --threshold 0.4\nmnemon gc --keep \nmnemon status\nmnemon log\nmnemon store list\nmnemon store create \nmnemon store set \nmnemon store remove " }, { "title": "Guardrails", "body": "Use the exec tool to run mnemon commands.\nDo not store secrets, passwords, or tokens.\nCategories: preference · decision · insight · fact · context\nEdge types: temporal · semantic · causal · entity\nMax 8,000 chars per insight." } ], "body": "mnemon\nInstall & Configure\n1. Install the binary\n\nHomebrew (macOS / Linux):\n\nbrew install mnemon-dev/tap/mnemon\n\n\nGo install:\n\ngo install github.com/mnemon-dev/mnemon@latest\n\n2. Set up OpenClaw integration\nmnemon setup --target openclaw --yes\n\n\nThis single command deploys all components:\n\nSkill → ~/.openclaw/skills/mnemon/SKILL.md\nHook → ~/.openclaw/hooks/mnemon-prime/ (agent:bootstrap — injects behavioral guide)\nPlugin → ~/.openclaw/extensions/mnemon/ (remind, nudge, compact hooks)\nPrompts → ~/.mnemon/prompt/ (guide.md, skill.md)\n\nRestart the OpenClaw gateway to activate.\n\n3. Customize (optional)\n\nEdit ~/.mnemon/prompt/guide.md to tune recall/remember behavior.\n\nPlugin hooks are configured in ~/.openclaw/openclaw.json:\n\n{\n \"plugins\": {\n \"entries\": {\n \"mnemon\": {\n \"enabled\": true,\n \"config\": {\n \"remind\": true,\n \"nudge\": true,\n \"compact\": false\n }\n }\n }\n }\n}\n\nHook\tDefault\tDescription\nremind\ton\tRecall relevant memories + remind agent on each message\nnudge\ton\tSuggest remember sub-agent after each reply\ncompact\toff\tSave key insights before context compaction\n4. Uninstall\nmnemon setup --eject --target openclaw --yes\n\nWorkflow\nRemember: mnemon remember \"\" --cat --imp <1-5> --entities \"e1,e2\" --source agent\nDiff is built-in: duplicates skipped, conflicts auto-replaced.\nOutput includes action (added/updated/skipped), semantic_candidates, causal_candidates.\nLink (evaluate candidates from step 1 — use judgment, not mechanical rules):\nReview causal_candidates: does a genuine cause-effect relationship exist? causal_signal is regex-based and prone to false positives — only link if the memories are truly causally related.\nReview semantic_candidates: are these memories meaningfully related? High similarity alone is not sufficient — skip candidates that share keywords but discuss unrelated topics.\nSyntax: mnemon link --type --weight <0-1> [--meta '']\nRecall: mnemon recall \"\" --limit 10\nCommands\nmnemon remember \"\" --cat --imp <1-5> --entities \"e1,e2\" --source agent\nmnemon link --type --weight <0-1> [--meta '']\nmnemon recall \"\" --limit 10\nmnemon search \"\" --limit 10\nmnemon forget \nmnemon related --edge causal\nmnemon gc --threshold 0.4\nmnemon gc --keep \nmnemon status\nmnemon log\nmnemon store list\nmnemon store create \nmnemon store set \nmnemon store remove \n\nGuardrails\nUse the exec tool to run mnemon commands.\nDo not store secrets, passwords, or tokens.\nCategories: preference · decision · insight · fact · context\nEdge types: temporal · semantic · causal · entity\nMax 8,000 chars per insight." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/Grivn/mnemon", "publisherUrl": "https://clawhub.ai/Grivn/mnemon", "owner": "Grivn", "version": "0.1.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/mnemon", "downloadUrl": "https://openagent3.xyz/downloads/mnemon", "agentUrl": "https://openagent3.xyz/skills/mnemon/agent", "manifestUrl": "https://openagent3.xyz/skills/mnemon/agent.json", "briefUrl": "https://openagent3.xyz/skills/mnemon/agent.md" } }