8b-is Sovereign Mirror & Crate Registry

ALEXIAI <3 — Omni edition. The fully offline AI app on the GAIA-MLX-QUANT substrate: zero third-party LLM usage, loopback-only egress, ternary b1.58 kernel, osarous local model support.
Updated 2026-11-16 04:10:37 +01:00
Updated 2026-11-16 04:10:35 +01:00
100% Pure-Rust A6000 Sovereign Constellation Orchestrator (49.13.101.247 · RTX 6000 Ada · C64 64KB Ring Buffers · MarineIntDetector · Zero Floats)
Updated 2026-11-16 01:50:28 +01:00
Decentralized agent routing and lifecycle substrate. Coordinates capacity-aware routing, context- pruning workloads, and cryptographic verification across heterogeneous nodes (cloud VMs and local Raspberry Pis).
Updated 2026-11-16 01:31:37 +01:00
Updated 2026-11-16 01:21:50 +01:00
Upstream pull mirror of https://github.com/8b-is/sops.git
Updated 2026-11-16 01:16:46 +01:00
Rust implementation of DeepSeek-OCR with OpenAI-compatible server & CLI No Python environment needed - just download and run.
Updated 2026-11-16 01:12:58 +01:00
Analyze ELF binaries like a boss 😼🕵️‍♂️
Updated 2026-11-16 01:08:03 +01:00
Burn is a next generation Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Updated 2026-11-16 01:01:58 +01:00
Pytorch implementation of MoLA
Updated 2026-11-16 01:01:27 +01:00
A hierarchical inference engine for frontier MoE models: hot experts on the GPU (CUDA, Vulkan), warm ones in RAM, cold ones streamed from NVMe. Written in C, runs on the hardware you already own.
Updated 2026-11-16 00:54:21 +01:00
Upstream pull mirror of https://github.com/8b-is/far.git
Updated 2026-11-16 00:52:09 +01:00
CPU-optimized LLM inference engine (C)
Updated 2026-11-16 00:51:29 +01:00
Official inference repo for FLUX.1 models
Updated 2026-11-16 00:48:54 +01:00
Differentiable Model Predictive Control on the GPU
Updated 2026-11-16 00:44:43 +01:00