Lists (17)
Stars
The open-source System One decision model. Sub-15ms, non-autoregressive, local drop-in alternative to TypeSafe Jev.
A massively multilingual modern encoder language model
Generalist and Lightweight Model for Text Classification
Datasets, scripts and results for the paper "The Pain Axis" by Valen Tagliabue, Leonard Dung & Cameron Berg
[MCP-001] Template architecture for an MCP server that gives any LLM structured access to your database. Layered design, schema mapping, read only guardrails, predefined queries. Part of AI for Fin…
Local-first search across your workspace, built for humans and AI agents.
DeepSeek Harness: Everything is a Plugin.
Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent…
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
24/7 AI-DJ radio in Go. Persistent ffmpeg→Icecast with live ducking, LLM banter, BYOK, editable skills. ~50MB RAM.
SONNY OS is an ultra-lightweight, agnostically unified open-source microkernel for any robot (arms, AMRs, drones, humanoids). Built in Rust and Zenoh, it replaces ROS 2 by eliminating memory leaks …
Real-time text-to-speech with Qwen3-TTS
NVIDIA DeepStream Monorepo: DeepStream SDK and reference apps for building GPU‑accelerated, real-time video and multi‑sensor analytics pipelines with GStreamer, TensorRT, and vision AI models acros…
Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, trade-offs, and numbers, not prompt tips
Official implementation of ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation (SIGGRAPH 2026).
Community plugin to control Blender 3D with any LLM of your choice
[RSS 2026] Causal video-action world model for generalist robot control
Time-Series-Optimized Transformer for Observability
The BABEL codec - a certified two-way dictionary between GPT-2's internal state and plain English. Paper + frozen artifacts + verdict-bearing repro harnesses.
Autonomous follow system for the Unitree Go2 robot using UWB tracking, YOLO-based vision and PID motion control.
One local API call gives your agent the entire live state of the planet — every major world event at once, plus forecasts. 40+ free keyless feeds, runs entirely on Ollama. No cloud, no cost. Keyles…
Minimal, fast + educational reimplementation of the TabICLv2 architecture + prior
Training code for TabDPT: Scaling Tabular Foundation Models on Real Data
[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥