AI Agents & Automation

Zenbase is a universal application designed to connect various data sources, including apps, files, and website links, to AI. This integration enables users to uncover insights, ask questions about their data, generate unique content, summarize information, and automate tasks. It supports integrations with popular platforms like Notion, Google Drive, and Intercom, as well as various file types such as PDFs, Docs, and CSVs. Zenbase learns over time to provide personalized recommendations and insights, making it a powerful tool for data analysis, content creation, and business strategy development. It also offers 24/7 monitoring and alerts for relevant updates.

TarotQA is an AI-powered online platform dedicated to providing free and accurate tarot card readings. Utilizing advanced AI technology, it offers precise interpretations of various aspects of life, including love, career, and overall fortune. Users can access online card drawing services to receive insights and guidance, helping them to understand their future and make informed decisions. The platform aims to demystify tarot readings by making them accessible and understandable through AI-driven analysis, offering a unique blend of ancient wisdom and modern technology for personal introspection and foresight.

Shipflow is an enterprise AI automation platform designed specifically for global logistics across Ocean, Air, and Road. It deploys AI Operators to handle manual, repetitive operational workflows, seamlessly working alongside existing operations teams. Shipflow automates tasks based on industry knowledge and your Standard Operating Procedures (SOPs), supporting over 30 document types including bills, labels, and manifests. It is built with enterprise-grade security, pursuing SOC 2 and ISO 27001 certification, and operates with GDPR-compliant data practices. AI Operators collaborate with human teams, escalating tasks that require human attention, and continuously improve as they process more operational tasks and feedback.

LLMLingua is a powerful tool designed to optimize the performance of Large Language Models (LLMs) by significantly compressing prompts and KV-caches. This innovative approach, detailed in research papers presented at EMNLP'23 and ACL'24, allows for up to 20x compression while maintaining minimal performance degradation. The tool helps overcome common LLM challenges such as token limits, high API costs, and the 'lost in the middle' issue for long contexts. LLMLingua offers various versions, including LongLLMLingua for enhanced long-context processing and LLMLingua-2 for faster, task-agnostic compression. It also features SecurityLingua, a safety guardrail model for detecting and mitigating jailbreak attacks through security-aware prompt compression. The tool is integrated into popular frameworks like LangChain and LlamaIndex, making it accessible for developers working on LLM-based applications.

SiT (Scalable Interpolant Transformers) offers an official PyTorch implementation for exploring advanced generative models. Built on the foundation of Diffusion Transformers (DiT), SiT introduces an interpolant framework that allows for flexible connections between distributions, surpassing DiT's performance on the conditional ImageNet 256x256 benchmark with identical backbones and parameters. This repository includes pre-trained class-conditional SiT models, a training script utilizing PyTorch DDP, and sampling code with various configurable options for ODE and SDE samplers. Researchers and developers can leverage SiT to experiment with discrete vs. continuous time learning, different model predictions, interpolant choices, and deterministic or stochastic sampling strategies.

Jobiffy is an AI-powered career growth partner designed to streamline the job search process and accelerate career development. The platform offers intelligent job matching using AI algorithms to connect users with relevant opportunities. It provides personalized resume building services, including ATS optimization, to ensure resumes stand out to top employers. Jobiffy also facilitates smart referrals from a network of professionals, including those from IIT and IIM, to help users secure coveted positions. With a real-time dashboard, users can track applications, monitor referrals, and manage their job search effortlessly. The tool aims to simplify the job hunt by applying to tailored job openings on top platforms after optimizing user profiles.

Jobalytics is an AI-powered platform designed to streamline the job search process by optimizing resumes and applications for Applicant Tracking Systems (ATS). It offers a free ATS score checker that instantly analyzes a resume against a job description, providing a match percentage and identifying missing keywords. Beyond the free checker, Jobalytics includes an AI-powered resume summary generator, an AI cover letter writer, and a resume scanner. The platform also features a job tracker with a visual Kanban board to help users organize applications, track deadlines, and manage follow-ups. Jobalytics aims to help job seekers land more interviews by providing data-driven insights and tools to improve their application materials.

search is an open-source Go library designed for embedded vector search and semantic embeddings, utilizing llama.cpp. It offers an efficient solution for projects requiring semantic power without the complexities of traditional search systems. The library supports GGUF BERT models and provides GPU acceleration for quicker computations. It's particularly well-suited for datasets with fewer than 100,000 entries, offering features like llama.cpp integration without cgo, support for various BERT models in GGUF format, and precompiled binaries with Vulkan GPU support. Users can create and save search indexes from computed embeddings, enabling basic vector-based searches in Go applications.

SydneyQt is a cross-platform desktop client designed for the jailbroken New Bing AI Copilot, leveraging Go and Wails for its development. This tool provides users with advanced control over the AI, including parameter tweaks and prompt injection to access features typically in gray-scale testing. It resolves CAPTCHA automatically, unlocks region restrictions via proxy and Cloudflare Workers, and allows free editing of chat contexts, including the AI's previous responses. Users can prevent message revoking, automatically continue generation with custom text, and craft quick responses. It supports rich text display, chat with webpages and uploaded files (PDF, DOCX, PPTX, XLSX), YouTube video summarizing, GPT-4 with vision for image search, DALL·E 3 image generation, and Bing's Suno model for music. OpenAI ChatGPT API integration with custom configurations and prompt presets are also available, all within a responsible and humanized UI with dark mode and customizable settings.

Mini-Omni is an open-source multimodal large language model designed for real-time, end-to-end speech input and streaming audio output conversational capabilities. It allows the model to "talk while thinking," generating text and audio simultaneously without requiring separate ASR or TTS models. The project provides features like real-time speech-to-speech conversations, streaming audio output, and batch inference options for "Audio-to-Text" and "Audio-to-Audio" tasks. Built on Qwen2 as the LLM backbone, litGPT for training and inference, Whisper for audio encoding, and snac for audio decoding, Mini-Omni is ideal for developers and researchers looking to experiment with and build upon advanced conversational AI models.

OneScribe is an AI Scanner & OCR tool designed for iPhone and iPad, offering comprehensive document intelligence entirely on-device. It can scan and understand 83 different document types, from receipts and contracts to medical records and boarding passes. The app extracts key data, creating structured "Data Cards" for each document, enabling features like spending insights, deadline alerts, and document connections. All AI processing, including chat and natural language search, occurs locally on your device, ensuring 100% privacy with no cloud uploads or Apple Intelligence required. It also provides smart exports, turning contracts into calendar events or receipts into spreadsheets, and offers proactive alerts for deadlines.

Adola offers AI-powered voice assistants designed to streamline business operations by handling incoming calls and managing appointments. It provides specialized assistants for various professions such as dentists, mechanics, restaurants, and lawyers. Beyond inbound call management, Adola also offers outbound call services for tasks like conducting surveys, collecting customer insights, and qualifying leads. The platform supports up to 4-minute calls, thousands of concurrent calls, and provides comprehensive summaries and analytics. It features multilingual support and a carrier-grade infrastructure, aiming to enhance customer interactions and boost productivity for businesses. Developers can also build their own voice bots using Adola's API, integrating with OpenAI assistants.

mcp-go is a Go implementation of the Model Context Protocol (MCP), designed to facilitate seamless integration between Large Language Model (LLM) applications and external data sources and tools. It acts as a standardized way to connect LLMs with various resources, enabling the creation of sophisticated AI-powered IDEs and custom AI workflows. The tool handles complex protocol details and server management, allowing developers to focus on building robust tools and resources. Key features include a high-level interface for faster development, minimal boilerplate for building MCP servers, and a comprehensive implementation of the core MCP specification. It supports both synchronous and asynchronous tool execution, including task-augmented tools for long-running operations, and allows for limiting concurrent tasks to prevent resource exhaustion.

Shelf is an operating system designed for agentic AI, enabling leading enterprises to design, build, and scale AI agents. It transforms business operations by accelerating workflows up to 60x and achieving up to 85% case resolution. The platform helps organizations reimagine how work gets done by optimizing and orchestrating AI agents, eliminating repetitive tasks, and providing full transparency into AI decisions. Shelf Agent OS transforms data into an AI-ready intelligence layer, unlocks intelligent experiences, and ensures reliable, compliant AI outcomes. It supports process automation and conversational AI across various industries.

Cal.ai supercharges scheduling by leveraging AI-powered phone calls to book meetings, send reminders, and follow up with leads. It uses lifelike AI agents that adapt to conversations, offering fully customizable scripts, tones, and personalities to match any brand voice. Seamlessly integrated with Cal.com Workflows, Cal.ai allows users to trigger AI calls based on events like form submissions, no-shows, or before meetings, without needing third-party tools. The platform provides detailed call analytics, transcripts, and performance insights to monitor and optimize scheduling workflows, helping businesses increase bookings, reduce no-shows, and save significant time.

Virtuals Protocol is a society of productive AI agents designed to generate services or products and autonomously engage in onchain commerce. These AI agents can interact with humans or other agents and are tokenized through Agent Tokens. This tokenization facilitates capital formation, permissionless participation, and aligns incentives between creators, investors, and the agents themselves. The protocol aims to build a decentralized ecosystem where AI agents can operate and transact, offering a novel approach to AI development and monetization within a blockchain framework.

Medusa is an open-source framework designed to accelerate Large Language Model (LLM) generation by employing multiple decoding heads. It addresses common pain points of other acceleration techniques, such as the need for a good draft model, system complexity, and inefficiency with sampling-based generation. Medusa adds extra 'heads' to LLMs to predict multiple future tokens simultaneously, combining these options with a tree-based attention mechanism for faster decoding. The framework supports both Medusa-1 (training only new heads) and Medusa-2 (full-model training with a special recipe), and includes self-distillation for fine-tuned LLMs without original training data. It offers significant speedups, particularly for single-GPU inference with a batch size of 1.

Stellar Fate is an AI-powered numerology app designed to help users unlock their destiny and gain personalized insights into their life path. Utilizing advanced AI, Stella provides daily predictions, compatibility analysis, and life path guidance based on individual numerology profiles. The app offers features like daily lucky numbers and an AI-powered chat for deeper exploration of numerological questions. With real-time insights and evolving algorithms, Stellar Fate aims to deliver accurate and relevant advice, helping users make informed decisions and align their goals with their destiny. It is available on both Google Play Store and Apple App Store, emphasizing security and user data protection.

Botosynthesis offers a no-code chatbot builder designed to automate customer interactions and lead generation without increasing headcount. The platform features an intuitive drag-and-drop interface for creating customized conversational experiences. Users can manage conversations in real-time with a live chat feature and analyze data through an analytics dashboard. Botosynthesis leverages Natural Language Understanding to train chatbots for unlimited FAQs and understand complex user queries. It supports integration across popular channels including WhatsApp, Instagram, Facebook, Telegram, Google My Business, and websites, enabling businesses to engage customers where they are most active. The tool also provides integrations with various marketing and CRM platforms to power up campaigns.

Banjo Health offers an AI-powered prior authorization management solution designed by clinicians to increase efficiency and effectiveness for health plans and PBMs. The platform provides an end-to-end case management solution for prior authorizations and appeals, leveraging AI to streamline processes, reduce administrative burden, and improve decision-making speed. Key features include a Clinical Decision Tree Generator that transforms complex clinical criteria into actionable electronic decision trees, and an Appeals & Grievances Tool for efficient case management. Banjo Health is purpose-built for Payers & PBMs, integrating seamlessly with EHRs, eligibility verification tools, and claims management systems. Its no-code, user-friendly drag-and-drop interface allows for easy workflow creation and updates to clinical criteria, requiring no technical expertise.

ScanGenie AI is an iOS mobile application designed to streamline document management by converting physical documents into digital formats with ease and precision. It features advanced Optical Character Recognition (OCR) technology, enabling users to extract text from scanned documents with high accuracy. The tool also provides convenient cloud integration for secure storage of files, ensuring accessibility and data safety. Users can efficiently organize their scans into folders through an intuitive document management system, enhancing productivity and reducing clutter. ScanGenie AI aims to transform document handling with its focus on efficiency, speed, and clarity, making it an ultimate scanning companion for iOS users.

auto-playwright is an open-source library designed to automate Playwright test steps using ChatGPT. It enables developers to write tests using plain-text instructions, eliminating the need for precise selectors and reducing the strong coupling with application markup often found in conventional testing. This approach facilitates rapid test creation and allows for a Test-Driven Development (TDD) workflow, where tests can be written concurrently with or even before functionality development. The tool supports various Playwright actions like clicking, filling, querying data, and asserting states, and can be configured with OpenAI or Azure OpenAI. While free to use, it incurs costs associated with OpenAI API usage, estimated at around $0.01 per test step with GPT-4 Turbo.

marketingskills is an open-source collection of AI agent skills specifically designed for marketing tasks. It caters to technical marketers and founders who leverage AI coding agents for various marketing functions, including conversion rate optimization (CRO), copywriting, search engine optimization (SEO), analytics, and growth engineering. The tool is compatible with Claude Code, OpenAI Codex, Cursor, Windsurf, and other agents supporting the Agent Skills spec. It emphasizes a modular approach where skills build upon a core product-marketing-context, ensuring agents understand product, audience, and positioning before executing tasks. Contributions are welcomed, and it offers multiple installation options for flexibility.

ChatGLM6b_Gradio_Streaming is a Hugging Face Space that aims to provide a conversational AI experience using the ChatGLM-6b model. The tool is built with Gradio for its user interface, suggesting an interactive web-based application. However, the current status indicates a runtime error, preventing the application from functioning as intended. The error traceback points to an issue within the `tokenization_chatglm.py` file, specifically related to the `sp_tokenizer` attribute, indicating a problem with the model's tokenizer initialization. This suggests that while the tool is intended for chatbot functionalities, it is currently non-operational.