Zentrix Agentic Workbench

Created By
deslito8 months ago
A short summary of what the server does. Example: Modular agentic AI workflows for dataset cleaning and orchestration.
Overview

what is Zentrix Agentic Workbench?

Zentrix Agentic Workbench is a modular AI workflow platform designed for dataset cleaning and orchestration, specifically aimed at generating high-quality datasets for training conversational AI models.

how to use Zentrix Agentic Workbench?

To use the workbench, you can run the main script in two modes: quick training set creation using existing datasets or full pipeline execution to generate everything from scratch.

key features of Zentrix Agentic Workbench?

  • Comprehensive pipeline for dataset generation and cleaning.
  • Integration of synthetic data generation with external datasets.
  • Validation and normalization of datasets to ensure quality.

use cases of Zentrix Agentic Workbench?

  1. Generating balanced datasets for training conversational AI models.
  2. Cleaning and normalizing datasets for improved model performance.
  3. Orchestrating workflows for multi-tool and file-access tasks.

FAQ from Zentrix Agentic Workbench?

  • Can I use my own datasets with Zentrix?

Yes! You can integrate your own datasets into the pipeline for cleaning and normalization.

  • Is there a way to evaluate the dataset quality?

Yes! The project includes tools for evaluating dataset quality using MCP.so.

  • What programming language is used?

The project is implemented in Python.

Server Config

{
  "mcpServers": {
    "zentrix": {
      "command": "node",
      "args": [
        "dist/server.js"
      ],
      "env": {
        "PORT": "3000",
        "NODE_ENV": "production",
        "DATASET_PATH": "/app/datasets/training_set.jsonl",
        "KIMI_API_KEY": "your-kimi-api-key",
        "KIMI_MODEL": "kimi-v1",
        "LOCAL_API_URL": "http://localhost:3000",
        "PROD_API_URL": "https://your-service-name.mcp.so"
      },
      "mounts": {
        "../final_datasets": "/app/datasets"
      }
    }
  }
}
Project Info
Created At
8 months ago
Updated At
8 months ago
Author Name
deslito
Star
-
Language
-
License
-

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

3 hours ago