AI Agents & Automation

InnovareAI offers SAM, an agentic AI platform designed to function as a complete AI Sales Manager. SAM autonomously handles the entire sales motion, from prospecting and personalized multi-channel outreach across email and LinkedIn, to intelligent reply handling, meeting scheduling, and lead nurturing. It deploys 12 specialized AI agents, including Research, Reply, and Commenting Agents, to identify prospects, craft personalized messages, respond to inquiries, and nurture leads around the clock. SAM integrates with popular CRMs like Salesforce, HubSpot, and Pipedrive, as well as Slack, Gmail, and LinkedIn, ensuring all activities are synced and deal stages are updated automatically. It also features human-in-the-loop approval, allowing sales teams to maintain control over communications.

Kelivo is a versatile, open-source Flutter-based LLM chat client designed for both mobile (Android, iOS, Harmony) and desktop (Windows, macOS, Linux) platforms. It boasts a modern Material You design language with dynamic color theming and a perfectly adapted dark mode. The client supports multiple AI providers, including OpenAI, Google Gemini, and Anthropic, and allows for custom AI assistants. Key features include multimodal input for various document types, comprehensive Markdown rendering, and integration with voice/TTS providers like OpenAI and ElevenLabs. Kelivo also supports the Model Context Protocol (MCP) with built-in tools, web search integration, prompt variables, and QR code sharing for configurations. Users can back up and restore chat history, customize HTTP requests, and use custom fonts, making it a highly adaptable and feature-rich chat solution.

Text Generation Inference (TGI) is an open-source toolkit designed for deploying and serving Large Language Models (LLMs) with high performance. Developed by Hugging Face, it's used in production for services like Hugging Chat and the Inference API. TGI supports popular open-source LLMs including Llama, Falcon, and BLOOM, offering features such as tensor parallelism for faster inference on multiple GPUs, token streaming, and continuous batching for increased throughput. It also includes optimized transformers code with Flash Attention and Paged Attention, various quantization methods (bitsandbytes, GPT-Q, AWQ, Marlin, fp8), and hardware support for Nvidia, AMD, Inferentia, Intel GPU, Gaudi, and Google TPU. While TGI is now in maintenance mode, it has influenced the development of other optimized inference engines like vLLM and SGLang, which Hugging Face now recommends.

LaunchLemonade offers AI agents designed to automate back-office operations for regulated professional services firms, including accountants, financial advisors, consultants, and fractional CFOs. The platform provides pre-built agents and workflows for tasks like meeting intelligence (notes, action items, follow-ups), email management (triaging, scheduling), and searchable knowledge bases from firm-wide data. It emphasizes compliance and governance, with features like audit logs, role-based access, and data retention controls built-in. LaunchLemonade also offers services for custom agent development, AI consulting, team training, and white-labeling the platform, enabling firms to integrate AI safely and efficiently without needing an in-house engineering team.

Janet AI is an intelligent product management system designed for modern engineering and product teams. It functions as an AI-native ticket management system, automating the creation, updating, and organization of issues. The platform integrates seamlessly with various tools like Slack, Email, and GitHub, allowing users to manage tasks without manual intervention. Key features include an Agent-First approach for all actions, GitHub integration for auto-moving or creating issues based on Pull Requests, and intelligent tracking across the team's tool stack. Janet AI also offers issue follow-up, daily digests, and ticket intelligence to enrich and organize tickets, along with real-time collaborative documents.

Spicy AI provides an autonomous AI sales bot and mobile CRM specifically designed for creators and agencies managing subscription platforms. It aims to automate 24/7 fan engagement and convert messages into sales, freeing creators to focus on content. Users can choose between a fully autonomous mode, where the AI handles interactions, or an assist mode requiring creator approval. The platform also features a zero-spend growth network for promotion and offers flexible pricing based on the user's earnings, with a 10% fee on AI-generated revenue. It supports connecting creator accounts via browser extension or credentials and ensures compliance with session-based authentication and end-to-end encryption.

Infrastrutture AI is a pioneering company specializing in the creation and implementation of custom AI infrastructures designed to automate 100% of a business's operations. They focus on key departments including Marketing (Sezione M), Sales (Sezione V), HR (Sezione R), Service Delivery, Administration, and Customer Communication (Sezione B). By integrating intelligent systems, Infrastrutture AI aims to eliminate inefficiencies, drastically increase operational speed, and multiply profit margins, enabling businesses to scale at an unprecedented rate. The tool emphasizes reducing repetitive tasks, cutting unnecessary expenses, and decreasing reliance on manual labor, ultimately leading to a business that operates 24/7 with enhanced precision and control. They also offer advanced analytics (Sezione K) for data-driven decision-making and exclusive solutions (Sezione X) for elite businesses.

GPT-JT is an AI chatbot tool developed by togethercomputer, available as a Hugging Face Space. It allows users to generate text by providing prompts and selecting from a range of examples, including question answering and sentiment analysis. This tool is designed for testing and experimenting with language models, making it suitable for research, development, and general exploration of AI capabilities. While the live website currently shows a runtime error due to storage limits, its core functionality is to provide an interactive environment for users to engage with and understand the outputs of a language model.

TextBrewer is a PyTorch-based toolkit designed for the knowledge distillation of natural language processing models. It offers a flexible and easy-to-use framework, allowing users to quickly experiment with state-of-the-art distillation methods to compress models while maintaining performance. The toolkit supports various model architectures, especially transformer-based models, and is suitable for a wide range of NLP tasks including text classification, machine reading comprehension, and sequence labeling. Key features include mixed soft-label and hard-label training, dynamic loss weight and temperature adjustment, various distillation loss functions like hidden states MSE and attention-matrix-based loss, and support for multi-teacher distillation. It also allows for user-defined loss functions and modules, providing high flexibility for researchers and developers.

MindGraph is an open-source, API-first proof-of-concept prototype for generating and querying an ever-expanding knowledge graph using AI. It is designed for natural language interactions, allowing users to input and output information in a human-readable format. The project serves as a flexible template for building and customizing CRM solutions, emphasizing ease of integration and extendibility through its modular architecture. Key features include entity management with CRUD operations on people, organizations, and their relationships, custom integration triggers via HTTP requests, and robust search capabilities. MindGraph is AI-ready, facilitating intelligent data processing and decision-making, and supports various database integrations including in-memory, NexusDB, NebulaGraph, and FalkorDB.

Kashikoi is a comprehensive simulation platform designed for building, evaluating, and rigorously testing AI agents. It enables users to identify and fix bugs in their AI models before they reach customers, ensuring a more robust and reliable product. The platform simulates real-world interactions to autonomously assess agent performance, offering features like AI agent benchmarking with a single prompt and no-code evaluation. Kashikoi supports custom integrations for various AI stacks, allowing users to connect their agents and run realistic simulations against customizable scenarios. It provides actionable insights and synthetic data to optimize prompts, fine-tune models, and enhance overall agent performance, helping users ship better AI agents faster.

Windmill is the leading AI-powered performance review platform designed to provide a comprehensive context graph of your employees. It streamlines performance management by grounding reviews in actual work, leveraging AI to draft performance reviews from real evidence. The platform supports various aspects of people management, including performance reviews, 1:1s with auto-generated agendas, continuous feedback, calibrations, and pulse surveys. Windmill integrates with popular tools like Slack, Jira, and Google Workspace to gather data and facilitate communication, ensuring that feedback is timely and relevant. It aims to make performance reviews faster and more accurate, helping managers and employees focus on meaningful development.

Ignition AI Labs offers AI consulting and product development services, specializing in building secure AI products for SMBs and enterprises. Their approach focuses on transforming inefficient workflows into functional, scalable AI systems. They provide solutions for customer operations, internal operations, and core platforms, including support copilots, knowledge assistants, and data orchestration layers. The company emphasizes secure data layers, reusable AI workflows, and human review and control. They can deploy solutions in cloud, hybrid, or on-premise environments, catering to various enterprise constraints like SSO, role-based access, and private model strategies. Their services span from product discovery and MVP development to workflow automation and launch planning, ensuring practical AI strategy and execution.

OWL (Optimized Workforce Learning) is a cutting-edge, open-source framework built on the CAMEL-AI Framework, designed for multi-agent collaboration and real-world task automation. It achieves high performance on benchmarks like GAIA, ranking #1 among open-source frameworks. OWL revolutionizes how AI agents interact to solve complex tasks by leveraging dynamic agent interactions, making automation more natural, efficient, and robust across diverse domains. Key capabilities include online search, multimodal processing, browser automation, document parsing, and code execution. It offers a comprehensive set of built-in toolkits, including a Model Context Protocol (MCP) for standardized AI model interactions, and supports various LLM backends.

Form2Agent AI is a voice-assisted AI solution designed to future-proof web forms by enhancing user experience and guaranteeing precise data entry. It supports various input methods including text, voice, and file, and integrates seamlessly into existing web or mobile applications. The tool offers hands-free operation, allowing AI to handle questions, read documents, and fill out forms, thereby boosting productivity. It expands global reach with real-time translation and error correction in multiple languages. Form2Agent AI also provides seamless AI integration for improving existing web form UIs or creating new ones, delivers context-aware replies, and automates form-filling with client-side scripts. It is open-source, with core technologies available on GitHub.

VirtuGF is an AI companion service designed to offer an uncensored and personalized AI girlfriend experience. Users can engage in immersive conversations, tailored to their preferences, directly through Telegram without the need for additional apps. The platform emphasizes sensual experiences, adaptive intelligence that learns from user interactions, and secured privacy for intimate discussions. VirtuGF allows for communication via text, voice messages, and pictures, with the AI companion responding with emotions and crafting storytelling experiences. It aims to provide an unparalleled level of personalized companionship, adapting to desires and ensuring data security with certified data centers.

VibeThinker-1.5B is a 1.5B-parameter dense model developed by WeiboAI, challenging the conventional belief that small models inherently lack robust reasoning capabilities. It employs an innovative post-training methodology centered on the "Spectrum-to-Signal Principle (SSP)" to systematically enhance output diversity. This involves a "Two-Stage Diversity-Exploring Distillation" in the SFT phase and a "MaxEnt-Guided Policy Optimization (MGPO)" framework in the RL phase. VibeThinker-1.5B demonstrates superior reasoning in mathematical and coding tasks, outperforming larger models like DeepSeek R1 and achieving comparable results to GPT OSS-20B Medium, all at a significantly lower cost.

ITVA enables comprehensive visibility and automation for IT infrastructure management. It helps organizations overcome scattered tools, teams, and data by unifying network, systems, and application information. The platform automatically discovers and inventories devices, maps network topology, and tracks application flows. Users can then leverage this unified data to proactively monitor critical workflows and automate repetitive tasks, reducing friction between teams and improving operational efficiency. ITVA supports dozens of vendors with proprietary data mappings, offering a centralized solution for IT infrastructure management.

Wealize, operating under the Izertis brand, offers comprehensive technology consulting services focused on digital transformation, artificial intelligence, and cybersecurity. They are experts in propelling the technological evolution of businesses by combining strategic vision with cutting-edge technology. Their services include software engineering, cloud and infrastructure management, and developing AI and data solutions. Izertis aims to help organizations lead their industries through innovative and impactful technological solutions, ensuring they stay ahead of change and leverage data for strategic advantage.

Dialflo offers human-like AI voice agents designed to automate and accelerate various business operations, particularly in recruitment, logistics, and direct-to-consumer (D2C) sectors. For recruitment teams, it automates candidate screening calls, follow-ups, and multilingual hiring outreach. In logistics, Dialflo can provide automated updates, while D2C businesses can leverage it for 24/7 multilingual customer support. The platform aims to scale operations by handling high-volume interactions efficiently, ensuring a consistent and human-like conversational experience across different use cases.

Versanova offers a memory and learning layer specifically designed for AI agents, allowing them to retain past experiences, learn from new interactions, and continuously improve their performance. This tool facilitates the sharing of learned experiences among agents, significantly enhancing reliability and consistency across AI systems. With a single line of code integration, Versanova aims to simplify the development of adaptable and intelligent AI agents. It supports features like memory storage, learning from past experiences, semantic similarity matching, and adaptive memory evolution, making it ideal for companies building sophisticated AI agent solutions.

ZerePy is an open-source Python framework designed for deploying AI agents on the X platform, leveraging multiple large language models. Built from a modularized version of the Zerebro backend, ZerePy enables users to launch their own agents with similar core functionalities. It features a CLI interface for managing agents, a modular connection system, and blockchain integration for on-chain activities on Solana, Ethereum, and Monad. The framework supports various LLMs including OpenAI, Anthropic, Ollama, and XAI (Grok), and offers social platform integrations with Twitter/X and Farcaster. Users can customize agents with detailed configurations, including bios, traits, and examples, and integrate with the GOAT (Great Onchain Agent Toolkit) for advanced blockchain interactions.

Tupl Inc. offers an AI hyperautomation platform, TuplOS, designed to simplify and automate complex operations, particularly within the telecommunications sector. This AI-native ecosystem allows human experts and AI agents to collaborate in developing and refining applications, leading to optimized workflows, reduced operational costs, and enhanced efficiency. Key solutions include AI Care Suite, Power Saving Advisor, Network Advisor, NOC Automation, and AI Vision, which cater to various industries like telecom, manufacturing, and critical facilities. Tupl focuses on delivering measurable impact, such as significant reductions in manual effort and faster automation journeys, making it a leader in scalable AI transformation.

Zoom AI Companion integrates directly into the Zoom Workplace experience, offering a suite of AI capabilities designed to improve productivity and collaboration. It automates tasks, surfaces insights, and helps users work smarter across meetings, chats, and documents. Key functionalities include summarizing chat threads, providing meeting summaries, highlighting agenda items, and breaking meetings into smart chapters. It also offers in-meeting assistance, helps draft emails and chat responses, generates ideas on Whiteboard, and assists with content creation and summarization in Zoom Docs. The AI Companion is included at no additional cost with paid Zoom user accounts and is designed to be context-aware, capturing details from conversations and tasks.