布萊嗯研究所

上傳數據，智能推薦圖表，一鍵生成交互式可視化 / Upload data, get smart chart recommendations, and generate interactive visualizations in one click. 🔎 工具速覽 / AT A GLANCE Category AI Data Visualization / AI 數據可視化 Pricing Open Source (GPL3.0) / 開源 BestFor Data Analysts, Business Intelligence, Non-technical Users / 數據分析師、商業智能、非技術用戶 GitHub Stars ⭐ 37 🚀 引言 / Introduction VizPilot AI 是一款將大語言模型（LLM）與強大可視化庫 Plotly 深度結合的智能系統。它打破了數據分析中『不知道該用什麼圖表』的痛點，讓用戶無需掌握複雜的數據分析理論，即可將乾枯的 CSV/Excel 轉換為具有洞察力的交互式圖表。 VizPilot AI is an LLM-powered intelligent system that merges the capabilities of Large Language Models with the Plotly visualization library. It solves the common pain point of 'not knowing which chart to use,' enabling users to transform raw CSV/Excel data into insightful interactive visualizations without needing deep expertise in data analysis theory. 🛠️ 核心功能 / Key Features ...

終結 AI 的『記憶喪失』，讓智能體在對話間持續進化。 | Ending AI amnesia, letting agents evolve continuously across sessions. 🔎 工具速覽 / AT A GLANCE Category AI Infrastructure / Memory Layer Pricing Open Source (Apache 2.0) BestFor AI Agents, MCP-compatible workflows, Long-term context management GitHub Stars ⭐ 61 🚀 引言 / Introduction 每個 LLM 每次對話都像是在從零開始。Stash 為您的 AI 智能體提供了一個持久記憶層，使其能夠在不同對話階段中記憶、回溯、整合並學習。您再也不需要重複解釋相同的事情。 | Every LLM starts every conversation from zero. Stash provides your AI agent with a persistent memory layer, enabling it to remember, recall, consolidate, and learn across sessions. No more explaining yourself from scratch. 🛠️ 核心功能 / Key Features Cognitive Layer Transformation: Converts raw episodes into facts, facts into relationships, and eventually into wisdom. 認知層級轉化：將原始片段轉化為事實，事實轉化為關係，最終演進為智慧。 8-Stage Consolidation Pipeline: Deep processing i...

一個專為測試大模型在長程規劃與持續學習能力而設計的開放式遊戲生成與評估框架。 / An open-ended game generation and evaluation framework designed to test the long-horizon planning and continual learning capabilities of LLM agents. 🔎 工具速覽 / AT A GLANCE Category AI Agent Evaluation Framework / LLM Research Tool Pricing Free / Open Source BestFor AI researchers studying continual learning, long-horizon planning, and autonomous agents. GitHub Stars ⭐ 37 🚀 引言 / Introduction AgentOdyssey 是一個輕量級的交互式環境，旨在挑戰 AI Agent 在未知環境中的適應能力。它不僅能生成全新的長程文字遊戲，更提供了一套嚴謹的評估機制，用以衡量 Agent 在測試時的持續學習表現。 / AgentOdyssey is a lightweight interactive environment designed to challenge the adaptability of AI agents in unknown environments. It not only generates novel long-horizon text games but also provides a rigorous evaluation mechanism to measure the test-time continual learning performance of agents. 🛠️ 核心功能 / Key Fea...

利用深層學習驅動的高性能框架，消除視覺偽影並實現高保真圖像修復。 | A high-performance deep learning framework designed to eliminate visual artifacts and achieve high-fidelity image restoration. 🔎 工具速覽 / AT A GLANCE Category Computer Vision / AI Restoration Pricing Free (MIT License) BestFor ML Engineers, Digital Artists, Data Scientists GitHub Stars ⭐ 44 🚀 引言 / Introduction 隨著生成式 AI 內容的普及，如何高效移除視覺偽影與雜訊成為業界痛點。Neural Vision Cleanup Suite (NVCS) 正是為此而生，透過頂尖的深度學習架構，將雜亂的生成素材轉化為專業級的生產資產。 | As AI-generated content becomes ubiquitous, the efficient removal of visual artifacts and noise has become a critical industry challenge. Neural Vision Cleanup Suite (NVCS) is engineered to bridge this gap, utilizing state-of-the-art deep learning architectures to transform raw generative assets into professional-grade production materials. 🛠️ 核心功能 / Key Features Generative Artifact Remova...

從需求研究到代碼提交的端到端自動化開發工作流 / An end-to-end automated development workflow from requirement research to code commit. 🔎 工具速覽 / AT A GLANCE Category AI Agentic Coding Workflow Pricing Open Source (MIT License) BestFor Medium to Large-scale Engineering Projects GitHub Stars ⭐ 89 🚀 引言 / Introduction AI Auto-Work 是一個革命性的代理編碼工作流系統，它將 LLM 的能力從單純的代碼補全提升到了完整的工程管理層級。透過 Claude 與 Codex 的雙模型協作，實現了從需求分析、規劃到開發與審查的閉環自動化。 AI Auto-Work is a revolutionary agentic coding workflow system that elevates LLM capabilities from simple code completion to full-scale engineering management, utilizing a dual-model collaboration between Claude and Codex to achieve a closed-loop automation of research, planning, development, and review. 🛠️ 核心功能 / Key Features Full-Cycle Autonomous Development: Covers the complete lifecycle from Requirement Research → Review → Planning → Rev...

從手動調試到自動化管線，定義 LLM 應用開發的新標準。 | From manual tuning to automated pipelines, defining the new standard for LLM application development. 🔎 工具速覽 / AT A GLANCE Category LLMOps / Prompt Engineering Framework Pricing Open Source / Enterprise Build BestFor Prompt Engineers, ML Developers, and Data Scientists scaling GenAI workflows GitHub Stars ⭐ 44 🚀 引言 / Introduction 隨著 AI 應用規模的擴張，提示詞（Prompt）的管理複雜度已成為開發者的核心痛點。LLM-Prompt-Orchestration-Engine 提供了一個專業級的框架，將提示詞從簡單的文字片段轉化為可版本化、可測試且高度優化的軟體資產。 | As AI applications scale, the complexity of prompt management has become a critical bottleneck. LLM-Prompt-Orchestration-Engine provides a professional-grade framework that transforms prompts from simple text snippets into versioned, testable, and highly optimized software assets. 🛠️ 核心功能 / Key Features Dynamic Templating Engine: Powered by Jinja2 for creating...