open-source

A Deepgram client for Dart and Flutter, supporting all Speech-to-Text and Text-to-Speech features on every platform.

PostgreSQL-native semantic search engine with multi-modal capabilities. Add AI-powered search to your existing database without separate vector databases, vendor fees, or complex setup. Features text + image search using CLIP embeddings, native SQL joins, and 10-minute Docker deployment.

A curated list of tools, frameworks, and resources for running AI locally — inference, RAG, orchestration, monitoring, and more.

🎤 开源免费的 AI 语音输入工具 — 基于FunASR，本地处理，为中文而生 | Free & open-source voice input tool with local FunASR

VTuber application which only requires your voice and microphone, no need for a webcam or other tracking nonsense.

Code for paper: "Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation"

Vortex is a self-hosted RAG (Retrieval-Augmented Generation) application that lets you chat with your documents using any LLM provider. Upload PDFs, ingest URLs, and get accurate answers grounded in your own knowledge bases — all with a clean, modern interface.

Universal MCP server for logistics. Connect any TMS/WMS to AI agents. Shipments, carriers, tenders, tracking — all via Model Context Protocol.

Push-to-talk voice dictation for macOS. 100% local, free, open source. Apple Silicon MLX. No cloud, no subscription.

🔒 Privacy-first MCP server for Claude using PostgreSQL + Ollama. Local alternative to cloud-based code context with full data sovereignty. No API keys, no external calls, 100% local.

Turn any NVIDIA GPU into a local AI platform. Inference + fine-tuning in your browser. One command to start, automatic clustering.

Open-source persistent memory infrastructure for LLM applications.🐬

SAM — Smart Agentic Model: CLI coding agent for open-source LLMs. pip install sam-agent

The ultimate desktop app for tracking, managing, and validating AI models from Hugging Face, Civitai, OpenModelDB & more.

Persistent memory and identity protocol for AI systems with evidence-aware recall and inspectable memory.

Open-source local AI server configs, GFX906 runtime maintenance, reproducible benchmarks, and QC methods for affordable AI research infrastructure.

🧪 SynthForge — toolkit for generating high-quality synthetic datasets for LLM fine-tuning. Multi-backend, filterable, GPU-accelerated. Early-stage experimental project.

Run IBM Granite 4.0 locally on Raspberry Pi 5 with Ollama.This is a privacy-first AI. Your data never leaves your device because it runs 100% locally. There are no cloud uploads and no third-party tracking.

A modern platform for competitive programming.

The open-source, self-hosted alternative to NotebookLM.