Novyx MCP

by novyxlabs

434 downloads Not rated yet
GitHub

About

Persistent memory for AI agents. 72 MCP tools for remember, recall, rollback, audit,

Explore

- 72 tools, 6 resources, 3 prompts
- Semantic search with importance scoring
- Undo any operation and time-travel to any point
- Cryptographic hash chain for tamper-proof audit trail
- Structured knowledge graph with confidence scores
- Policy-evaluated agent actions with approval workflows

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Novyx MCP
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

uvx novyx-mcp

No API key needed. Works locally with SQLite out of the box.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "novyx mcp": {
            "novyx-mcp": {
                "command": "uvx",
                "args": [
                    "novyx-mcp"
                ]
            }
        }
    }
}

McpServers

{
    "novyx-mcp": {
        "command": "uvx",
        "args": [
            "novyx-mcp"
        ]
    }
}
Give your AI agents memory that survives across sessions. Remember, recall, rollback, audit — with semantic search, a knowledge graph, and governed actions. ### Quick Start uvx novyx-mcp No API key needed. Works locally with SQLite out of the box. ### What You Get - 72 tools, 6 resources, 3 prompts - Remember & Recall — semantic search with importance scoring - Rollback — undo any operation, time-travel to any point - Audit Trail — cryptographic hash chain, tamper-proof - Knowledge Graph — structured triples with confidence scores - Governed Actions — policy-evaluated agent actions with approval workflows - Eval & Baselines — memory regression testing, CI/CD quality gates - Context Spaces — isolated memory namespaces for multi-agent coordination - Cortex — autonomous memory consolidation, reinforcement, and decay - Replay — time-travel debugging across memory state ### Works With Claude Desktop, Claude Code, Cursor, Windsurf, Cline, and any MCP-compatible client. ### Links - Docs - PyPI - GitHub - Demo
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.