-
GitHub
- New Zealand
- http://twitter.com/igorcosta
- @igorcosta
Highlights
- Pro
Lists (4)
Sort Name ascending (A-Z)
Starred repositories
A modern model graph visualizer and debugger
A research prototype of a human-centered web agent
Base docker image used in Codex environments
An open protocol enabling communication and interoperability between opaque agentic applications.
Tool for generating high quality Synthetic datasets
FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent, VSCode Agent, Dia Browser & Trae AI (And other Open Sourced) System Prompts, Tools & AI Models.
A method for steering llms to better follow instructions
igorcosta / openai-cookbook
Forked from openai/openai-cookbookExamples and guides for using the OpenAI API
High performance self-hosted photo and video management solution.
The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.
A Conversational Speech Generation Model
Prevent merging of malicious code in pull requests
Codium-ai / ai-collection
Forked from ai-collection/ai-collectionThe Generative AI Landscape - A Collection of Awesome Generative AI Applications
A 4-hour coding workshop to understand how LLMs are implemented and used
This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"
9CFF AdalFlow: The library to build & auto-optimize LLM applications.
Beautifully designed open-source layouts and UI experiments built with Origin UI and shadcn/ui.
Enable AI models for video production in the browser
Smart proxy for LLM APIs that enables model-specific parameter control, automatic mode switching (like Qwen3's /think and /no_think), and <think> tag filtering. Perfect for using advanced models wi…
A Python package that makes it easy for developers to create AI apps powered by various AI providers.
Python tool for converting files and office documents to Markdown.
🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.
AI app store powered by 24/7 desktop history. open source | 100% local | dev friendly | 24/7 screen, mic recording
A lightweight library for portable low-level GPU computation using WebGPU.
LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.