Constellation · 02
Mind
FFAI, Mercury, Carmenta, Diana: AI that stays local
Why this band exists
Cloud inference means your voice, your documents, and your camera feed leave the room before the model ever answers. Remade Mind remakes Whisper-class, YOLO-class, and OCR stacks in Rust so the neighborhood can see and hear without renting a GPU in someone else's region.
Why now
"On-device" that still uploads is a lifestyle brand. Households and OEMs need ASR, OCR, and detection that compile into a tab, a phone, or a board: without a Python glue stack and without a training-set commute. Local AI is how Digital Freedom survives contact with a neural net.
How it fits
Media decodes the bytes Mind reads. Memory keeps transcripts and embeddings beside the user. Identity decides who may run the model. Edge puts FFAI next to the sensor. Trust keeps the lockfile under the weights honest. Mind is perception that refuses exfiltration as architecture.
Stars in Mind
Each crate is open under Remade-With-Rust. Open the repo, then the field note, then compose with the rest of the sky.
FFAI
The Remade-with-Rust AI media suite. Engines for ASR, TTS, OCR, VLM, and YOLO-class detection share one Rust surface so perception stays local.
Mercury · replaces Whisper.cpp
FFAI ASR engine: pure-Rust Whisper speech recognition
Carmenta · replaces Tesseract / Python OCR
FFAI OCR engine: text from images without the C tax
Diana · replaces YOLO C++ stacks
FFAI detection engine: object detection in Rust
Argus · replaces cloud VLM caption APIs
Vision-language that captions locally
What to build first
- An on-device media suite path through FFAI (ASR, TTS, OCR, VLM, detection)
- Speech notes that transcribe in-process with Mercury
- Scan and screenshot OCR with Carmenta, including WASM in the browser
Field notes in Mind
Local AI Is Not A Hobby. It Is The Point.
Cloud AI is a polite burglar. FFAI, Mercury, Carmenta, and Diana keep speech, sight, and OCR on the device in memory-safe Rust so the model never needed your upload.
September 29, 2026
Pure Rust Alternative for heavy Python ML runtimes
Looking for a pure Rust alternative for heavy Python ML runtimes? candle eliminates edge inference that still needs a C/Python circus so you can ship memory-safe products...
September 29, 2026
Pure Rust Alternative for Hugging Face tokenizers with Oniguruma
Looking for a pure Rust alternative for Hugging Face tokenizers with Oniguruma? tokenizers eliminates C regex in the tokenizer hot path so you can ship memory-safe products...
September 29, 2026
Pure Rust Alternative for Python AI media stacks
Looking for a pure Rust alternative for Python AI media stacks? FFAI eliminates cloud-bound AI media glue and unsafe native kernels so you can ship memory-safe products without...
September 29, 2026
Pure Rust Alternative for Python VLM servers
Looking for a pure Rust alternative for Python VLM servers? argus eliminates vision-language stacks that exfiltrate frames so you can ship memory-safe products without...
September 29, 2026
Pure Rust Alternative for Tesseract
Looking for a pure Rust alternative for Tesseract? carmenta eliminates C OCR and Python wrappers that upload scans so you can ship memory-safe products without babysitting C/C++.
September 29, 2026
Pure Rust Alternative for Whisper.cpp
Looking for a pure Rust alternative for Whisper.cpp? mercury eliminates C++ speech stacks that leave the room so you can ship memory-safe products without babysitting C/C++.
September 29, 2026
Pure Rust Alternative for YOLO C++ stacks
Looking for a pure Rust alternative for YOLO C++ stacks? diana eliminates detector runtimes that require cloud GPUs so you can ship memory-safe products without babysitting C/C++.
September 29, 2026
The rest of the constellation
Six technology bands, one sky. Open another star, or return to the full map.
01
Media
ffmpeg, H.264, Opus, PNG/JPEG: pure Rust pipelines
03
Memory
rusty_alloc, SpaceDB: local-first replicas
04
Identity
mID & Sovereign ID: keys you hold
05
Edge
ESP mesh nodes: neighborhood hardware
06
Trust
Deputy: supply chain you can audit