querying-gemini

costiash/CognivAgent

Reference implementation of an AI Agent using Claude Agent SDK. Transforms videos into knowledge graphs via MCP tools: transcription, entity extraction, graph building, natural language querying.

4 stars

0 forks

Python

85 views

View on GitHub Add to Favorites

Installation

Option 1: Use slash command in Claude Code

/install-skill https://github.com/costiash/CognivAgent/tree/main/.claude/skills/querying-gemini

Option 2: Clone to skills directory

# Global (all projects)

git clone https://github.com/costiash/CognivAgent/tree/main/.claude/skills/querying-gemini ~/.claude/skills/CognivAgent

# Project-specific

git clone https://github.com/costiash/CognivAgent/tree/main/.claude/skills/querying-gemini .claude/skills/CognivAgent

Add MCP server to .cursor/mcp.json:

{
  "mcpServers": {
    "skillz": {
      "command": "npx",
      "args": ["-y", "skillz-mcp", "https://github.com/costiash/CognivAgent/tree/main/.claude/skills/querying-gemini"]
    }
  }
}

Restart Cursor after adding the configuration.

Option 1: Use Gemini CLI command

gemini extensions install https://github.com/costiash/CognivAgent/tree/main/.claude/skills/querying-gemini

Option 2: Clone to extensions directory

git clone https://github.com/costiash/CognivAgent/tree/main/.claude/skills/querying-gemini ~/.gemini/extensions/CognivAgent

Topics

agentic-ai ai-agents anthropic claude claude-agent-sdk entity-extraction fastapi graph-visualization information-extraction knowledge-graph llm mcp mcp-tools networkx nlp open-source openai python research-tools video-transcription