Top Finds

A web editor to create and edit publiccode.yml files

A new network stack based on gVisor

CLI for .faf (Foundational AI-Context Format). Init, score, bi-sync, export to AGENTS.md, GEMINI.md, .cursorrules. npm: faf-cli

A cross-platform GUI for ecapture built with Tauri, enabling eBPF-based, non-intrusive TLS inspection on Linux & Android, with remote clients for Windows, macOS, and Linux.

Same AI, fewer tokens. Free forever. — tokenshrink.com

You writes your code. Brakit watches what it does.

AI Robustness Evaluation System

A Rust reimplementation of genai-bench for benchmarking LLM serving systems at high concurrency with accurate timing and industry-standard metrics

Modular, high-performance deep learning research framework

Knowledge graph construction and reasoning library

Zero dependencies Query Builder for Cloudflare Workers

The project implements AI DIAL API for language models from AWS Bedrock

A High Performance Java AIO framework

A React PDF component library with pre-built, themeable components and a CLI for seamless PDF document creation.

Multi-LLM AI debate platform — orchestrate structured debates between Claude, GPT, and Gemini with consensus scoring and synthesized verdicts.

Cloudant SDK for Node.js

This extension is designed to provide a seamless experience for Couchbase Server users who want to work within the popular Visual Studio Code editor.

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models

Lightweight self-hosted observability for AI/LLM and agent workflows: traces, observations, and metrics.

Arbiter provides simple APIs, complete observability, and provider-agnostic infrastructure for evaluating LLM outputs. Built on PydanticAI with automatic interaction tracking, multiple evaluators, and extensible architecture.

AI integration layer for Jido agents with LLM orchestration and reasoning strategies.

An alternative frontend for OpenFoodFacts, made with SvelteKit

RESTai is an AIaaS (AI as a Service) open-source platform. Built on top of LlamaIndex & Langchain. Supports any public LLM supported by LlamaIndex and any local LLM suported by Ollama/vLLM/etc. Precise embeddings usage and tuning. Built-in image generation (Dall-E, SD, Flux) and dynamic loading generators.

The developer community designing and developing public digital services in Italy