[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73DS7SQP5YNRAWG6YXQC8DS":3,"skill-same:01M73DS7SQP5YNRAWG6YXQC8DS":51},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M73DS7SQP5YNRAWG6YXQC8DS","mesh-memory",null,"Self-hosted semantic memory for AI agents via MCP. Save worklogs, decisions, and notes, then recall them across sessions by meaning, not keyword. Postgres + pgvector with auto-tagging.","Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fmesh-memory\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: mesh-memory\ndescription: \"Self-hosted semantic memory for AI agents via MCP. Save worklogs, decisions, and notes, then recall them across sessions by meaning, not keyword. Postgres + pgvector with auto-tagging.\"\nrisk: safe\nsource: dklymentiev\u002Fmesh-memory (MIT)\ndate_added: \"2026-05-23\"\n---\n\n# Mesh Memory\n\nMesh Memory is a self-hosted semantic memory service with a built-in MCP server. It stores documents (worklogs, decisions, notes, research) in PostgreSQL with pgvector and retrieves them by meaning, so a query like \"what database did we pick?\" surfaces a saved note that says \"chose Redis for caching\" even with zero keyword overlap. Embeddings are generated locally with `multilingual-e5-base` (768 dimensions); the core flow requires no external API keys.\n\nUse this skill when an agent needs persistent memory across sessions: saving its own work, recalling prior decisions, or building a project knowledge base shared between multiple agents.\n\n## When to Use This Skill\n\n- Saving a session worklog, decision, or research note so a later session can find it.\n- Recalling past work by topic when you do not remember the exact words you used.\n- Sharing a long-lived knowledge base across multiple agents, terminals, or teammates.\n- Organizing context by role or project through workspaces (one workspace per role\u002Fproject).\n- Looking up structured tags (e.g. all `type:decision` entries from one project).\n\n## Prerequisites\n\n- A running Mesh Memory instance reachable from the MCP server. Local Docker is the common path -- `docker compose up -d` in the upstream repo brings it up; see https:\u002F\u002Fgithub.com\u002Fdklymentiev\u002Fmesh-memory for the full Quick Start.\n- The MCP server (`mcp_server.py`) registered with your client (Claude Code, Cursor, Claude Desktop, or any other MCP-aware agent).\n- `MESH_API_URL` pointing at the running instance (default: `http:\u002F\u002Flocalhost:8000`).\n\n## Setup\n\nRegister the MCP server in your client configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"mesh\": {\n      \"command\": \"python3\",\n      \"args\": [\"\u002Fpath\u002Fto\u002Fmesh-memory\u002Fmcp_server.py\"],\n      \"env\": {\n        \"MESH_API_URL\": \"http:\u002F\u002Flocalhost:8000\"\n      }\n    }\n  }\n}\n```\n\nWhen the server is reachable, the 13 tools listed below become available.\n\n## MCP Tools\n\n| Tool | Purpose |\n|------|---------|\n| `mesh_focus` | Switch the active workspace (optionally prefetch recent docs). |\n| `mesh_add` | Save a document with optional tags. Auto-adds `date:YYYY-MM-DD` and `source:`. |\n| `mesh_update` | Update content, tags, or pinned status of an existing document. |\n| `mesh_delete` | Delete a document by GUID. |\n| `mesh_get` | Fetch a single document by GUID. |\n| `mesh_search` | Semantic search by query, optionally across multiple workspaces with weights. |\n| `mesh_bytag` | List documents that match one or more tags (AND logic). |\n| `mesh_recent` | List most recently created documents, optionally filtered by `type:` tag. |\n| `mesh_projects` | List per-project document counts (uses `guid:` tag as project marker). |\n| `mesh_tags` | List existing tags with counts; optional prefix filter. |\n| `mesh_versions` | Show the version chain of a document (similarity-linked revisions). |\n| `mesh_stats` | Memory statistics for the active workspace. |\n| `mesh_schema` | Show the tag schema (recognized prefixes and types). |\n\n## Workflows\n\n### Save a session worklog\n\nAfter completing work, persist it for future sessions:\n\n```\nmesh_add(\n  content=\"Investigated 502s on the checkout flow. Root cause: missing CORS header on the cart API. Fix shipped in commit abc123.\",\n  tags=\"type:worklog,topic:checkout,date:2026-05-23\",\n  workspace=\"developer\"\n)\n```\n\n`date:` and `source:` are added automatically when omitted. Type and topic tags are inferred from nearest neighbors after the embedding completes (5-10 seed documents required before inference kicks in).\n\n### Recall past work by meaning\n\nSearch across sessions for related context, even with different vocabulary:\n\n```\nmesh_search(query=\"checkout was failing for some users\", limit=5, workspace=\"developer\")\n```\n\nThe query shares no keywords with the original note (\"502s\", \"CORS\"), but the embedding-based search surfaces it.\n\n### Switch role \u002F context\n\nFor a multi-role agent, switch the active workspace at the start of a session:\n\n```\nmesh_focus(workspace=\"sysadmin\", prefetch=true, limit=5)\n```\n\nSubsequent calls default to that workspace. Pin a role-prompt document at the top of each workspace so the agent re-orients on every prefetch.\n\n### Cross-workspace search with weights\n\nTo pull context from related domains without diluting the primary signal:\n\n```\nmesh_search(\n  query=\"nginx rate limit recipe\",\n  workspaces={\"sysadmin\": 0.7, \"security\": 0.2, \"developer\": 0.1},\n  limit=10\n)\n```\n\nResults are merged across workspaces and re-scored by workspace weight.\n\n### Structured lookups by tag\n\nWhen you need an exact filter rather than semantic similarity:\n\n```\nmesh_bytag(tags=\"type:decision,status:active,guid:my-project\", limit=20)\n```\n\n## Tag Conventions\n\nMesh accepts arbitrary tags. The recommended prefixes (used by auto-inference and surfaced by `mesh_schema`):\n\n| Prefix | Meaning |\n|--------|---------|\n| `type:worklog` | Completed work; the most common type. |\n| `type:note` | Quick notes, observations. |\n| `type:decision` | Architecture or product decisions. |\n| `type:research` | Investigation results, findings. |\n| `type:task` | Action items. |\n| `type:rfc` | Proposals for review. |\n| `status:active` \u002F `status:completed` \u002F `status:archived` | Lifecycle. |\n| `date:YYYY-MM-DD` | When the document was created (auto-added). |\n| `source:` | How the document arrived (auto-added: `mcp`, `api`, etc.). |\n| `guid:\u003Cproject-id>` | Project marker -- use a consistent slug across all docs of a project. |\n\nWith fewer than ~5-10 documents in a workspace, neighbor inference is skipped; manually tag seed documents until the corpus self-organizes.\n\n## Troubleshooting\n\n**Tool calls fail with connection errors.** The MCP server cannot reach `MESH_API_URL`. Verify the instance is up (`curl $MESH_API_URL\u002Fhealth` returns `{\"status\":\"healthy\"}`) and the env var is set in the MCP config.\n\n**A saved document does not appear in semantic search yet.** Embedding generation runs in the background. After a save, expect a 1-2 second delay before semantic search hits the new document. `mesh_get(guid=...)` confirms the document exists immediately.\n\n**Search returns results from the wrong domain.** The active workspace is not what you expected. Call `mesh_focus(workspace=\"\u003Cname>\")` explicitly, or pass `workspace=` on every call. With no focus and no explicit param, calls land in the `default` workspace.\n\n**Auto-tagging never adds anything.** The workspace has too few documents for neighbor inference (~5-10 minimum). Manually tag a handful of seed documents, then auto-inference takes over.\n\n**A deleted document still appears in a search result.** Embedding indices are eventually consistent; rerun the search after a few seconds, or use `mesh_get(guid=...)` to confirm deletion.\n\n## Limitations\n\n- Mesh is a knowledge store, not a chat memory. Long conversation transcripts should be summarized before being saved.\n- Vector similarity is robust but not perfect; for high-precision structured lookups, prefer `mesh_bytag` over `mesh_search`.\n- Embeddings run on CPU by default; very large corpora (hundreds of thousands of documents) benefit from a dedicated instance and pgvector tuning, not covered here.\n- The optional AI categorizer requires an OpenAI-compatible LLM endpoint and is disabled by default.\n","# Mesh Memory\n\nMesh Memory is a self-hosted semantic memory service with a built-in MCP server. It stores documents (worklogs, decisions, notes, research) in PostgreSQL with pgvector and retrieves them by meaning, so a query like \"what database did we pick?\" surfaces a saved note that says \"chose Redis for caching\" even with zero keyword overlap. Embeddings are generated locally with `multilingual-e5-base` (768 dimensions); the core flow requires no external API keys.\n\nUse this skill when an agent needs persistent memory across sessions: saving its own work, recalling prior decisions, or building a project knowledge base shared between multiple agents.\n\n## When to Use This Skill\n\n- Saving a session worklog, decision, or research note so a later session can find it.\n- Recalling past work by topic when you do not remember the exact words you used.\n- Sharing a long-lived knowledge base across multiple agents, terminals, or teammates.\n- Organizing context by role or project through workspaces (one workspace per role\u002Fproject).\n- Looking up structured tags (e.g. all `type:decision` entries from one project).\n\n## Prerequisites\n\n- A running Mesh Memory instance reachable from the MCP server. Local Docker is the common path -- `docker compose up -d` in the upstream repo brings it up; see https:\u002F\u002Fgithub.com\u002Fdklymentiev\u002Fmesh-memory for the full Quick Start.\n- The MCP server (`mcp_server.py`) registered with your client (Claude Code, Cursor, Claude Desktop, or any other MCP-aware agent).\n- `MESH_API_URL` pointing at the running instance (default: `http:\u002F\u002Flocalhost:8000`).\n\n## Setup\n\nRegister the MCP server in your client configuration:\n\n```json\n{\n  \"mcpServers\": {\n    \"mesh\": {\n      \"command\": \"python3\",\n      \"args\": [\"\u002Fpath\u002Fto\u002Fmesh-memory\u002Fmcp_server.py\"],\n      \"env\": {\n        \"MESH_API_URL\": \"http:\u002F\u002Flocalhost:8000\"\n      }\n    }\n  }\n}\n```\n\nWhen the server is reachable, the 13 tools listed below become available.\n\n## MCP Tools\n\n| Tool | Purpose |\n|------|---------|\n| `mesh_focus` | Switch the active workspace (optionally prefetch recent docs). |\n| `mesh_add` | Save a document with optional tags. Auto-adds `date:YYYY-MM-DD` and `source:`. |\n| `mesh_update` | Update content, tags, or pinned status of an existing document. |\n| `mesh_delete` | Delete a document by GUID. |\n| `mesh_get` | Fetch a single document by GUID. |\n| `mesh_search` | Semantic search by query, optionally across multiple workspaces with weights. |\n| `mesh_bytag` | List documents that match one or more tags (AND logic). |\n| `mesh_recent` | List most recently created documents, optionally filtered by `type:` tag. |\n| `mesh_projects` | List per-project document counts (uses `guid:` tag as project marker). |\n| `mesh_tags` | List existing tags with counts; optional prefix filter. |\n| `mesh_versions` | Show the version chain of a document (similarity-linked revisions). |\n| `mesh_stats` | Memory statistics for the active workspace. |\n| `mesh_schema` | Show the tag schema (recognized prefixes and types). |\n\n## Workflows\n\n### Save a session worklog\n\nAfter completing work, persist it for future sessions:\n\n```\nmesh_add(\n  content=\"Investigated 502s on the checkout flow. Root cause: missing CORS header on the cart API. Fix shipped in commit abc123.\",\n  tags=\"type:worklog,topic:checkout,date:2026-05-23\",\n  workspace=\"developer\"\n)\n```\n\n`date:` and `source:` are added automatically when omitted. Type and topic tags are inferred from nearest neighbors after the embedding completes (5-10 seed documents required before inference kicks in).\n\n### Recall past work by meaning\n\nSearch across sessions for related context, even with different vocabulary:\n\n```\nmesh_search(query=\"checkout was failing for some users\", limit=5, workspace=\"developer\")\n```\n\nThe query shares no keywords with the original note (\"502s\", \"CORS\"), but the embedding-based search surfaces it.\n\n### Switch role \u002F context\n\nFor a multi-role agent, switch the active workspace at the start of a session:\n\n```\nmesh_focus(workspace=\"sysadmin\", prefetch=true, limit=5)\n```\n\nSubsequent calls default to that workspace. Pin a role-prompt document at the top of each workspace so the agent re-orients on every prefetch.\n\n### Cross-workspace search with weights\n\nTo pull context from related domains without diluting the primary signal:\n\n```\nmesh_search(\n  query=\"nginx rate limit recipe\",\n  workspaces={\"sysadmin\": 0.7, \"security\": 0.2, \"developer\": 0.1},\n  limit=10\n)\n```\n\nResults are merged across workspaces and re-scored by workspace weight.\n\n### Structured lookups by tag\n\nWhen you need an exact filter rather than semantic similarity:\n\n```\nmesh_bytag(tags=\"type:decision,status:active,guid:my-project\", limit=20)\n```\n\n## Tag Conventions\n\nMesh accepts arbitrary tags. The recommended prefixes (used by auto-inference and surfaced by `mesh_schema`):\n\n| Prefix | Meaning |\n|--------|---------|\n| `type:worklog` | Completed work; the most common type. |\n| `type:note` | Quick notes, observations. |\n| `type:decision` | Architecture or product decisions. |\n| `type:research` | Investigation results, findings. |\n| `type:task` | Action items. |\n| `type:rfc` | Proposals for review. |\n| `status:active` \u002F `status:completed` \u002F `status:archived` | Lifecycle. |\n| `date:YYYY-MM-DD` | When the document was created (auto-added). |\n| `source:` | How the document arrived (auto-added: `mcp`, `api`, etc.). |\n| `guid:\u003Cproject-id>` | Project marker -- use a consistent slug across all docs of a project. |\n\nWith fewer than ~5-10 documents in a workspace, neighbor inference is skipped; manually tag seed documents until the corpus self-organizes.\n\n## Troubleshooting\n\n**Tool calls fail with connection errors.** The MCP server cannot reach `MESH_API_URL`. Verify the instance is up (`curl $MESH_API_URL\u002Fhealth` returns `{\"status\":\"healthy\"}`) and the env var is set in the MCP config.\n\n**A saved document does not appear in semantic search yet.** Embedding generation runs in the background. After a save, expect a 1-2 second delay before semantic search hits the new document. `mesh_get(guid=...)` confirms the document exists immediately.\n\n**Search returns results from the wrong domain.** The active workspace is not what you expected. Call `mesh_focus(workspace=\"\u003Cname>\")` explicitly, or pass `workspace=` on every call. With no focus and no explicit param, calls land in the `default` workspace.\n\n**Auto-tagging never adds anything.** The workspace has too few documents for neighbor inference (~5-10 minimum). Manually tag a handful of seed documents, then auto-inference takes over.\n\n**A deleted document still appears in a search result.** Embedding indices are eventually consistent; rerun the search after a few seconds, or use `mesh_get(guid=...)` to confirm deletion.\n\n## Limitations\n\n- Mesh is a knowledge store, not a chat memory. Long conversation transcripts should be summarized before being saved.\n- Vector similarity is robust but not perfect; for high-precision structured lookups, prefer `mesh_bytag` over `mesh_search`.\n- Embeddings run on CPU by default; very large corpora (hundreds of thousands of documents) benefit from a dedicated instance and pgvector tuning, not covered here.\n- The optional AI categorizer requires an OpenAI-compatible LLM endpoint and is disabled by default.\n",{"name":5,"risk":24,"source":25,"date_added":26,"description":7},"safe","dklymentiev\u002Fmesh-memory (MIT)","2026-05-23","main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa","core\u002Fskills\u002Fmesh-memory",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill mesh-memory",{"tool":43,"command":44},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill mesh-memory",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill mesh-memory","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fmesh-memory\u002FSKILL.md",true,[],[52,60,67,75,83,91],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":56,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":71,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]