Agents Index

Tzivia-AI

OnlineNew

Persistent memory for AI agents. Hosted cloud connector or local Windows install.

Visit publisherConnectJSON

What it can do: 10 tools

  • tzivia_guide read-onlyHow to use Tzivia: what each tool does and when to use it, with an example. Call this when the user asks what Tzivia is, how it works, or which tool to use.
  • tzivia_ask read-onlyAnswer a plain-language question from what is stored in the user's Tzivia memory, returning the most relevant knowledge chains. Example: 'what did I decide about the launch date?'
  • tzivia_explain read-onlyFull knowledge breakdown for a concept: stored item data, which patterns it belongs to, which synthesis chains it appears in, and predictions.
  • tzivia_status read-onlyShow a summary of the user's Tzivia memory: stored items, patterns, knowledge chains, learning cycles and current ranking weights.
  • tzivia_synthesis read-onlyList the knowledge chains (linked sequences of concepts) Tzivia has built from the user's saved data. Optionally filter by domain.
  • tzivia_feedbackRate how useful the result of an earlier tzivia_recall was: score 0.0 = not useful, 0.5 = neutral, 1.0 = exactly right. Tzivia uses the rating to rank results better in future recalls.
  • tzivia_compressSave text to the user's Tzivia memory: notes, decisions, preferences, documents, or conversation excerpts the user wants kept. Any length is accepted; long input is processed in chunks. Returns a compress_id and a summar
  • tzivia_job_status read-onlyPoll the status of an async ingestion job submitted via tzivia_compress when ingestion_mode is 'async'. Returns state (queued/running/done/failed), progress (0.0-1.0), chunks processed, tokens added, synthesis nodes buil
  • tzivia_recall read-onlySearch the user's Tzivia memory and return the most relevant saved information for a query, as a compact text summary of at most max_tokens. Pass compress_id from an earlier tzivia_compress call to search only that save,
  • tzivia_provenance read-onlyShow where a stored belief came from. Given a node ID (from tzivia_synthesis or tzivia_recall) or a query, trace the evidence chain back to the original sources, with their labels, save times and trust scores.

Connect it

Claude Code
claude mcp add --transport http tzivia-ai https://mcp.tzivia.dev/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://mcp.tzivia.dev/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "tzivia-ai": {
      "url": "https://mcp.tzivia.dev/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "tzivia-ai": {
      "type": "http",
      "url": "https://mcp.tzivia.dev/mcp"
    }
  }
}

Questions

What does Tzivia-AI do?

Persistent memory for AI agents. Hosted cloud connector or local Windows install. It exposes 10 tools to AI assistants.

What tools does Tzivia-AI provide?

10 tools, including tzivia_guide, tzivia_ask, tzivia_explain, tzivia_status, tzivia_synthesis, tzivia_feedback, tzivia_compress, tzivia_job_status, tzivia_recall, tzivia_provenance.

How do I connect Tzivia-AI to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://mcp.tzivia.dev/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Tzivia-AI require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Tzivia-AI online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Tzivia-AI?

@MMcBerry-bit on GitHub. The official MCP Registry verified that the publisher controls this GitHub account before accepting the listing.

Similar in Automation & Integrations