Dec 17, 2025 · 4 min read · Introduction: Create two agents which talks to each other and comes to conclusion Native Tool Usage: It uses litellm's built-in tool handling (compatible with OpenAI, Anthropic, etc.), rather than manual string parsing. Two Agents, Two Tools: As re...
Join discussionDec 17, 2025 · 4 min read · Building a Travel Desk Agent using LiteLLM. This guide helps create a functional agent capable of "using tools" to search for flights and hotels—the core requirement for a travel desk. Why LiteLLM? LiteLLM is ideal for this because it provides a unif...
Join discussionNov 5, 2025 · 2 min read · Let’s say you want a ChatGPT-like interface to access the models you’ve set up in LiteLLM. Let’s add that to the docker_compose.yaml that we’ve been building up. The first thing you’ll need is an API key access your LiteLLM server. To create one, go ...
Join discussion
Nov 2, 2025 · 3 min read · Let’s enable LiteLLM to reach the models you’re paying for with your subscription to Github Copilot. Building off of the last LiteLLM article, we just need a couple more steps. We need to create a directory for the Copilot token outside the container...
Join discussion
Nov 1, 2025 · 3 min read · While I’m waiting for my Nanochat training to complete (it’s about half done), I decided to set up LiteLLM on my MacBook. That will allow me to set up completely local AI workflows for being completely offline (such as on an Airplane) but also make i...
Join discussion
Oct 16, 2025 · 6 min read · The AWS Summit Bangalore, which I got the chance to attend on May 8, 2025, was an amazing learning experience. The summit gathered together cloud enthusiasts, developers, and architects to discuss the newest developments in AI and cloud computing. Al...
Join discussion
May 29, 2025 · 4 min read · I've been telling myself for quite some time now that I need to seriously get into Python. That moment is today! And I couldn't settle for a simple "👋 hello world 🌍". Given my current passions, my job, and my curious nature, what could be more "nat...
Join discussion
Apr 24, 2024 · 9 min read · TL;DR. Installing Twinny for VS Code involves creating two Miniconda environments to run different variations of Code Llama using LiteLLM, which provides accessible IP addresses and ports for local LLMs. Twinny, an AI code completion tool, is integra...
Join discussion
Mar 12, 2024 · 9 min read · TL;DR. This post is a guide through installing and setting up Microsoft AutoGen Studio, a tool for orchestrating collaborative AI agents. It covers prerequisites like setting up Ubuntu with Miniconda, Ollama and Llama2, and LiteLLM. The process inclu...
Join discussion