ipyflow
A reactive Python kernel for Jupyter notebooks.
HYSEN LABS DIRECTORY
Language tag · curated repositories and deep analysis.
A reactive Python kernel for Jupyter notebooks.
Examples of programs built using Modal
Frigate integration for Home Assistant
LLM Inference Engine for Metal, CUDA and Vulkan.
LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and interact with your apps, and to proxy xcodebuild to save token and context wastage.
Helping Ethical Hackers use LLMs in 50 Lines of Code or less..
This is a project that unifies the management of LLM APIs. It can call multiple backend services through a unified API interface, convert them to the OpenAI format uniformly, and support load balancing. Currently supported backend services include: OpenAI, Anthropic, DeepBricks, OpenRouter, Gemini, Vertex, etc.
Generate master-level posters, book covers and album covers from a single sentence - no Photoshop, color theory or art history needed. AI picks the best style from 20 legendary poster designers, defaults to 9:16 for social media, and includes prompt optimization, style comparison and image-to-image conversion.
[NeurIPS2026] We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.
A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions
Lossless Context Management plugin for Hermes Agent, DAG-based context engine that never loses a message.
OpenTelemetry Instrumentation for AI Observability
AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Reliability layer for multi-agent setups — keep agents coordinating without an orchestrator. Cross-dialog contracts + drift detection + black-box memory (no LLM extraction).
Open source alternative to LangGraph Platform (now LangSmith Deployments) - Self-hosted AI agent backend with FastAPI and PostgreSQL. Zero vendor lock-in, full control over your agent infrastructure.
Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizing build settings.