Inference · Serving

Native C inference for MiniMax-H3 video and audio generation on Apple Silicon, with an interactive terminal UI and an SSD-streaming mode that cuts resident transformer memory from ~36 GiB to ~2 GiB.

It exists so you can run DeepSeek and Kimi inside OpenAI’s Codex app without switching editors or leaking API keys into chat.

To prove that a 2.78-trillion-parameter model can run on a single CPU with 8 GB of RAM and no GPU.

It exists to stop your AI gateway from quietly burning through quotas, cash, and expired OAuth tokens without leaving a paper trail.

It keeps the entire agent loop—prompts, tool calls, browser state, and memory—on your laptop so you don't have to rent a control plane in the cloud.

A privacy-first Android fork that runs LLMs, image generation, and speech AI entirely offline, then locks itself behind your fingerprint.

Espressif's C framework turns cheap microcontrollers into edge AI agents you program through IM chat.

A distilled Gemini 3.1 that fits on watches and glasses, finetunable on a laptop.

It breaks the vendor lock on Codex and Claude Code by translating their API calls to any LLM backend you choose.

WASTE exists to find out how far local inference can be pushed when model weights live mostly on fast storage instead of RAM.

WorldX turns one sentence into a self-running simulation of AI agents who gossip, scheme, and remember grudges without a script.

Because dictating to your cursor on Linux shouldn’t require a browser tab or a cloud subscription.

Agnes AI is a hosted multimodal API that speaks OpenAI's protocol, letting you reroute existing clients to its text, image, video, and agent models by changing a base URL.

TokenHub exists because dropping a shared OpenAI key into a Slack channel does not scale past one invoice and zero accountability.

Real-time screen translation for Android games and manga, no root needed.

It turns any LLM into a ComfyUI operator that edits live graphs, manages models, and runs workflows instead of just forwarding prompts.

SIE replaces the usual tangle of separate embedding, reranking, and extraction servers with a single open-source container that scales from a laptop to Kubernetes.

One desktop UI that wires together ComfyUI, OpenAI, Gemini, ModelScope, and a dozen other generative APIs—plus some very opinionated legal terms.

TurboFieldfare streams individual experts from SSD on demand so Gemma 4 26B-A4B fits inside ~2 GB of RAM on any Apple Silicon Mac.

It automates web-only AI services through a stealth browser to expose them as OpenAI-compatible endpoints with multi-account isolation.