-
@nandaiart
- Vancouver, BC
- https://nandai.store
- in/karanyadav97
- @karany97
- https://nandai.store
Pinned Loading
-
nandai-atelier
nandai-atelier PublicDestiny Atelier — single-file local AI chat. Three brains vote on every answer. 540 KB. 108 MCP tools. Open-source local Claude / GPT alternative. Local LLM. Runs on your own hardware.
HTML
-
atelier-os
atelier-os PublicMulti-session AI desktop fleet. Sway+Wayland+wayvnc+noVNC. Per-employee container, iframe-embeddable, action-daemon for fast clicks. 259/259 tests. MIT.
Python 1
-
moa-router
moa-router PublicSelf-MoA (ICLR 2025) as a drop-in OpenAI-compatible proxy. Fan to 2 LLM upstreams, synthesize verbatim. +3.8%–6.6% on reasoning. 627 LOC FastAPI.
Python
-
llamacpp-gemma4-mtp
llamacpp-gemma4-mtp PublicReproducible Gemma 4 multi-token-prediction bench harness for ik_llama.cpp. PR #1744 merged 2026-05-10. 2.6-2.98x lossless speedup verified. Two scripts to clone, build, bench.
Shell 2
-
tooltalk
tooltalk PublicDrop-in middleware translating Gemma 4 text-format tool calls into OpenAI structured tool_calls. Streaming-safe, quote-tolerant. 972 LOC FastAPI.
Python
-
pingate
pingate PublicThe simplest signed-cookie PIN gate for any local AI tool. HMAC-SHA256 cookie auth + reverse proxy + WebSocket passthrough + optional LiteLLM proxy + CSS theme injection. 544 LOC FastAPI. MIT.
Python
If the problem persists, check the GitHub status page or contact support.


