deep-thinking

A large language model (LLM) plugin for Neovim, provides commands to interact with LLM (like ChatGPT, Copilot, ChatGLM, kimi, deepseek, openrouter and local llms). Support Github models.

Deepdive: Deep iterative thinking slash command for Claude Code - enables multi-round exploratory reasoning and non-linear problem-solving

MCP server for unified cognitive processing — deep reasoning framework for Cline, Claude & AI code assistants

🔥 This time, the AI interrogates YOU. Progressive Socratic questioning engine with 5 depth levels, 7 flavors, and anti-deflection system. Supports Claude Code, Codex CLI, Cursor, Kiro, OpenClaw.

A Claude skill that enforces deep reasoning, web-searched citations, multiple perspectives, and visual illustrations on every response

This repo contains all Codes in C that are not a part of Competitive programming like CSES that I do for better understanding

Cognitive architecture for AI agents. 19 skills that force language models past surface-level reasoning into genuine depth. Compatible with Claude Code, Cursor, Gemini CLI, Copilot, and any agent that reads markdown.

专为AI Agent设计的轻量级思维树+代码深度分析插件。两级触发链（开启思维树→开启深度思考模式），耦合基因库省Token，支持5语言函数级分析、安全/性能/逻辑检测、沙箱动态测试。零依赖，手机端Termux流畅运行。

AI-assisted structured deep thinking — pin any AI reply to branch an isolated sub-thread, infinite nesting, one-click merge. Next.js + FastAPI + Supabase + 5-provider SmartRouter.

🌱 工程化跑出来的深度思考实验场 · 每日中英双语原创 | Daily bilingual deep-dives on growth, learning & AI, written through a 13-step pipeline

Deep-Harness is a Codex skill for rigorous artifact improvement and AI-agent harness engineering through intent analysis, AI-compiled multi-role review, traceable edits, and independent verification.

Dash · Emergent Outlier Intelligence — local LLM map-reduce framework with content-hash cache, streaming reduce, LLM-as-judge, persona panel, ratcheting quality floor, and 1M-4M token capacity on a single GPU. ⚡

CLI bridge for delegating heavy reasoning from Claude Code to Gemini API. Auto-routing, deep thinking tiers, SHA256 caching, daily budget enforcement. Python.

🧠 AI 深度思考笔记 | Deep thoughts on AI, technology, and life by 王爱成

Maximum reasoning + multi-agent orchestration framework for AI coding assistants. Adaptive 6-phase pipeline: ultrathink analysis, parallel research, architecture, parallel execution, synthesis, and quality gate.

全域深度分析框架-Profound Cognition