llm-wrapper

A robust CLI powering autonomous web agents. Seamlessly integrate Playwright, browser-use, and LangChain to automate your daily web workflows.

Agent SDK for Go - with Temporal & Restate support for durable execution, multi-agent support, and OTeL tracing support

Python wrapper that simplifies the Google Gemini API

🐍 Script to compare llm performances with statistics

My Universal AI HUB - Beta

Local-first AI chat workspace. Compare LLMs side by side with streaming latency and token metrics, vote to build a model leaderboard, bring your own keys for 6 providers, and generate images and video.

From 90's cartoon, Courage the Cowardly dog, A LLM Wrapper and TTS based off of courage's snarky computer in the attic. The Bagge family's Computer AI has finally been brought into real life.

Modified version of Le Wagon Data Science capstone project (March 2024)

🤖 Minimal CLI agent using single-turn ReAct pattern with OpenAI LLM wrapper. Intelligently selects between calculator, string operations, and direct responses. Extensible tool system with comprehensive testing.

LLM based git-hook script that leverages the model to generate conventional commit style message based on context gather around the diff. In Case it doesn't work for you, create an Issue. Works on my machine LOL

Privacy-preserving LLM wrapper that anonymizes PII locally before it reaches a cloud LLM and restores it in the response. Drop-in OpenAI replacement, multi-SDK support, CLI, REST API, and audit logging. No Docker required.

An ultra-lightweight, asynchronous Python 3.14 client to centralize and unify calls across AI providers (Cerebras, Cohere, DeepSeek, Gemini, Groq, Mistral, Nvidia NIM, OpenRouter, OrcaRouter). Powered by uv.

Automated quiz app for familiarising with a code repository

Unified LLM abstraction layer with fallback routing, retry policies, and token/latency telemetry.