An open-source multi-agent chat interface that lets users manage multiple AI agents in one dynamic conversation using Next.js, LangGraph, and CopilotKit.

A speaker diarization toolkit that uses self-supervised learning and structured pruning to accurately identify who spoke when in audio recordings.

A generative model for atomistic protein binder design that unifies generative modeling and hallucination to create binders for proteins and small-molecule ligands.

An Android chat application that provides a unified interface for interacting with cloud-based LLMs via OpenRouter and locally hosted models via Ollama, LM Studio, and others.

GrayMatter is a Go‑written, single‑binary memory layer for LLM agents. It stores facts persistently, retrieves the most relevant ones (top‑8 by default), and reduces context tokens by about 90 %. It also auto‑builds a typed knowledge graph, integrates with many MCP‑compatible clients (Claude Code, Cursor, Codex, etc.), and provides a terminal UI and health‑checking tools. Install via `go install`, Homebrew, Scoop, or a pre‑built binary; use the CLI (`graymatter recall`, `remember`, `kg render`, etc.) or embed the Go library directly in your agent code.

A fast, fully differentiable physics engine written in JAX for large-scale rigid body simulation and reinforcement learning training.

A Python text-to-speech library designed for low-latency audio generation from strings, generators, and LLM token streams, supporting a wide variety of local and cloud TTS engines.

A Python library that repairs malformed JSON from LLMs and APIs by fixing syntax errors and completing missing structures to ensure valid parsing.

An open-source AI voiceover platform that automates multi-character and multi-emotion speech synthesis for novels and scripts.

A pure Python library for simulating various poker variants, evaluating hands, and conducting statistical analysis, designed for AI development and tool creation.

A diffusion-based framework for 6-DOF robotic grasp generation that supports multiple gripper types and provides real-time, collision-aware grasp predictions from 3D point clouds or meshes.

A Rust-based, Git-compatible monorepo engine designed to provide AI coding agents with the full codebase context and infrastructure needed for petabyte-scale software engineering.

A tool that turns software repositories into agent-ready workspaces by installing a repository protocol and structured documentation to guide AI coding agents.

An AI-powered quality engineering fleet that automates test generation, coverage analysis, and flaky test detection across 11 coding agent platforms.

Deep Lake is a serverless database for AI that stores and streams large-scale unstructured data and vectors, optimizing the workflow for deep learning training and LLM applications.

A library of portable Markdown persona files (SOUL.md) that give AI agents distinct identities and behavioral convictions to move beyond generic assistant voices.

A deep learning package that turns quantum-mechanical reference data into fast, scalable interatomic potentials for molecular and materials science simulations.

A collection of advanced ComfyUI utility nodes for 3D Gaussian Splatting, infinite-canvas image editing, and professional 3D character posing and lighting.

A CLI proxy that enables Claude Code to work with any AI model, including local models and existing AI subscriptions from OpenAI, Google, and others.

A tool to mount Hugging Face Buckets and repositories as local filesystems, enabling lazy loading of models and datasets without full downloads.

A Model Context Protocol server that turns any Odoo 16+ database into an AI-ready interface, enabling LLMs to safely query and manage Odoo data without requiring Enterprise AI modules.

An open-source pipeline that uses Stable Diffusion, gTTS, and SadTalker to create and animate consistent virtual AI influencers for social media.

A lightweight Python-based 3D eye tracking algorithm that detects the pupil ellipse from video or image data.

An open-source marketplace repository for AI agent skills, providing a secure distribution system and CLI for adding capabilities to tools like Claude Code and Codex.

A cross-platform desktop app that provides a unified interface to run and manage multiple AI coding agents like Claude Code and Codex without losing context.

A lightweight Lidar-inertial odometry system for high-speed pose tracking and point cloud mapping, offering 1.5-2x speed increase over FastLIO2.

An automated developer tool that generates professional, structured README files by analyzing a codebase using LLMs.

A browser extension that provides instant translations of web text, images, and PDFs via tooltips using Google and Bing translation services.

A library that brings WebGPU capabilities to React Native applications using the Dawn implementation for high-performance GPU computing and graphics.

A tool that uses LLMs to generate personalized, hands-on technical tutorials and provides a local UI for working through them manually to ensure the user actually learns the material.

NeoVerse is a 4D world model that reconstructs 3D scenes from monocular videos to enable high-quality video generation along novel camera trajectories.

A software development kit for creating AI agents that can be deployed across Microsoft 365 Copilot, Teams, and custom apps while remaining agnostic to the underlying AI provider.

A high-fidelity neural audio codec that compresses 44.1 kHz audio into discrete codes at 8 kbps, providing approximately 90x compression for speech, music, and environmental sounds.

TurboVLA is a lightweight Vision-Language-Action model that enables real-time robotic control at 32 Hz using less than 1 GB of VRAM by replacing LLM-centric architectures with a direct vision-language to action mapping.

EdgeBench is a benchmark of 134 real-world tasks designed to evaluate how autonomous AI agents learn and improve through iterative interaction with an environment over long horizons.

A tool for fetching X/Twitter tweets, timelines, and articles without API keys or logins, featuring automatic backend fallback and a unified JSON schema for AI agents.

A Kubernetes API for deploying and managing multi-node AI inference workloads as unified groups of pods, supporting sharded LLMs and disaggregated architectures.

A spec-driven development framework for Claude Code and Codex that turns feature requests into structured research, design, and task lists before executing them.

A collection of modular agent skills for Claude Code and Codex that provide journalists and researchers with specialized workflows for source verification, records requests, and professional reporting.

A general-purpose image editing model that provides high-fidelity, consistent edits with strong identity preservation and multi-element fusion capabilities.

A universal web interface for real-time interaction and benchmarking of Vision Language Models using live webcam or IP camera streams.

A runtime interface for AI agents to execute commands in sandboxed shell environments across various local and remote platforms.

A zero-dependency tool that pre-compiles codebase structure and documentation into compact context maps and wikis to drastically reduce token consumption for AI coding assistants.

An agentic harness for writing verified AI/ML review papers in LaTeX, featuring a gated, issue-driven workflow that prevents citation hallucinations.

An AI-native Cloud Operating System built on Kubernetes that unifies development, deployment, and scaling for AI applications and SaaS platforms.

A GUI for dispatching multiple AI coding agents in parallel, using git worktrees to isolate each task into its own branch and directory for concurrent development.

A JAX-based library for numerical differential equation solvers that is autodifferentiable and GPU-capable, supporting ODEs, SDEs, and CDEs.

A machine learning project that uses image inpainting to remove watermarks from images, creating seamless results.