The context API to search, scrape, and interact with the web at scale. 🔥

A 7-layer memory operating system for Hermes Agent — persistent memory with Qdrant, structured facts, fabric recall, auto-curated wiki, and surgical context injection. Runs locally, any LLM provider.

Native macOS and iOS App for the Hermes AI agent — multi-window, multi-server (local + remote over SSH). Chat, dashboard, sessions, memory, cron, MCP, and more.

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a git repository (Github, Gitlab, Azure, Local) or…

Agent skills for Obsidian. Teach your agent to use Obsidian CLI and open formats including Markdown, Bases, JSON Canvas.

State-of-the-art TTS model under 25MB 😻

Native web workspace for Hermes Agent — chat, terminal, memory, skills, inspector.

The agent that grows with you

A curated list of amazingly awesome MeshCore resources

Open-source Flutter client for MeshCore LoRa mesh networking devices

Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

A calibre device plugin for Remarkable 2, using local SSH

High Resolution Depth Maps for Stable Diffusion WebUI

🚀Neumorphic is a SwiftUI utility to build Neumorphism Soft UI (supports both *outer shadow and *inner shadow)

Moving numbers effect in SwiftUI

Build, run, and manage agent platforms.

Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.

A simple FastAPI Server to run XTTSv2

A fast inference library for running LLMs locally on modern consumer-class GPUs

batched loras

Spherical Merge Pytorch/HF format Language Models with minimal feature loss.

Customizable implementation of the self-instruct paper.

Go ahead and axolotl questions