Skip to content
@sybil-solutions

Sybil

A place for all things AI
README.md
Sybil Solutions

Sybil Solutions

A place for all things AI.

Website X Email Repos

Sybil Solutions builds local-first tooling for running, steering, and using self-hosted LLM backends. Everything here assumes you own the box it runs on.

Repositories

Repository Language Stars Description
local-studio TypeScript stars Control panel for VLLM, SGLang, llama.cpp, ExLlamaV3
codex-shim Python stars Local Responses-API shim exposing Factory BYOK models (and optional ChatGPT GPT-5.5 passthrough) to Codex Desktop

Focus areas

  • Local model lifecycle — install, launch, and supervise inference engines on your own hardware.
  • OpenAI-compatible proxies — point existing tools at local endpoints without changing call sites.
  • Agent runtimes — run coding agents against local or remote controllers from one surface.

Links

Profile README lives in sybil-solutions/.github. Edit profile/README.md to update this page.

Popular repositories Loading

  1. local-studio local-studio Public

    Control panel for VLLM, Sglang, llama.cpp, exllamav3

    TypeScript 1.8k 166

  2. ai-data-extraction ai-data-extraction Public

    extract all your personal data history from cursor, codex, claude-code, windsurf, and trae

    Python 1.3k 112

  3. codex-shim codex-shim Public

    Local Responses-API shim that exposes Factory BYOK models (and optional ChatGPT GPT-5.5 passthrough) to Codex Desktop.

    Python 1.1k 103

  4. local-ai-registry local-ai-registry Public

    Local AI registry: one validated recipe per machine, with the evidence attached

    HTML 243 46

  5. dsv41-flash-offload dsv41-flash-offload Public

    DeepSeek-V4.1-Flash EXL3 on one 24 GB RTX 3090 + DDR4 + NVMe: staged-DMA prefill, AVX2 CPU expert tier, elastic VRAM expert cache, Engram on disk, OpenAI API

    Python 118 18

  6. omarchy-local-ai omarchy-local-ai Public

    Local AI for Omarchy: the model validated for your GPU, one button on the bar. Start serves it, any coding agent opens on it, one click shares it on your tailnet.

    Shell 116 19

Repositories

Showing 10 of 21 repositories
  • moetier Public

    Minimal data-first standard for MoE expert placement and scheduling across VRAM, RAM and NVMe (records + 500-line core + simulator)

    sybil-solutions/moetier's past year of commit activity
    Python 5 MIT 1 0 0 Updated Oct 8, 2026
  • local-ai-registry Public

    Local AI registry: one validated recipe per machine, with the evidence attached

    sybil-solutions/local-ai-registry's past year of commit activity
    HTML 243 MIT 46 1 17 Updated Oct 8, 2026
  • qwen38-flash-next-b70-offload Public

    Qwen3.8-Flash-Next on one Intel Arc Pro B70 with experts on NVMe and 32 GB host RAM: SGLang + exl3xpu tier, staged NVMe prefill, SYCL sparse attention, measured results

    sybil-solutions/qwen38-flash-next-b70-offload's past year of commit activity
    Python 20 MIT 1 1 0 Updated Oct 8, 2026
  • omarchy-local-ai Public

    Local AI for Omarchy: the model validated for your GPU, one button on the bar. Start serves it, any coding agent opens on it, one click shares it on your tailnet.

    sybil-solutions/omarchy-local-ai's past year of commit activity
    Shell 116 MIT 19 3 1 Updated Oct 8, 2026
  • local-ai-images Public

    Attested container images pinned by the local-ai registry

    sybil-solutions/local-ai-images's past year of commit activity
    Python 8 1 1 1 Updated Oct 8, 2026
  • glm53-flash-offload Public

    GLM-5.3-Flash EXL3 on one 24 GB RTX 3090 + DDR4: elastic GPU expert cache, zero-copy experts, AVX2 CPU tier, OpenAI API

    sybil-solutions/glm53-flash-offload's past year of commit activity
    Python 113 MIT 9 1 0 Updated Oct 8, 2026
  • ai-data-extraction Public

    extract all your personal data history from cursor, codex, claude-code, windsurf, and trae

    sybil-solutions/ai-data-extraction's past year of commit activity
    Python 1,345 112 2 4 Updated Oct 7, 2026
  • dsv41-flash-offload Public

    DeepSeek-V4.1-Flash EXL3 on one 24 GB RTX 3090 + DDR4 + NVMe: staged-DMA prefill, AVX2 CPU expert tier, elastic VRAM expert cache, Engram on disk, OpenAI API

    sybil-solutions/dsv41-flash-offload's past year of commit activity
    Python 118 MIT 18 0 0 Updated Oct 7, 2026
  • trellis-serve Public

    EXL3 (ExLlamaV3 trellis quantization) in stock SGLang and vLLM on RTX 3090 and Intel Arc B70, bit-exact with ExLlamaV3

    sybil-solutions/trellis-serve's past year of commit activity
    Python 2 MIT 2 0 3 Updated Oct 7, 2026
  • local-studio-site Public

    Frontend https://localstudio.ai

    sybil-solutions/local-studio-site's past year of commit activity
    TypeScript 0 0 0 0 Updated Oct 5, 2026
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…