8000 kduxin (Xin Du) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View kduxin's full-sized avatar

Highlights

  • Pro

Block or report kduxin

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Browser use using Typesafe's Jev model

JavaScript 375 35 Updated Nov 17, 2026

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Python 428 63 Updated Nov 13, 2026

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

Python 1,309 123 Updated Sep 29, 2026

An LLM built without a language model — using TypeSafe Jev's non-generative AI for contextual response selection. Zero hallucination. Zero prompt injection.

JavaScript 2 Updated Sep 21, 2026

Autonomous robotics research with simulation feedback

Python 19 2 Updated Mar 10, 2026

Value-guided action selection and self-improvement for frozen behaviour-cloning policies

Python 74 6 Updated Aug 24, 2026

AI agents running research on single-GPU nanochat training automatically

Python 100,334 13,792 Updated Mar 26, 2026

SSH remote workspaces for DeepSeek Harness: parallel projects across hosts, remote file browsing and editing, recursive search, terminals, Git diffs, and workspace-bound Agent tools to edit, build …

JavaScript 338 59 Updated Nov 20, 2026

Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX.

Python 1,778 169 Updated Oct 23, 2026

JevStyle: local decision models for AI agents. Classify, route and score with a probability per option. systemone-compatible local server, MCP tools, Claude Code guard. Open weights, Apache-2.0.

Python 138 4 Updated Nov 4, 2026

SMAC: The StarCraft Multi-Agent Challenge

Python 1,377 243 Updated Feb 18, 2024
Python 334 53 Updated Feb 15, 2024

The Starcraft Multi-Agent challenge lite

Python 50 9 Updated Sep 13, 2024

The NVIDIA-native robotics stack for deploying humanoids, mobile robots and manipulators.

C++ 23 2 Updated Oct 30, 2026

🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or…

TypeScript 37,679 4,281 Updated Nov 20, 2026

Hierarchal Agent Loop Optimizer

TypeScript 1,219 101 Updated Oct 26, 2026

Qwen3.8-Flash-Next is the foundation model developed by Qwen Team, Alibaba Group.

485 31 Updated Aug 27, 2026

SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

Python 6,943 534 Updated Nov 20, 2026

EMER, OV-MER (ICML25), AffectGPT (ICML25, Oral), EmoPrefer (ICLR26), AffectGPT-RL (NeurIPS26)

Python 441 39 Updated Oct 13, 2026

Jev-like family of decision models built on top of Qwen3.5/3.8 you can train and run on your own

Python 10,074 690 Updated Nov 20, 2026

Open multimodal decision models, 0.8B to 27B, for text, images and video. Decide with probabilities over your own candidates and locate with bounding boxes, in place of generated text. Free API, ON…

Python 932 88 Updated Nov 15, 2026

Geometric regulation and correlation dimension tracking for autoregressive text generation in C++

C++ 1 Updated May 6, 2026
Python 1,064 86 Updated Nov 5, 2026

同济大学毕业设计论文 LaTeX 模板 | TongjiThesis - LaTeX Thesis Template for Tongji University

TeX 478 53 Updated Oct 30, 2026
Python 1,599 220 Updated Oct 27, 2025

[ICLR 2025] Released code for paper "Spurious Forgetting in Continual Learning of Language Models"

Jupyter Notebook 64 6 Updated May 9, 2025

Pretraining and inference code for a large-scale depth-recurrent language model

Python 993 90 Updated Dec 29, 2025

Embodied intelligence memory for physical AI robots. Built on PowerMem + SeekDB. Zero ROS dependency. Brain-like architecture with spatial-temporal-causal graphs, DTW trajectory search, and gRPC.

Python 7 Updated Sep 16, 2026

Official implementation of the transformer (TF) architecture suggested in a paper entitled "Looped Transformers as Programmable Computers"

Jupyter Notebook 50 8 Updated Apr 8, 2023
Next
0