Give DeepSeek V4 Flash eyes. OpenAI-compatible shim + tiny local VLM. Point any harness at one URL and your text-only model accepts images. Zero dependencies.

Permanent memory for AI agents. A 426-token prompt, a script, plug and play.

List and toggle local LLMs (GGUF via llama.cpp, vLLM via Docker) from per-model YAML configs

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional RouterOS switch monitoring, and per-model decode/prefill/…

Neoflow is an open-source whiteboard application designed for seamless collaboration and creativity. It combines simplicity with advanced features, making it perfect for teams, designers, and creat…

The headless browser for AI agents and web scraping

Shodan.io for Hermes Agent. Host intel, search, DNS, CVE lookups, monitoring and on-demand scanning, with credit budgeting and response shaping that keeps results inside the context window.

Agent-ready two-node DGX Spark recipe for DeepSeek V4 Flash plus an optional Qwen Vision sidecar, with generic OpenAI-compatible, Hermes, and Pi integration guides

A sliding, tiling window manager for MacOS.

Graph-Native Infrastructure for Context and Accountable AI Systems

keys-DGX-Sparkticus Utimate Power Pack Unleashed (Dual DGX-Sparks Needed)

Rio's Rust terminal core (librio), compiled to WebAssembly and packaged for the web.

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

An all-in-one, 100% local AI video, image, and music studio. Director mode plans full music videos and short films from a single prompt. Built on the WanGP pipeline. Install via Pinokio.

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, LTX-2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Open-source, community-driven agent harness

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetil…

Compile Zod schemas into zero-overhead validation functions at build time. Works with Vite, webpack, esbuild, Rollup, etc

SuperBrain — AI-powered save-it-later brain for Instagram, YouTube & Web

self-hosted, distributed Durable Objects

Native Hermes Desktop dock for direct profile chat, concurrent jobs, cancellation, and explicit Kanban assignment.

Virtual filesystem overlay built on event streams for state replay and time travel

Inter-session communication extension for pi coding agent

Create smooth, responsive interactive web animations.

Give your agent a computer 👾

🧻 Knowledge system for agents. Local-first, file-based, progressively disclosed.

Claude subscription wire compatibility for Pi.