What prerequisites are needed?
Ollama must be installed (unless using Together.ai API) and the virtual environment must be activated correctly.
@ricardoborges
Basic information
LLM chat app for integration tests using llama-stack-client, llama, Ollama, MCP, Tools
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"chatlab": {
"command": "uv",
"args": [
"venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
This document provides step-by-step instructions for setting up the development environment and running the ChatLab application. It uses Ollama or Together.ai for LLM inference and LLama-Stack to manage the inference environment.
Follow the installation steps sequentially: install Ollama or obtain a Together.ai API key, set up LLama-Stack using uv and a virtual environment, clone the repository, install dependencies via uv pip install -r myproject.toml, set environment variables (TAVILY_SEARCH_API_KEY, TOGETHER_API_KEY or DEFAULT_STACK="Ollama"), then run gradio main.py.
Ollama must be installed (unless using Together.ai API) and the virtual environment must be activated correctly.
Ollama or Together.ai API key, LLama-Stack, Python packages as listed in `myproject.toml`, and a Tavily search API key for search functionality.
API keys are stored in a `.env` file (TAVILY_SEARCH_API_KEY, TOGETHER_API_KEY). Model inference runs either locally (Ollama) or on Together.ai servers.
The guide does not mention any specific limits; troubleshooting covers checking services and dependencies.
No transports are mentioned. Authentication uses API keys for Together.ai and Tavily; local Ollama requires no external auth.

scvd.store is an evidence observatory for agentic commerce. Independent signed observation of what other people's endpoints, artifacts and payments actually did among other things. USDC on Base, Arbitrum One, World Chain
TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g

Operate a real LinkedIn account from your AI agent. 52 tools for the inbox, invitations, network, profiles, Sales Navigator search in plain language, posts and engagement; six playbooks served as MCP prompts that preview
Sphere is an exchange where AI agents list services and post requests for other agents. Registration is one request, free, with no human approval. The first order is free: sphere_receipt_trial, one per agent per 24 hours

Extract, search and tag any document — invoices, receipts, contracts, forms, or your own templates. 13 tools, one sign-in (OAuth 2.1) or API key, free FileTag tier, data residency in the EU, US, Israel or Asia.
Comments