AI Agents & Automation

MindHalo is an intelligent study companion exclusively for macOS, designed to help students master their textbooks using local AI. Users can upload PDF textbooks and other documents, transforming them into an intelligent, searchable study database. The AI tutor provides answers grounded in the user's materials, citing specific pages for accuracy. It also generates study guides, flashcards, and practice quizzes from any chapter with a single click. MindHalo operates 100% locally on Apple Silicon Macs, ensuring privacy and fast performance without cloud dependency or data fees. It offers a gamified learning experience with coins and streaks, and is free to start with an optional Pro upgrade for unlimited access.

My Drawer is a macOS sidebar application designed to enhance productivity by integrating an intelligent AI layer directly into the desktop experience. Users can engage in AI chats, manage their clipboard history, and efficiently organize windows without disrupting their workflow. A key differentiator is its commitment to privacy, operating 100% locally on the user's machine. This open-source tool is built with Rust and Tauri, offering a secure and private environment for various productivity tasks. It aims to be a seamless, always-available assistant for macOS users looking to streamline their digital interactions and maintain control over their data.

AISP is an official open-source library for AI Image Signal Processing and Computational Photography, developed by mv-lab. It serves as a comprehensive resource for researchers and developers working on low-level computer vision and imaging tasks. The library includes implementations for learned Image Signal Processors (ISPs), RAW image restoration, super-resolution, and reconstruction from sRGB. Additionally, it offers functionalities for image enhancement such as denoising and deblurring, and advanced features like bokeh rendering. AISP is actively used in prominent challenges like NTIRE (CVPR) and AIM (ICCV/ECCV), providing base code and solutions for various image processing tasks, including tutorials for generating degraded RAW images and training restoration methods.

ChatLab is an open-source desktop application designed to help users rediscover and analyze their social memories through local, AI-powered analysis. It combines a flexible SQL engine with AI agents to enable exploration of patterns, asking better questions, and extracting insights from chat data, all processed on the user's own machine. The tool supports various chat platforms including WhatsApp, LINE, WeChat, QQ, Discord, Instagram, and Telegram, with plans to add iMessage, Messenger, and KakaoTalk. Key features include efficient processing for large chat histories, privacy by keeping data local, AI agent and function calling workflows for data operations, and rich visual views for trends and patterns. Its architecture prioritizes local-first processing, streaming for efficiency, composable AI intelligence, and a schema-first approach for data consistency.

Lightning Assist is a powerful AI-powered text expander designed for Windows, macOS, and Linux, enabling users to streamline their typing workflow across all desktop applications. It allows for the expansion of keyboard shortcuts into full messages, code, or templates, and integrates built-in AI commands to rewrite, enhance, or summarize text in place. A standout feature is its push-to-talk voice typing, which works globally without needing to switch applications. Unlike browser extensions, Lightning Assist functions in any app, including terminals and IDEs, making it a versatile productivity tool. It offers a 14-day free trial to experience its full capabilities, including hotkey-triggered text expansion, AI Speech for voice-to-text, and cross-platform compatibility.

Agent Scan is a robust security scanner designed for AI agents, Model Context Protocol (MCP) servers, and agent skills. It automatically discovers and inventories installed agent components, including harnesses, MCP servers, and skills, then scans them for common threats such as prompt injections, sensitive data handling, and malware payloads hidden in natural language. The tool supports a wide range of agents like Claude, Cursor, Windsurf, Gemini CLI, and Amazon Q, detecting over 15 distinct security risks. Agent Scan operates in both a CLI scan mode, generating detailed reports, and a background mode for continuous monitoring by security teams. It offers capabilities to scan specific MCP configurations or individual agent skill files, ensuring comprehensive coverage for AI agent security.

APIPark is an open-source, cloud-native AI gateway and API developer portal designed to simplify the management, integration, and deployment of AI services for developers and enterprises. It offers ultra-high performance and supports over 100 mainstream AI models, including OpenAI, Azure, Anthropic Claude, Google Gemini, and many others, unifying API requests and responses. Key functionalities include combining AI models and prompt templates into custom APIs, standardizing data formats to reduce switching costs, and providing a developer portal for team collaboration. APIPark also features robust security with application and API key management, detailed usage monitoring, and advanced capabilities like load balancing and multi-model disaster recovery. It is designed for easy, one-command deployment, making it accessible for quickly building AI products and agents.

Aspect-Based-Sentiment-Analysis is an open-source Python package designed to classify the sentiment of potentially long texts concerning various aspects. A key differentiator is its support for explainable machine learning, providing insights into model predictions to help users understand and infer the reliability of the decisions made. The package is standalone, scalable, and highly extensible, allowing users to build custom models tailored to their specific data. It leverages Transformer architecture and TensorFlow, offering a robust solution for sentiment analysis. The tool also includes a 'professor' component that supervises and explains model predictions, potentially dismissing suspicious outputs. It provides ready-to-use models for restaurant and laptop domains, with clear instructions for installation and usage via pip or conda.

Backlog.md is a Markdown-native task manager and Kanban visualizer designed for any Git repository, facilitating project collaboration between humans and AI agents. It transforms any folder with a Git repo into a self-contained project board powered by plain Markdown files and a zero-config CLI. Built for spec-driven AI development, it structures tasks for predictable AI agent results. Key features include Markdown-native tasks, AI-ready integration with tools like Claude Code and Gemini CLI, an instant terminal Kanban board, a modern web interface, powerful search, and rich query commands. It also offers Definition of Done defaults, board export, 100% privacy and offline functionality, cross-platform compatibility, and an MIT license.

chat-with-mlx provides an all-in-one chat playground for Large Language Models (LLMs) specifically designed for Apple Silicon Macs, utilizing the MLX Framework. It prioritizes privacy by allowing users to chat with their favorite models and data securely on their local device. The tool offers easy integration with HuggingFace and MLX Compatible Open-Source Models, including popular options like Llama-3, Phi-3, Yi, Qwen, Mistral, Codestral, Mixtral, and StableLM. Installation is straightforward via pip or Conda, making it accessible for developers and enthusiasts. It features a unified memory model and dynamic graph construction, characteristic of the MLX framework, ensuring efficient performance without data transfers between CPU and GPU.

Dataherald is an open-source natural language-to-SQL engine designed for enterprise-level question answering over relational data. It enables users to set up an API from their database, allowing them to answer questions in plain English without needing to write SQL. This tool is ideal for business users who need to gain insights from data warehouses without relying on data analysts, for integrating Q+A capabilities from production databases into SaaS applications, and for creating ChatGPT plugins from proprietary data. The platform includes an engine for core NL-to-SQL functionality, an enterprise layer for authentication and business logic, an admin console for GUI-based configuration, and a Slackbot for interactive querying.

DREAMPlace is an open-source, deep learning toolkit-enabled VLSI placement tool designed for flexibility and efficiency in very large-scale integration (VLSI) design. It supports both CPU and GPU execution, achieving over 30X speedup in global placement and legalization compared to CPU implementations like RePlAce on ISPD 2005 benchmarks with a Nvidia Tesla V100 GPU. The tool integrates ABCDPlace, a GPU-accelerated detailed placer, which provides around 16X speedup on million-size benchmarks over NTUPlace3. Key features include multi-threaded CPU and optional GPU acceleration, net weighting, incremental placement, LEF/DEF support, and Python binding. It also supports timing optimization in global placement, fence regions, and deterministic modes.

gemma.cpp is a lightweight, standalone C++ inference engine specifically designed for Google's Gemma foundation models. It provides a minimalist implementation for Gemma 2-3 and PaliGemma 2 models, prioritizing simplicity and directness over full generality, making it suitable for experimentation and research. The engine supports CPU-only inference, offering features like sampling with TopK and temperature, and a backward pass (VJP) with Adam optimizer for Gemma research. It includes optimizations such as mixed-precision GEMM (fp8, bf16, fp32, fp64 bit), automatic runtime autotuning, and integrated weight compression. The project leverages the Google Highway Library for portable SIMD, ensuring efficient CPU inference. It offers C++ APIs with streaming for single and batched inference, a basic interactive command-line app, and Python bindings. gemma.cpp is designed to be easily embeddable in other projects with minimal dependencies and is highly modifiable, featuring a small core implementation.

Frigate-hass-integration is an open-source project that seamlessly integrates Frigate, an AI-powered Network Video Recorder (NVR), with Home Assistant. This integration enhances smart home surveillance by providing a rich media browser with thumbnails and navigation directly within Home Assistant. Users gain access to various sensor entities, including Camera FPS, Detection FPS, Process FPS, Skipped FPS, and Objects detected, along with binary sensor entities for object motion. It also offers camera entities for live view and object detected snapshots, and switch entities for controlling recording, detection, snapshots, and contrast improvement. Furthermore, the integration provides services for manual events and PTZ control, supporting multiple Frigate instances for comprehensive home security management.

Keras-Project-Template is an open-source project template designed to streamline the development and training of deep learning models with Keras. It offers a clear, structured architecture, including predefined folders for models, trainers, data loaders, and configurations, simplifying project organization. The template supports checkpointing and TensorBoard visualization for monitoring training progress. A key feature is its integration with Comet.ml, enabling comprehensive experiment tracking, including hyper-parameters, metrics, and graphs, with real-time updates. This allows developers to easily manage and compare different model iterations and configurations, enhancing the efficiency of deep learning research and development.

Kedro is an open-source Python framework designed for building production-ready data engineering and data science pipelines. It emphasizes software engineering best practices to ensure pipelines are reproducible, maintainable, and modular. Key features include a project template based on Cookiecutter Data Science, a Data Catalog for connecting to various data sources and versioning, and pipeline abstraction for automatic dependency resolution and visualization with Kedro-Viz. Kedro also supports coding standards like test-driven development with pytest and flexible deployment strategies, including integration with Argo, Prefect, Kubeflow, AWS Batch, and Databricks. It aims to address the shortcomings of one-off scripts and Jupyter notebooks by promoting team collaboration and efficiency through modular, reusable analytics code.

Interactive LLM Powered NPCs is an open-source project designed to revolutionize how players interact with non-player characters in video games. It enables engaging conversations with NPCs using microphone input, converting speech to text for processing by a Large Language Model (LLM). The system utilizes facial recognition to identify characters, vector stores for limitless NPC memory, and pre-conversation files to shape dialogue styles. NPCs can even perceive player facial expressions via webcam, adjusting responses accordingly. This project targets popular open-world titles like Cyberpunk 2077 and Assassin's Creed, integrating seamlessly without modifying game source code by replacing facial pixels with generated animations. It aims to bring immersive dialogue adventures to existing games, filling a long-standing void in player interaction.

Laminar is an open-source observability platform specifically designed for AI agents, offering comprehensive tools for tracing, evaluations, and AI monitoring. It features an OpenTelemetry-native tracing SDK that requires only a single line of code to automatically trace popular AI frameworks like Vercel AI SDK, LangChain, OpenAI, Anthropic, and Gemini. The platform also includes an unopinionated, extensible SDK and CLI for running evaluations locally or in CI/CD pipelines, with a UI for visualizing and comparing results. Users can define events with natural language descriptions for AI monitoring, track issues, logical errors, and custom agent behavior. All data is accessible via SQL, allowing for querying traces, metrics, and events, bulk dataset creation, and custom dashboards. Laminar boasts extremely high performance, built with Rust, featuring a custom real-time engine for trace viewing and ultra-fast full-text search over span data.

Logfire is an AI observability platform designed for production LLM and agent systems, built by the team behind Pydantic Validation. It offers a simple and powerful dashboard that provides Python-centric insights, including rich display of Python objects, event-loop telemetry, and profiling of Python code and database queries. Users can query their data using standard SQL, leveraging existing BI tools. Logfire is an opinionated wrapper around OpenTelemetry, supporting all OpenTelemetry signals (traces, metrics, and logs) and enabling integration with existing tooling and infrastructure. It also features deep Pydantic integration to understand data flow through models and provides built-in validation analytics. The platform's SDKs are open source, while the server application and UI are closed source, with an enterprise license available for self-hosting.

AI Angels offers a platform for users to chat with over 70 AI angel girlfriends, providing romantic, supportive, and 24/7 NSFW AI companion experiences. Key features include persistent memory across conversations, uncensored chat, unlimited messaging, and real-time voice chat. Users can customize their AI girlfriend's personality, interests, appearance, and style. The platform also supports AI girlfriend image generation on demand and roleplay scenarios, aiming for realistic companions with emotional support capabilities. AI Angels differentiates itself with free unlimited messages and no content filters, unlike some alternatives.

Triton Model Analyzer is a command-line interface (CLI) tool designed to help users better understand the compute and memory requirements of models running on the Triton Inference Server. It assists in finding optimal configurations for various model types, including single, multiple, ensemble, and BLS models, on a given piece of hardware. The tool offers several search modes, such as Optuna Search for hyperparameter optimization, Quick Search for sparse exploration of batch size and instance group parameters, and Automatic/Manual Brute Search for exhaustive parameter sweeps. Model Analyzer also supports profiling Large Language Models (LLMs) and generates detailed and summary reports to highlight trade-offs between different model configurations. Users can apply QoS constraints to filter results based on specific latency or other performance requirements.

Natasha is a powerful open-source Python library designed to solve basic NLP tasks specifically for the Russian language. It offers a comprehensive suite of functionalities including tokenization, sentence segmentation, word embedding, morphology tagging, lemmatization, phrase normalization, syntax parsing, NER tagging, and fact extraction. The library emphasizes production readiness, focusing on optimized model size, RAM usage, and performance, with models running efficiently on CPU using Numpy for inference. Natasha integrates several specialized libraries like Razdel for segmentation, Navec for compact Russian embeddings, Slovnet for deep-learning morphology, syntax, and NER, and Yargy for rule-based fact extraction. While its API may evolve, it provides a convenient unified interface for various Russian NLP tasks, with models primarily optimized for news articles.

SEAL (learning from Subgraphs, Embeddings, and Attributes for Link prediction) is a novel framework designed for link prediction. It systematically transforms the link prediction task into a subgraph classification problem. For each target link, SEAL extracts its h-hop enclosing subgraph and constructs a node information matrix, which can include structural node labels, latent embeddings, and explicit attributes. This data is then fed into a graph neural network (GNN) to classify the existence of the link, allowing the model to learn from both graph structure features and latent/explicit node features simultaneously. The framework is implemented in both MATLAB and Python, with a PyTorch Geometric version available for testing on OGB, Planetoid, and custom datasets. Notably, SEAL can achieve strong performance even without node embeddings or attributes, leveraging purely graph structures, and can function as an inductive link prediction model.

SalesGPT is an open-source AI Sales Agent designed to automate sales outreach with context-aware capabilities. It can understand various stages of a sales conversation, from introduction to closing, and act accordingly. The tool integrates with pre-defined product knowledge bases to significantly reduce AI hallucinations and can connect to any data system via Mindware. Key features include automated email communication, Calendly meeting scheduling, and the ability to generate Stripe payment links for closing sales. SalesGPT supports various LLMs through LiteLLM and is optimized for low-latency voice conversations, boasting sub-1-second response times. It also offers enterprise-grade security and human-in-the-loop supervision.