A text-to-speech system that preserves and compiles the original source code of the classic DECtalk speech synthesis engine for modern platforms.

A Japanese text-to-speech software that uses the AivisSpeech Engine and ONNX-based models to generate emotionally rich synthetic voices.

Dotnet bindings for OpenAI Whisper via whisper.cpp, enabling high-performance speech-to-text transcription and translation in .NET applications.

An open-source, cross-platform subtitle editor that integrates AI transcription, translation, and dubbing tools for professional subtitle creation.

A free online text-to-speech tool that supports over 300 voices and allows integration with custom OpenAI-compatible TTS APIs.

AI Agent Skills is an npm‑based CLI/TUI that ships a curated library of ~115 AI‑agent “skills” (prompt‑code bundles) organized into shelves (frontend, backend, mobile, workflow, agent‑engineering, marketing). It lets you browse, search, install, and manage both local “house‑copy” skills and upstream metadata‑only skills. You can also bootstrap a personal library with `init-library`, add or catalog new skills, vendor copies, sync updates, and generate documentation. Works with any Agent‑Skills‑compatible agent (Claude, Cursor, Gemini, etc.) and supports multiple install targets. Ideal for developers or teams who want a tidy, searchable toolbox of reusable agent capabilities.

Mega-ASR is a foundation ASR model designed for robust speech recognition in challenging real-world environments by scaling up acoustic simulations of noise, echo, and distortion.

RustFinance Terminal (Rust‑Forge) is an open‑source, Rust‑only trading platform that combines real‑time market‑data ingestion (direct exchange binary feeds, broker APIs, crypto WebSockets), a full‑screen terminal UI, Claude‑powered AI commentary, a library of micro‑structure indicators, risk models, and execution algorithms (TWAP, VWAP, Almgren‑Chriss, etc.). It offers native Nasdaq/NYSE connectivity, a modular crate architecture, and research‑grade documentation, targeting quant researchers, low‑latency developers, and AI‑enthusiasts.

DataArc SynData Toolkit is an open‑source Python framework that lets you generate synthetic training data (text or image‑text) for LLMs via a single YAML config, then fine‑tune models (SFT/GRPO) and evaluate them with DeepEval—all accessible through a CLI or a FastAPI + React GUI.

OpenDeRisk is an open‑source, multi‑agent AI platform that automates root‑cause analysis for software incidents. It ingests the large OpenRCA dataset, lets specialized agents (SRE, Code, Report, Visual, Data) collaborate, and presents a visual evidence chain through a web UI. Installable via a single curl script or from source with the uv package manager, it supports quick‑start usage, flame‑graph assistance, and conversational data analysis.

Apache Texera is an open‑source visual platform that lets users build and run data‑analysis pipelines through a drag‑and‑drop GUI, with AI agents that translate natural‑language commands into workflow steps. It supports Python and Java operators, real‑time collaboration, interactive debugging, and scales from a laptop to large cloud clusters.

An MLX-based implementation of Nvidia's Parakeet ASR models for Apple Silicon, providing efficient local audio transcription with streaming and timestamp support.

OpenMobius‑skill is a plug‑in for AI coding agents (Claude Code, Codex, OpenClaw, Hermes, Cursor, WorkBuddy) that adds a curated trading‑knowledge base (≈2 000 cards from ICT, SMC, ChanLun, etc.), real‑time market data, 60+ technical indicators, and chart‑generation. It routes user queries through strict/augment/compare modes, supports multiple schools of analysis, and installs self‑contained with its own Python virtual environment, model weights, and Playwright Chromium.

WelsonJS is a Windows‑only framework that lets you write console or GUI desktop apps with JavaScript (and TypeScript, CoffeeScript, etc.) using the built‑in Windows Script Host engine. It runs without extra runtimes, supports legacy Windows versions, bundles many libraries (jQuery, Monaco, React, ESENT DB, native Windows service APIs), and includes optional LLM integrations (ChatGPT, Gemini). Apps can be packaged as zip files, Inno Setup installers, or simple copy‑and‑run bundles, and a PowerShell bootstrap script can pull the runtime automatically.

NVIDIA cuDF plugin for Apache Spark is a GPU‑accelerated library that replaces Spark’s CPU DataFrame operations with cuDF, delivering faster joins, aggregations, and other SQL‑style queries while keeping results identical to vanilla Spark. It integrates via a Spark plugin, offers zero‑copy data paths to other GPU ML libraries, and includes qualification and profiling tools to help users assess and tune performance.

ast-index is a CLI that builds a SQLite AST index for multi‑language codebases, enabling fast structural queries (symbols, classes, dependencies, etc.). It reduces LLM token usage by returning precise code slices, integrates with Claude, Codex, Cursor and Gemini via plugins, and supports monorepos, incremental updates, and a rich JSON schema.

AlphaBot is an open‑source, Docker‑deployable web app that combines a LLM‑driven chat assistant with real‑time market data (global via Alpha Vantage, Chinese A‑shares via Tushare/AKShare). It offers AI‑generated technical and fundamental analysis, chart visualisation, risk assessment, and simple quant‑strategy suggestions for retail investors.

ck is a Rust‑based CLI/TUI tool that builds local embeddings of source code and lets you search by meaning (semantic search) as well as by traditional regex. It supports incremental indexing, multiple embedding models, AI‑agent integration via an MCP server, and outputs results in JSON/JSONL for automation.

IronCurtain is a research‑grade runtime that secures autonomous LLM agents by compiling a plain‑English "constitution" into deterministic allow/deny rules, validating them, and enforcing the rules on every tool call via a policy engine. It supports a V8 sandbox or Docker‑isolated agents, provides an interactive terminal multiplexer and optional web UI for escalation handling, and includes persona/workflow features for multi‑agent pipelines.

NNCF (Neural Network Compression Framework) is an open‑source Python library that adds post‑training and training‑time compression (quantization, weight compression, pruning, etc.) to PyTorch, TorchFX, ONNX, and OpenVINO models, enabling smaller, faster inference with minimal accuracy loss.

aTrain is an offline transcription app that runs Whisper (via faster‑whisper) on your computer, offering speaker diarisation, 99‑language support, and export formats compatible with MAXQDA, ATLAS.ti, and NVivo. It’s distributed as a desktop app for Linux/Windows and as a pip‑installable CLI, with optional CUDA GPU acceleration for faster processing.

VectorDBBench is a Python CLI tool that benchmarks insertion, vector search, filtered search, and full‑text BM25 retrieval across many open‑source and cloud vector databases. It ships with standard ANN datasets (SIFT, GIST, Cohere, OpenAI embeddings) and newer multimodal Hugging Face datasets, reports latency/recall/QPS and cloud cost, and offers a visual UI for comparing results.

An Android app that uses machine learning to identify over 6,000 bird species by their sound in real time and entirely offline.

A Python library that transcribes audio using faster-whisper and uses LLMs to translate and polish the text into synchronized .lrc subtitles.

Flow‑Next is a plugin for coding agents (Claude Code, OpenAI Codex, Cursor, etc.) that turns a change request into a durable spec, then automatically drives planning, implementation, adversarial review, live QA and PR creation, recording all evidence in the repository.

A Claude/Codex skill that lets an LLM draft, review, and (optionally) post social‑media comments on Facebook, Instagram and Threads via a controlled Chrome session. It learns a brand’s voice, keeps a cryptographically‑signed ledger of every action, and includes extensive safety checks and test suites. Live posting is off by default; the repo supplies the automation framework, not the private content.

VoiceBench is a benchmark suite for evaluating LLM‑based voice assistants. It supplies a Hugging‑Face dataset with audio‑driven QA and instruction‑following tasks, a command‑line toolkit to run a model, collect spoken responses, and automatically score them (via GPT‑4o‑mini for open‑ended sets). Results are posted on a public leaderboard, and the repo includes a curated list of recent voice‑assistant papers.

A web-based multi-voice TTS application for creating narrated stories and audiobooks, supporting a wide array of local and cloud-based speech engines.

An open-source, 100% local audio transcription and subtitling suite with a web UI that uses FasterWhisper for fast, private processing.

A production-oriented end-to-end speech recognition toolkit that provides full-stack solutions for streaming and non-streaming speech-to-text.

An open-source speech and audio toolkit on the PaddlePaddle platform providing state-of-the-art models for speech recognition, synthesis, and translation.

A unified workspace for creating audiobooks, subtitles, and voiceovers by coordinating local and cloud-based speech and language models.

Claude Code Development Workflows is a set of Claude Code plugins that turn the Claude AI assistant into a structured development pipeline. The plugins provide “recipes” (e.g. `/recipe‑implement`, `/recipe‑design`, `/recipe‑review`) that enforce outcome agreement, design documentation, work‑plan generation, task‑level implementation with automated verification, and an independent security review. Three plugin families cover backend, React frontend, and full‑stack projects, and they can be installed via Claude’s marketplace. The system is useful when you need repeatable safety gates and a formal hand‑off between design and code generation; for quick prototypes you can skip it.

A utility for downloading Dify AI platform plugins and repackaging them for different OS/architecture targets, usable via GitHub Actions, Docker, or a direct shell script.

DSH Plugin Radar is an open‑source system that automatically discovers, validates (via Kubernetes pods), and catalogs DeepSeek Harness plugins. It produces a live markdown list, curated “featured” lists, bundle collections, and a public JSON API, helping developers and users find reliable DSH plugins without trial‑and‑error.

PUAX is a production‑ready runtime that adds a mind‑set layer to LLM agents. It provides arena/gate/dream primitives, thin‑prompt compression, a zero‑dependency Python SDK, hybrid trigger detection, 59 built‑in (and custom) roles, outcome‑driven verification, a Carbon Shield for human‑targeted manipulation detection, and a reproducible multi‑model benchmark suite. The system is accessed via an MCP server (`npx puax-mcp-server`) that injects native hooks into popular IDEs, and can be embedded directly into LangChain/AutoGen via a one‑line AMP middleware. MIT‑licensed and marked production‑ready.

LuJie CareerKit is an AI‑enhanced web app for managing resumes, JD matching, interview preparation, mock interviews, and application tracking. It stores all data locally in SQLite, uses a configurable OpenAI‑compatible model, and includes an experimental in‑app career agent that can generate and edit job‑search artifacts via natural‑language commands.

kimchi is a terminal‑based AI coding assistant built on the pi‑mono SDK. It orchestrates one or more LLMs across roles (planner, builder, reviewer, explorer, researcher), supports multi‑model routing, persistent project management via Ferment, tag‑based usage tracking, optional LSP integration, and remote‑session teleporting.

Claude Forge is a plug‑in pack that turns the basic Claude Code terminal coding assistant into a production‑grade development environment. It adds 16 specialist AI agents, 35 slash‑commands, 33 saved “skills”, 22 safety hooks, 14 behavior rules and 4 external‑tool connections. Install with a one‑liner script (full install) or via Claude Code’s plugin marketplace (commands only). The pack automates planning, test‑first development, security reviews, documentation sync, and an adversarial verification loop that requires an independent agent to approve every change. Licensed MIT, actively maintained (v4.3.0, Sep 2026).

graph‑flow is a Rust library that lets you build stateful, graph‑based workflows for AI agents. Tasks read/write a typed Context, the engine can pause for human input, persist sessions (in‑memory or PostgreSQL), and resume later. It includes conditional edges, parallel fan‑out, and optional Rig integration for LLM calls. Example services (insurance claims, recommendation) show real‑world usage. MIT‑licensed and published on crates.io.

Marsha is an LLM‑powered, markdown‑style language that lets you describe a data‑processing function with types, a natural‑language spec, and input‑output examples. The Marsha compiler sends this spec to an LLM, generates Python code, validates it against the examples, and produces a ready‑to‑run CLI or REST service.

A Python and JavaScript solution for near-real-time audio streaming and transcription using WebSockets, Voice Activity Detection, and Faster Whisper.

A GPU-accelerated Python library for simulating Room Impulse Responses (RIRs) using the Image Source Method, offering up to 100x speedup over CPU implementations.

A Python quantitative‑trading platform that structures the workflow into a “Three‑Ministries‑Six‑Departments” hierarchy, offers back‑testing, multi‑strategy management, risk‑first execution, and an AI‑driven natural‑language stock‑screening feature. It runs via a FastAPI + HTML dashboard, supports multiple data sources, and is free for personal/academic use (commercial use needs a license).

A C# framework for audio and video fingerprinting and recognition, enabling the fast identification of media content through acoustic and video hashes.

A peer-to-peer TCP protocol for voice assistants that standardizes communication between audio I/O, wake word detection, speech-to-text, and text-to-speech services.

A production‑ready Next.js 16 starter that combines Supabase SSR authentication with Claude‑powered chat and eight built‑in AI tools (RAG, web search, charts, PDF generation, memory, artifact workspace, usage dashboards, admin console). One‑file Supabase schema, per‑token cost tracking, and caching make it ready for SaaS or internal AI assistants.

Captum is a PyTorch library that provides a suite of model‑interpretability algorithms (Integrated Gradients, DeepLift, Gradient Shap, SmoothGrad, TCAV, TracIn, neuron/layer conductance, etc.) to help developers and researchers understand which inputs, neurons, or training examples drive a model’s predictions. It installs via pip/conda and works with any PyTorch model.