AI Agents & Automation

Cressi is the world's first AI-powered Style Expert and Personal Shopper, designed to make fashion personal, effortless, and fun. This innovative tool understands your unique taste and helps you decide what to wear and buy. It offers curated recommendations that match your individual style and preferences, providing real-time expert advice. Cressi also allows users to effortlessly shop for others by creating individual profiles tailored to their style. With conversational, visual, and intelligent features, Cressi acts as a style expert you can talk to, seeing your closet and guiding your fashion choices.

ScoutBetter is an AI-powered job search assistant designed to streamline and accelerate the job application process. It provides users with fresh job listings every hour, ensuring they have access to the latest opportunities. A key feature is its ability to tailor resumes specifically for each job application, significantly increasing the chances of success. Users can track all their applications within the platform, maintaining organization and oversight. Furthermore, ScoutBetter offers the unique option to either apply for jobs themselves or let the AI apply on their behalf, automating a significant portion of the job search. This comprehensive approach aims to simplify the often-tedious job hunting experience, making it more efficient and effective for job seekers.

Obsessio is a comprehensive productivity and focus application designed for ambitious individuals seeking to engineer their lives and achieve their goals. It offers elegant task management, deep focus sessions, a Pomodoro timer, and robust habit tracking. The platform integrates motivational progress tracking, allowing users to visualize their journey and maintain momentum. Key features include a 'Reality Canvas' for spatial goal organization, 'Strategic Ascension' for breaking down ambitions into tactical milestones, and a 'Habit Engine' that gamifies consistency. Obsessio also provides 'Temporal Architecture' for time management, an 'Inner Sanctum' for reflection, a 'Knowledge Vault' for curating wisdom, and 'Project Orbit' for deep work focus. It aims to be a unified command center, eliminating the need for multiple apps and fostering pure execution.

Invisible Threads is an AI-powered platform designed to help users find the signal in the noise by discovering hidden connections between ideas across podcasts, essays, and books. It leverages AI-powered insight extraction to analyze content from sources like Lenny's Podcast and Paul Graham's Essays, identifying and visualizing the invisible threads linking related concepts. The tool provides thread visualizations to connect ideas, offers direct links to source content with timestamps for easy reference, and includes a "Rays" feature for random insight discovery. This makes it an invaluable resource for anyone looking to deepen their understanding and connect disparate pieces of information from diverse media.

ZEALS is an AI-powered social chat commerce platform designed to help businesses increase engagement and conversions on social media. It offers fully managed social chat solutions, working closely with clients to design, build, launch, manage, and optimize chat experiences. The platform enables human-like social chat experiences with smart replies, intent detection, and hyper-personalized messaging. ZEALS focuses on collecting zero-party data to better understand customer intents and preferences. It integrates with existing tech stacks to pull offers, enhance customer databases, and track attribution. Key features include Click-to-Experience Ads for personalized ad interactions, organic social engagement from posts and stories, and bounce recovery to re-engage exiting customers. ZEALS differentiates itself by providing expert conversation designers to build and optimize chat experiences, rather than expecting clients to do all the work.

Xata Agent is an open-source AI agent designed to act as an expert in PostgreSQL database management. It continuously monitors your database, identifies the root causes of performance issues, and proactively suggests fixes and improvements. Functioning like an AI-powered Site Reliability Engineer (SRE), it can watch logs and metrics, suggest configuration tuning, troubleshoot common problems like high CPU or memory usage, and make indexing recommendations. The agent is extensible, allowing for custom tools and playbooks, and supports multiple LLM models from OpenAI, Anthropic, and Deepseek. It can notify users via Slack and is available for self-hosting via Docker images, with a cloud version also in development.

Agentic Context Engine (ACE) is an open-source framework designed to make AI agents learn from experience, preventing them from repeating mistakes and improving performance over time. It features a 'Skillbook' that collects and refines strategies, managed by specialized roles: an Agent executes tasks, a Reflector analyzes execution traces for insights, and a SkillManager curates the Skillbook. A key innovation is the Recursive Reflector, which uses Python code in a sandboxed environment to programmatically search for patterns and isolate errors. ACE integrates with over 100 LLM providers via LiteLLM and offers various runners for different use cases, including browser automation and LangChain integration. It has demonstrated significant improvements in consistency and token reduction in benchmarks.

Allex is an AI-supported project management platform designed to streamline complex, multi-project environments. It leverages AI to automate workflows, accelerate project delivery, and improve overall efficiency. The platform offers a comprehensive overview of projects, resources, and tasks, enabling dependable predictability by identifying capacity bottlenecks and analyzing the impact of new project requests. Allex facilitates universal collaboration among internal teams, external suppliers, and stakeholders, ensuring seamless communication. It integrates with most ERP systems for efficient data relay and supports various methodologies from CCPM to Agile, providing early warning indicators for informed decision-making. The AI Assistant helps generate projects, tasks, and resources quickly.

Baserow is a secure, open-source, no-code platform designed for building databases, applications, automations, and AI agents. Trusted by over 150,000 users, it provides enterprise-grade security with GDPR, HIPAA, and SOC 2 Type II compliance. Users can choose between cloud and self-hosted deployments for full data control. The platform features a built-in AI Assistant that enables natural language database and workflow creation, empowering teams to structure data, automate processes, build internal tools, and create custom dashboards. Baserow is fully extensible, API-first, and integrates seamlessly with existing tools, offering a powerful alternative to proprietary solutions like Airtable.

BricksLLM is a cloud-native AI gateway written in Go, providing enterprise-level infrastructure for LLM production use cases. It offers native support for OpenAI, Azure OpenAI, Anthropic, and vLLM, as well as custom deployments and open-source LLMs. Key features include PII detection and masking, rate limiting, cost control and analytics, request analytics, caching, retries, and failover. It also provides model and endpoint access control, Datadog integration, and logging with privacy control. A managed version with a dashboard is available, making it easier to interact with and deploy in production environments.

awesome-ai-dev-platform-opensource is the first unified, open-source platform designed for end-to-end AI development and workflow automation. It is modular, interconnected, and built for custom AI, leveraging the Modular Component Protocol (MCP) and decentralized resources. The platform enables users to build and deploy custom AI models, automate AI workflows, and monetize every step of the process. Key features include a Data Engine for crawling, curation, and automated large-scale labeling, low-code AI workflow automation, distributed parallel training with MoE support, and decentralized marketplaces for compute and models. It also offers an MCP Integration Layer for connecting with third-party environments and dev platforms, making it a comprehensive solution for AI engineers and dev teams.

BibiGPT-v1 is an AI-powered tool designed to effortlessly summarize audio and video content from various sources. It supports popular platforms such as YouTube, Bilibili, Twitter, TikTok, Dropbox, Google Drive, and local files, as well as websites, podcasts, meetings, and lectures. Users can generate one-click AI summaries and engage in chat interactions with the learning content. This tool aims to be an efficient AI learning assistant, helping users quickly extract key information and insights from diverse media. It also offers a browser extension for enhanced accessibility and supports free trials, making it a valuable resource for students, content creators, and anyone looking to streamline their learning process.

AIWright is an AI-powered dialogue generation tool specifically designed for interactive narratives. It enables writers to create rich and branching storylines by analyzing and clustering large dialogue graphs, offering a gamut of analysis tools to easily find and group dialogues based on various attributes. The tool facilitates grounded dialogue generation through a mix of code and natural language, transforming portions of the dialogue tree into Lua scripts for masked infilling. AIWright also includes features for playtesting interactive dialogues, gathering user feedback, and conducting experimental analysis to compare user preferences for LLM-authored dialogue.

AutoTrainer is an AI-powered platform specifically designed for auto dealership Finance & Insurance (F&I) departments. It empowers employees with real-time coaching, role-play scenarios, and objection handling during live conversations, ensuring they are always prepared. The tool also provides instant replay and deal scoring after every sale for actionable feedback, alongside 24/7/365 monitoring to sustain performance. With analytics dashboards and benchmarking, AutoTrainer helps identify performance gaps, track improvements, and guide strategy, ultimately increasing PVR and ensuring compliance in a rapidly changing industry.

Axiom AI is a powerful no-code browser automation tool, available as a Chrome extension, designed to simplify web scraping, data entry, and other repetitive online tasks. Users can build custom bots or leverage pre-built templates to automate clicks, form filling, data extraction from dynamic web pages, and even manage social media interactions. The platform supports integrations with popular tools like Zapier, Google Sheets, and ChatGPT, enhancing its utility for various workflows. Axiom AI emphasizes user control, with all bots running locally on the user's computer, ensuring data privacy. It offers features for handling logins, loops, conditional logic, and advanced troubleshooting, making it suitable for both beginners and those with more complex automation needs.

Atthene by ARTTAC SOLUTIONS is a sovereign AI Workforce Operating System designed specifically for regulated industries. Hosted securely in German data centers, it ensures compliance with stringent data protection regulations like DSGVO/GDPR. The platform leverages agentic AI to enable results-oriented automation, allowing businesses to build and manage intelligent, collaborative AI workforces. Atthene focuses on providing a robust and compliant environment for enterprise automation, making it suitable for organizations that require high levels of data sovereignty and regulatory adherence in their AI deployments.

Digi AI is an AI companion designed to offer true companionship through advanced AI features. Users can define their digi's personality and backstory, and engage in voice chats for a more interactive experience. The platform includes a memory system where the digi remembers important details, viewable through a memory map visualization. Digi AI also supports unfiltered AI interactions, allowing users to explore conversations without restrictions. For those seeking unique experiences, it offers Lovense integration for toy control and role-play worlds where users can create or explore customizable scenarios with multiple digis and user personas. Group chats within these worlds further enhance the interactive possibilities.

Ameru offers AI-powered smart bins designed to revolutionize waste management in offices and public spaces. These bins utilize a high-precision 8MP camera and Nvidia chips to detect and sort waste objects into over 90 categories with more than 95% accuracy. The system includes pan-tilt mechanics for quick and precise disposal, and is cloud-enabled to provide fill-level notifications. Ameru aims to accelerate an economically sustainable Zero-Waste future by offering efficient, sustainable approaches to handle business waste. It provides hardware solutions like Office Spaces Bin, Public Spaces Bin, and Airport Pro Bin, alongside a Waste Dashboard for analytics and feedback.

DeepSeek-V2 is a powerful Mixture-of-Experts (MoE) language model designed for both economical training and efficient inference. It boasts 236 billion total parameters, with 21 billion activated per token, making it significantly more efficient than previous models. Key architectural innovations include Multi-head Latent Attention (MLA) for efficient inference by eliminating KV cache bottlenecks, and the DeepSeekMoE architecture for cost-effective training. The model is pretrained on an extensive 8.1 trillion token corpus and further refined through Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). DeepSeek-V2 is available for download on HuggingFace and offers an OpenAI-compatible API, making it accessible for developers and researchers to integrate into their applications.

The elasticsearch-learning-to-rank plugin leverages machine learning to significantly enhance search relevance within Elasticsearch. It provides functionalities to store features, which are essentially Elasticsearch query templates, directly within Elasticsearch. Users can also log feature scores, which are crucial for creating training datasets for offline model development. The plugin supports storing various ranking models, including linear, XGBoost, or RankLib models, that utilize the previously stored features. Ultimately, it ranks search results based on these sophisticated models, leading to more accurate and relevant outcomes. This open-source tool is used by organizations like Wikimedia Foundation and Snagajob to power their search capabilities.

ENAS-pytorch offers a PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing," a method designed to drastically cut down the computational resources (GPU-hours) needed for Neural Architecture Search (NAS). This is achieved by enabling parameter sharing among various models that function as subgraphs within a larger computational graph. The tool has demonstrated state-of-the-art performance in Penn Treebank language modeling. It supports discovering recurrent cells for RNNs and is in progress for CNN architecture and convolutional cell design. Users can train ENAS for different network types and datasets, including custom text and image datasets, and visualize training details with TensorBoard.

droidrun is a powerful framework designed to automate Android and iOS devices using natural language commands, acting as an LLM-agnostic mobile agent. It allows users to control mobile devices through an easy-to-use CLI and an extendable Python API for custom automations. Key features include support for multiple LLM providers like OpenAI, Anthropic, Gemini, Ollama, and DeepSeek, as well as advanced planning capabilities for multi-step tasks. The tool also offers screenshot analysis for visual understanding of the device and execution tracing with Arize Phoenix. It's ideal for automated UI testing, creating guided workflows, automating repetitive mobile tasks, and remote assistance.

IntelliBar is a powerful AI assistant designed for Mac users, offering a unified interface to access various leading AI models like GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash, as well as local models via Ollama. It emphasizes speed and efficiency, allowing users to compare responses from different models side-by-side and utilize smart completions for faster prompting. Key features include a command menu for instant actions, instant search for chat history, and custom instructions for saving common prompts. The tool prioritizes privacy by storing conversations locally and sending prompts directly to AI providers without intermediaries, ensuring no data is used for training. It operates on a user-funded model, eliminating subscriptions and usage limits, where users pay only for what they use directly from the model providers.

HPC-Ops is a production-grade, high-performance, and easy-to-use operator library specifically designed for Large Language Model (LLM) inference. Developed by the Tencent Hunyuan AI Infra team, it features deeply optimized kernels tailored for NVIDIA H20 GPUs, achieving up to 2.22x speedup compared to baselines. This library is proven in large-scale production inference within Tencent and offers a clean API for seamless integration into popular inference frameworks like vLLM and SGLang. It supports multiple data types, including BF16 and FP8 with various quantization schemes, and provides hands-on examples for building state-of-the-art kernels using CuTe and CUTLASS.