Projects

Overview: Guess.js is a library and toolset designed to enable data-driven user experiences on the web, leveraging machine learning and Google Analytics for predictive analytics. Key features: - Data-driven bundling - Data-driven loading - Predictive fetching for sites Tech stack: TypeScript Why it matters: Guess.js simplifies the implementation of predictive data-analytics thinking, making it easier to apply these approaches to modern web applications and sites, including integrating predictive fetching using the Google Analytics API.

### Overview: OpenSquilla is a token-efficient, microkernel AI agent designed for CLI, Web UI, and chat channels, offering the same budget with higher intelligence density. It uses a local model router to send turns to the cheapest model, complemented by persistent memory, a sandboxed environment, built-in web search, and on-device embeddings. ### Key Features: - **Token-Efficient Routing**: Sends each turn to the cheapest model that can handle it. - **Persistent Memory**: A shared turn loop across multiple entry points. - **Layered Sandbox**: Built-in web search and on-device embeddings. - **Multi-Model Ensemble Routing**: Outperforms Fable 5. - **Pluggable Providers**: Supports 20+ LLM providers with no changes to code or config schema. - **Stable Release**: Version 0.5.6 is the current stable release. ### Tech Stack: Python ### Why it Matters: OpenSquilla provides a token-efficient, microkernel AI agent that offers the same budget with higher intelligence density, making it suitable for various applications and environments.

### Overview: iPolloWork is an enterprise-grade, local-first Agent Workbench designed for people and agent teams. It provides a unified workspace for multiple agent engines, plugins, and Skills, enabling seamless collaboration and editing across code, documents, presentations, and video. ### Key Features: - **Unified Workspace**: One workspace for multiple agent engines, plugins, and Skills. - **Multi-Agent Projects and Tasks**: Supports multi-agent projects and tasks. - **Editable Code, Documents, and Presentations**: Allows teams to edit and review code, documents, and presentations in real-time. - **Cross-Platform Compatibility**: Compatible with Codex, DeepSeek Harness, and OpenCode, ensuring seamless integration with future agent runtimes. ### Tech Stack: TypeScript ### Why it Matters: iPolloWork is the unified workspace layer for the next agent-native way of working. It provides a single control surface for agents, tasks, schedules, plugins, Skills, tools, execution, and editable outputs, enabling teams to coordinate, plan, and review progress in the same place.

### Overview: Magnitude is an open-source inference engine that optimizes model performance on various hardware architectures, including Apple Silicon, NVIDIA, AMD, and CPUs. It significantly outperforms competitors like Ollama, offering up to 2x faster execution times and is designed to be easily integrated with existing agents. ### Key Features: - **2x Faster Than Ollama:** On average across popular local models, on Mac and NVIDIA. - **Hardware-Tuned Kernels:** Automatically tunes kernels for each model when downloading it. - **Speculative Decoding Drafter:** Ships with the fastest speculative decoding drafter for each model. - **Quantized KV Memory Management:** Halves memory usage per agent when agents stop, freeing up resources. - **Concurrent Sessions:** Sessions share prefix caches to prevent slowdowns. - **Agent Compatibility:** One-click integration with popular agents like Pi, OpenCode, Hermes, and Codex. - **Free, Private, Open Source:** No token costs, no data leaves the machine, Apache 2.0 license. ### Tech Stack: Rust ### Why It Matters: - **2x Faster than Ollama:** On average across popular local models, on Mac and NVIDIA. - **Tuned on Hardware:** Automatically optimizes performance for each model. - **Best Drafter Built In:** Ships with the fastest speculative decoding drafter. - **Memory Efficiency:** Halves memory usage per agent when agents stop. - **Fast Concurrency:** Sessions share prefix caches to prevent slowdowns. - **Agent Compatibility:** One-click integration with popular

Overview: 这个项目是基于Meta发布的可商用大模型Llama-2开发的，是中文LLaMA&Alpaca大模型的第二期项目。项目开源了中文LLaMA-2基座模型和Alpaca-2指令精调大模型，支持FlashAttention-2训练。标准版模型支持4K上下文长度，长上下文版模型支持16K、64K上下文长度。RLHF系列模型为标准版模型基础上进行人类偏好对齐精调，相比标准版模型在正确价值观体现方面获得了显著性能提升。 Key features: - 开源了中文LLaMA-2和Alpaca-2大模型 - 支持FlashAttention-2训练 - 提供预训练脚本和指令精调脚本 - 支持4K、16K和64K上下文长度 - 为RLHF系列模型提供人类偏好对齐精调 Tech stack: Python Why it matters: 这些模型在原版Llama-2的基础上扩充并优化了中文词表，使用了大规模中文数据进行增量预训练，进一步提升了中文基础语义和指令理解能力，相比一代相关模型获得了显著性能提升。

Overview: Plano is an AI-native proxy server and data plane designed for agentic applications, simplifying the delivery of agents by centralizing core concerns like routing, orchestration, and observability. Key features: - **Orchestration**: Low-latency orchestration between agents. - **Model Agility**: Route models by name, alias, or via preferences. - **Agentic Signals**: Zero-code capture of Signals and OTEL traces/metrics. - **Moderation & Memory Hooks**: Build jailbreak protection, moderation policies, and memory hooks. Tech stack: Rust Why it matters: Plano simplifies the delivery of agentic applications, reducing the complexity of "hidden middleware" and focusing developers on the core logic of their applications. The AI-native approach and Envoy integration make it a powerful tool for modern software development. Repository: katanemo/plano Primary language: Rust GitHub stars: 7091 GitHub description: Plano is an AI-native proxy server and data plane for agentic apps. Smart LLM routing, observability, agent orchestration, and guardrails so you stay focused on your agents core logic. Use any language or AI framework, and deliver agents faster to production. [Quickstart Guide](https://docs.planoai.dev/get_started/quickstart.html) • [Build Agentic Apps with Plano](#Build-Agentic-Apps-with-Plano) • [Documentation](https://docs.planoai.dev) • [Contact](#Contact) [![CI](https://github.com/katanemo/pl

### Overview: WantWords is an open-source online reverse dictionary system designed to help users find words that match their descriptions. It is based on a unique multi-channel reverse dictionary model that can assist in solving the "tip-of-the-tongue problem," helping language learners, and aiding individuals with word selection issues. ### Key features: - **Reverse Dictionary Functionality:** Returns words that are semantically similar to the query descriptions. - **Django Integration:** Built using Django, allowing for a robust and scalable backend. - **Pre-trained Models and Data:** Available for download to quickly set up the system locally. - **Workflow Diagram:** Illustrates the process of how the system works, emphasizing the multi-channel approach. - **Core Model:** Based on the Multi-channel Reverse Dictionary Model, which is described in detail in the paper. ### Tech stack: - **Frontend:** React.js - **Backend:** Django - **Database:** PostgreSQL ### Why it matters: - **Solves Common Language Problems:** Helps users quickly retrieve words they can't recall, aiding in memory recall and language learning. - **Versatile Application:** Useful for language learners, individuals with neurological disorders, and anyone looking to expand their vocabulary. ### Repository: - **GitHub Repository:** thunlp/WantWords - **GitHub Stars:** 7092 - **Primary Language:** JavaScript ### Primary Language: - **JavaScript** ### GitHub Description: An open-source online reverse dictionary.

Overview: GEPA (Genetic-Pareto) is a framework designed to optimize any system with textual parameters using LLM-based reflection and Pareto-efficient evolutionary search. It excels in diagnosing and optimizing prompts, code, and more, outperforming RL and gradient-based methods by leveraging full execution traces for more comprehensive optimization. Key features: - Optimizes prompts for math problems - Enhances code quality - Improves agent architectures and scheduling policies - Supports various text parameters and evaluation metrics Tech stack: Python with Jupyter Notebook Why it matters: GEPA provides a more comprehensive and efficient way to optimize systems by leveraging LLMs to read and analyze full execution traces, leading to better performance and reduced costs. Repository: gepa-ai/gepa GitHub stars: 7,075 GitHub description: Optimize prompts, code, and more with AI-powered Reflective Optimization README excerpt: Optimize any text parameter — prompts, code, agent architectures, configurations — using LLM-based reflection and Pareto-efficient evolutionary search. Tech stack: Python with Jupyter Notebook Why it matters: GEPA provides a more comprehensive and efficient way to optimize systems by leveraging LLMs to read and analyze full execution traces, leading to better performance and reduced costs. GitHub stars: 7,075

Overview: DeepChem aims to democratize the use of deep learning in drug discovery, materials science, quantum chemistry, and biology by providing a high-quality open-source toolchain. Key features: - Deep learning models for drug discovery - Quantum chemistry simulations - Materials science analysis - Biological data analysis Tech stack: Python Why it matters: DeepChem simplifies the application of deep learning to complex scientific problems, making it accessible to researchers and developers across various fields.

### Overview: This project integrates an AI agent (Cursor, Claude Code, Codex) with Figma, enabling the AI agent to communicate with Figma for reading designs and modifying them programmatically. This allows for more efficient design automation and collaboration between AI and human designers. ### Key features: - **Figma Plugin for Cursor**: A Figma plugin that allows the AI agent to communicate with Figma. - **WebSocket Server**: Facilitates communication between the MCP server and the Figma plugin. - **Bulk Text Replacement**: A feature that allows for bulk text content replacement in designs. - **Instance Override Propagation**: Propagates component instance overrides from a source instance to multiple target instances. ### Tech stack: TypeScript, Node.js, WebSocket, and Figma API. ### Why it matters: This integration streamlines design workflows, enabling AI agents to easily read and modify designs directly within Figma, improving collaboration and productivity.

Overview: DeepPavlov is an open-source library designed for the development and deployment of state-of-the-art deep learning models for natural language processing tasks. Key features: - Modular and configuration-driven development - Support for a wide range of NLP model applications - Integrates with PyTorch and transformers - Provides a comprehensive documentation and community resources Tech stack: Python Why it matters: DeepPavlov simplifies the process of creating and deploying advanced NLP models, making it accessible to practitioners with limited knowledge in the field.

### Overview: Trafilatura is a comprehensive Python package designed to gather text from the Web and extract structured data, including text, metadata, and comments. It supports advanced web crawling, text discovery, and efficient processing of HTML files, making it a versatile tool for developers. ### Key Features: - **Advanced Web Crawling**: Supports sitemaps (TXT, XML) and feeds (ATOM, JSON, RSS) for comprehensive web discovery. - **Parallel Processing**: Efficiently processes live URLs and download queues, and supports previously downloaded HTML files and parsed HTML trees. - **Robust Extraction**: Extracts key elements like main text, metadata, formatting, and comments, with optional add-ons for language detection and speed optimizations. - **Output Formats**: Supports multiple formats including TXT, Markdown, CSV, JSON, HTML, and XML-TEI. ### Tech Stack: Python ### Why It Matters: Trafilatura is widely used across thousands of projects, including by HuggingFace, IBM, Microsoft Research, NVIDIA, the Allen Institute for AI, Stanford, and the Internet Archive, making it a reliable and efficient tool for developers looking to gather and extract meaningful data from the web.

### Overview: Serpent.AI is a powerful, game-based framework that allows developers to create AI agents for any video game they own. It simplifies the process of creating and training agents, making it a valuable tool for both research and hobby use. ### Key Features: - **Game Support**: Serpent.AI supports a wide variety of games, including those from popular franchises like "The Binding of Isaac: Afterbirth+." - **Plugin-Based Architecture**: Agents can be created using plugins, allowing for flexibility and portability. - **Python Backend**: The framework is built on Python, making it easy to integrate with existing Python projects. - **CLI Tools**: Command-line interfaces are provided to speed up development and experimentation. - **Community and Documentation**: A growing community and comprehensive documentation are available on GitHub and the blog. ### Tech Stack: Python ### Why it Matters: Serpent.AI offers a unique and powerful way to create AI agents for video games, making it a valuable tool for both research and personal projects. Its flexibility and ease of use make it accessible to a wide range of developers, from beginners to advanced researchers. Repository: SerpentAI/SerpentAI GitHub Stars: 6990 GitHub Description: Game Agent Framework. Helping you create AIs / Bots that learn to play any game you own!