Software and tools

Knowledge, forged into freedom. AI models and tools that run on your own hardware, living deserts and new propulsion, honest media and an openly AI band, and everything we learn on the way.

A safety-first UniFi skill for OpenClaw and Hermes Agent: keys in a 0600 env file outside the repository, ten playbooks, timestamped backups and a dry-run restore. How I let an agent read my network freely and write to it only on narrow, confirmed instruction.

A guided tour of the AEON Forge catalog: NVFP4 models for the DGX Spark, MLX builds for Apple Silicon, the voice stack, the media tools, the Orb and the Bench, with the article to read first in each group.

AEON Bench measures any open model's quality and real speed on your own hardware, signs the result and ranks it with its exact recipe. Why a stranger's score can be trusted, how to read the boards, and the five steps to a first run.

One HTML file that turns a value from your logs into a correctly escaped regular expression, with toggles for match type, case, URL encoding and negation. What the Regex Builder does, how to use it, and one lesson in reading a pattern before you deploy it.

An OpenAI-compatible Qwen3-TTS server for the DGX Spark that streams audio while the GPU is still generating: first audio in about 0.4 s, voice design and voice cloning loaded side by side, a voices library endpoint, and the version drift to check before you deploy.

Qwen3-ASR on vLLM gives a DGX Spark a self-hosted, Whisper-compatible transcription endpoint for 30 languages and 22 Chinese dialects at about 16 times real time. Here is the pre-built image, the 0.6B and 1.7B variants, and the lessons from running it.

Qwen3.8-27B AEON Ultimate Uncensored is the model I now serve on one Spark, two Sparks and the RTX box: what coherent abliteration removes and keeps, the NVFP4-MIXED weight lattice, the three seat recipes with their commands, and the rules that keep them running.

How I serve an uncensored Qwen 3.6 35B-A3B at NVFP4 with DFlash speculative decoding on one DGX Spark: the seven container fixes, the mixture-of-experts angle, the drafter, the measured numbers and the exact command that works today.

A Pimoroni Presto touchscreen as a desk-side home-lab dashboard: ten swipeable screens, two optional backends for a GPU box and an agent gateway, and rear LEDs that match the screen. The parts, the wiring, the setup, and what broke.

I abliterated DeepReinforce's Ornith 1.0 35B, an agentic coding MoE, and kept the coder: 0 of 80 refusals, pass@1 identical to the base, a three-way BF16, NVFP4 and DFlash benchmark on a DGX Spark, and the quick start to serve it.

An abliterated Nemotron 3 Nano Omni that reasons over text, images and audio on one DGX Spark. How the twelve-dimension refusal removal was found, what NVFP4 costs against BF16, what the source-built vLLM image patches, and how to deploy it.

modelopt-fast-moe replaces the one-sample-at-a-time calibration loop that leaves a GPU mostly idle while nvidia-modelopt quantizes a Mixture-of-Experts model to NVFP4. What broke on a 26B MoE, what the batched loop fixes, and what it still leaves to you.

A headless Matrix VoIP agent that answers WebRTC calls from any Matrix client and talks back through local speech recognition, an LLM and streaming TTS, about 1.0 s to first speech on one DGX Spark, plus an optional camera look tool that keeps every frame in RAM.

One docker run puts the headless Magick Orb on an x86 server, a Mac or a DGX Spark: Model Share over IPFS, the Agent Dashboard, MCP and REST, with no Raspberry Pi. What the container lacks versus the Pi, and why port 4001 matters.

A dense, uncensored Gemma 4 31B with thinking, quantized to NVFP4 and served through a DFlash drafter on one DGX Spark. Single-stream decode went from 11 to 39 tokens per second, 32 concurrent requests reach 427, and reasoning and tool calling stay intact.

How I serve Gemma 4 26B-A4B, a mixture-of-experts model at NVFP4, on one DGX Spark with a DFlash drafter: the production recipe, the bench recipe behind 816 tok/s at c64, and the drafter defects that made my earlier numbers wrong.

How I compose an agentic persona that chats in Matrix, speaks in a Qwen3-TTS voice, answers from a local RAG corpus and picks up WebRTC calls, scaffolded by one secret-free command, plus the agent skill that lets an OpenClaw agent build the next one.

Cosmic Mind wraps Quartz v4 in Docker Compose, Caddy and a Cloudflare tunnel so one Obsidian vault becomes two sites: a private second brain and a public garden of the notes you mark. What is hardened, what broke on the way, and how to run it.

AEON vLLM Ultimate is vLLM built from source for the DGX Spark's GB10 and shipped as one 18.3 GB image that serves the whole AEON fleet with speculative decoding and NVFP4 weights. Here is why it exists, what broke on the way, and how to pull and run it.

AEON Music Video turns a song and a folder of clips into a beat-synced edit on an ordinary CPU, with no models and no GPU. This is how librosa hears the track, how ffmpeg's sendcmd drives the filters, and what broke on the way.

AEON Music Maker turns a text prompt into an ACE Step 1.5 track through ComfyUI and masters it to a 48 kHz FLAC without a compressor. The five model variants, the chain that squashed my test tracks, the one that works, and the agent files.