一个先进的聊天应用,演示了一种独特的对话范式:用户的查询首先由两个不同的人工智能角色进行辩论和提炼,然后才提供最终的综合答案。该项目利用 Google Gemini API 驱动一个逻辑型 AI (Cognito) 和一个怀疑型 AI (Muse),它们协作生成更健壮、准确和经过严格审查的响应。
-
Updated
Jul 16, 2026 - TypeScript
一个先进的聊天应用,演示了一种独特的对话范式:用户的查询首先由两个不同的人工智能角色进行辩论和提炼,然后才提供最终的综合答案。该项目利用 Google Gemini API 驱动一个逻辑型 AI (Cognito) 和一个怀疑型 AI (Muse),它们协作生成更健壮、准确和经过严格审查的响应。
Advanced cognitive reasoning MCP server — DAG thought graph, 10 strategies, metacognition, self-critique, knowledge integration, and pruning
One-line fix: inject a fixed system-prompt section so the agent always thinks and replies in Chinese, whatever the user's language · 中文思考:注入固定提示词,让 agent 始终用中文思考与回复(无论用户语言)
🧠 Open-source AI reasoning research platform — persistent reasoning graphs, multi-agent swarms, Graph-of-Thoughts, and MemGPT-style memory. Built with Claude Opus 4.6 by Anthropic. Explore, verify, and fork AI thinking in real-time.
A collection of Concepts
让 DeepSeek Harness 的思考状态被看见——零侵入地将 reasoning 等待转化为由蓝到金、持续升温的动态 ThinkBar。
DSH「大胖鲸智商检测器」:Thinking 短语检测统计 · 全会话 reasoning 短语命中/分组/聪明程度判定
MemEX: Epistemic memory for AI agents. A structured memory for knowledge as an evolving belief state, with explicit provenance, scoring, and contradiction-aware updates.
Universal LLM provider compatibility layer — normalizes provider-specific payload differences (thinking formats, output budgets, tool pairing, media transport) into a single first-match-wins dispatch pipeline. Plus dynamic version detection with strategy-pattern version parsing.
DSH 插件:直接在 DeepSeek Harness 对话里编辑任意 AI 消息的正文与思维链(thinking)。保留 AI 的聪明,让 AI 完全符合你的心意。🐛 修复选中删除联动清空问题。| DeepSeek Harness plugin to edit any assistant reply + reasoning/thinking chain. Make the AI output truly yours.
DSH web plugin: cap expanded thinking blocks with a bounded scroll window.
Coach-style deep thinking skill for AI Agents — 68 structured thinking modules, Chinese-Western fusion methodology · AI Agent深度思考教练:68个思维元件+中西融合方法引擎
pi coding-agent extension: live-translate assistant thinking (EN→zh) in the TUI via local llama.cpp (Hy-MT2-1.8B)
Research-grounded structured thinking + steel-manning verification for AI agents via MCP. Sequential step tracking with cognitive mode separation. Backed by 43+ papers.
To associate your repository with the thinking topic, visit your repo's landing page and select "manage topics."