Skip to content
OpenSmartRoute
Skillv1.0.0

memory

Short-term (conversation) and long-term (vector) memory for RAG agents.

by lei-jia-xing(0) 0 installs
Free
Sign in to install

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from lei-jia-xing/rag-agent (rag_agent/memory/AGENTS.md). Install upstream with npx skills add lei-jia-xing/rag-agent --skill memory. Copyright stays with the author.

rag_agent/memory/ - Memory Systems

OVERVIEW

Short-term (conversation) and long-term (vector) memory for RAG agents.

STRUCTURE

memory/
├── __init__.py       # Exports memory classes
├── short_term.py     # Conversation history (in-memory)
└── long_term.py      # Vector store memory (FAISS)

WHERE TO LOOK

Task Location
Change history window short_term.py
Add memory persistence short_term.py (currently in-memory only)
Modify vector memory long_term.py

CONVENTIONS

  • Short-term: Session-based, cleared on restart
  • Long-term: Persisted to .vectorstore/

ANTI-PATTERNS

  • long_term.py warning: Logs warning if vector store not initialized - silent empty results

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml
targets:
  - https://api.opensmartroute.ai/api/v1/registry/lei-jia-xing-rag-agent-memory/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

lei-jia-xing-rag-agent-memory.ocm.jsonjson
{
  "ocm": "1",
  "id": "lei-jia-xing-rag-agent-memory",
  "kind": "skill",
  "name": "memory",
  "description": "Short-term (conversation) and long-term (vector) memory for RAG agents.",
  "publisher": "lei-jia-xing",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Short-term (conversation) and long-term (vector) memory for RAG agents."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-agents",
      "repository": "https://github.com/lei-jia-xing/rag-agent",
      "path": "rag_agent/memory/AGENTS.md",
      "ref": "5f9566a423cf9711b9c7f338a1c721f1d86c5ee1",
      "url": "https://github.com/lei-jia-xing/rag-agent/blob/5f9566a423cf9711b9c7f338a1c721f1d86c5ee1/rag_agent/memory/AGENTS.md",
      "key": "lei-jia-xing/rag-agent/rag_agent/memory/AGENTS.md"
    }
  },
  "instructions": "# rag_agent/memory/ - Memory Systems\n\n## OVERVIEW\n\nShort-term (conversation) and long-term (vector) memory for RAG agents.\n\n## STRUCTURE\n\n```\nmemory/\n├── __init__.py       # Exports memory classes\n├── short_term.py     # Conversation history (in-memory)\n└── long_term.py      # Vector store memory (FAISS)\n```\n\n## WHERE TO LOOK\n\n| Task | Location |\n|------|----------|\n| Change history window | short_term.py |\n| Add memory persistence | short_term.py (currently in-memory only) |\n| Modify vector memory | long_term.py |\n\n## CONVENTIONS\n\n- **Short-term**: Session-based, cleared on restart\n- **Long-t",
  "cost": {
    "context_tokens": 187
  }
}

Fetch it by URL: GET /api/v1/registry/lei-jia-xing-rag-agent-memory/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.