This repository provides a comprehensive starter kit for leveraging GitHub's GPT-4o AI models with Node.js.
-
Updated
Jun 26, 2025 - JavaScript
#
reasoning-model
Here are 13 public repositories matching this topic...
Qwen & Deepseek V4 PRO: A Powerful 4B AI Fusion! - Distilled 4B STEM reasoning engine with MTP speculative decoding.
-
Updated
Aug 15, 2026 - Python
DeepSeek Mechanism Atlas — V1→V4 mechanisms (MLA/MoE/DSA/DSpark) as a bidirectional wiki + mdBook. Unofficial.
-
Updated
Jul 31, 2026 - Python
Fixes Step 3.7 Flash, Nemotron 3 Ultra and Kimi k2.6 (NIM Endpoint) silently returning empty responses in Continue.
-
Updated
Jun 14, 2026 - Python
CPU-trained reasoning model pipeline. LoRA SFT + DPO on SmolLM2-360M, GSM8K math reasoning, single-laptop deployment.
-
Updated
Jul 12, 2026 - Python
The agent that grows with you
python conversational-ai agent-framework autonomous-agent ai-agent agentic-ai tool-calling reasoning-model llm-assistant multi-turn-agent
-
Updated
Jun 17, 2026 - Python
PAMELA 行为指纹识别系统：基于单 token 输出分布的 Jensen-Shannon Divergence 度量，识别 LLM API 真实身份。内置 173 个模型参考指纹库（涵盖 OpenAI/Anthropic/Google/Meta/Qwen/DeepSeek/GLM/Mistral/Moonshot/Llama/Nvidia/Amazon/Nous/Cohere/ByteDance 等 30+ 厂商），工具无关——任何能调 LLM API 的客户端（curl/Python/浏览器/Hermes/OpenClaw/Codex）都能采集。Apache-2.0/MIT/CC-BY-4.0
glm jensen-shannon-divergence ai-safety claude pamela model-identification llm token-distribution behavioral-fingerprinting anthropic zhipu reasoning-model model-fingerprint behavioral-signature llm-fingerprint ai-model-detection api-fingerprinting jsd-analyzer llm-identification model-id
-
Updated
Jul 21, 2026 - Python
nori - evidence-driven AI answer engine with a bring-your-own-key chat UI. Runs strategies in parallel, streams real chain-of-thought, and synthesizes the best-of-all answer. Zero runtime dependencies.
python agent benchmark ai chatbot multi-agent chat-ui reasoning agent-framework llm byok chain-of-thought ollama llm-agents deepseek openai-compatible reasoning-model
-
Updated
Aug 10, 2026 - Python
Web app for creating structured LLM prompts for reasoning tasks
-
Updated
Apr 4, 2025 - Makefile
A real-time AI Incident Commander demo. Yaqzan connects a deterministic disaster simulation engine to a reasoning LLM (K2 Think V2) for live, verifiable emergency response and tactical triage.
-
Updated
Jun 15, 2026 - TypeScript
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
-
Updated
Jun 23, 2026 - Python
Run a 27B thinking model locally on consumer hardware — ternary / 1-bit Bonsai 27B on Apple Silicon (Metal) or NVIDIA (CUDA, 8 GB VRAM), with an OpenAI-compatible API and a web chat UI. Fully offline.
macos docker privacy metal cuda self-hosted quantization ternary apple-silicon llm llama-cpp local-llm gguf offline-ai open-webui openai-compatible-api reasoning-model 1-bit-llm
-
Updated
Aug 24, 2026 - Shell
Autonomous 1.58-Bit Local AI Desktop Studio with Real-Time Streaming, ChatGPT-Style Canvas, RLVR Sandbox, and EWC Sleep Consolidation
desktop-app reinforcement-learning ai mcp tkinter code-generation mlx ewc bitnet apple-silicon llm local-ai qwen bitlinear reasoning-model ai-canvas rlvr sleep-consolidation ternary-bonsai dolphin-vision
-
Updated
Aug 30, 2026 - Python
Improve this page
Add a description, image, and links to the reasoning-model topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the reasoning-model topic, visit your repo's landing page and select "manage topics."