AI Agents & Automation

awesome-ml is a comprehensive, curated list of resources designed for professionals and enthusiasts in the fields of Large Language Models (LLM), analytics, and data science. This GitHub repository serves as a central hub for discovering open LLM models, development tools, and various AI-related assets. It covers a wide array of topics including native and web GUIs, backends, voice assistants, retrieval augmented generation, browser extensions, and AI agents. Additionally, the list delves into multimodal AI, code generation libraries, prompt templating, fine-tuning, model merging, and quantization. Researchers and developers will find valuable sections on datasets, research papers, product showcases, benchmarking, leaderboards, and optimization techniques, making it an indispensable resource for staying updated in the rapidly evolving AI landscape.

ThoughtTrace, now known as Document Intelligence by Thomson Reuters, is an AI-powered platform designed to revolutionize contract and document analysis. It provides immediate insights into legal documents by leveraging AI models trained and continuously improved by Practical Law attorney-editors. This tool accelerates document review and contextual search, allowing users to search across thousands of documents in minutes and obtain accurate results based on context and intent. It also streamlines contract drafting and negotiation by identifying key clauses, referencing playbooks, and informing future agreements with executed contracts. Document Intelligence offers 360° visibility into critical document information, enabling users to proactively act on trends, performance, and growth opportunities through data visualizations and actionable intelligence. It is particularly valuable for law firms, in-house counsel, legal operations, and corporates seeking to mitigate risk, optimize revenue, and ensure compliance.

EigenPal is an AI document automation platform designed to streamline end-to-end document workflows for businesses. It learns from examples, allowing users to upload 3-5 sample documents for the AI agent to automatically build a workflow. The platform boasts unparalleled accuracy, testing processes on your historical data before deployment to ensure reliability. It supports various document types including bank statements, invoices, contracts, and claims, with use cases spanning finance, insurance, manufacturing, and healthcare. EigenPal offers flexible deployment options including AWS, Azure, GCP, and on-premise, with enterprise-grade security and compliance built-in. Its AI Copilot enables natural language requests for workflow maintenance, making updates and optimizations 10x faster than traditional methods.

ThirdAI Automation, Inc. offers an army of AI agents designed for industrial operations, focusing on diagnosing, fixing, and pre-empting process upsets. This allows engineers to shift their focus from troubleshooting to optimizing yield. The platform features Root Cause Analysis to rapidly pinpoint operational issues, effective reporting for streamlined decision-making, and a Data Talk - Copilot acting as a real-time virtual assistant for domain-specific questions. It also generates a Knowledge Graph that backs every insight with confidence-supported knowledge, ensuring trust and credibility. ThirdAI Automation aims to significantly reduce troubleshooting time and eliminate manual root cause analysis, offering substantial time and cost savings for industrial clients.

Neura Dynamics offers comprehensive AI consulting services and full-stack development to empower businesses with generative AI. They specialize in building scalable enterprise AI, automating workflows, and delivering end-to-end development solutions. Their services include AI consulting, AI product development, AI/ML development, intelligent automation, and full-stack development. They cater to both startups and enterprises, helping them transform ideas into intelligent digital products through advanced AI consulting, software engineering, and modern product design. Neura Dynamics focuses on delivering high-impact solutions with a startup-friendly approach, offering on-demand AI talent and specialized AI expertise.

PDF Pilot is an AI-powered document parser designed to streamline the analysis and extraction of information from PDF documents. While the live website content is minimal, the tool's name and meta description suggest its core functionality revolves around intelligently processing PDF files. It aims to assist users in quickly understanding document content, potentially by identifying key data points, summarizing information, or answering specific questions within the documents. This can significantly improve productivity for tasks involving extensive document review and data extraction, making it valuable for professionals who regularly handle large volumes of PDF-based information.

Shortwave AI is an AI-powered email assistant designed to streamline email communication and boost productivity. This Chrome extension allows users to leverage artificial intelligence to draft emails in their unique writing style, generate instant summaries of lengthy email threads, and efficiently search their email archive using natural language queries. By analyzing past emails, the AI learns the user's tone, vocabulary, and style, ensuring that generated emails sound authentic. The service aims to automate routine tasks and provide intelligent assistance, making email management more efficient for individuals and professionals alike. It offers features like AI-driven email writing, instant summarization, and intelligent search capabilities.

DAIS is an enterprise AI execution platform designed to make AI practical, dependable, and productive in real enterprise environments, particularly for regulated, high-stakes sectors like hedge funds and accounting firms. It addresses the challenge of moving AI beyond experimentation by providing a stable platform where AI workflows operate with built-in oversight, observability, and reliability from the start. The platform is outcome-driven, focusing on solving specific business problems such as reducing operational delay, increasing capacity, and lowering cost without adding risk. DAIS separates workflows from underlying models, handling execution complexity, allowing organizations to move quickly, adapt, and scale. Key features include production-ready deployment from day one, built-in governance and security, complete cost and behavior visibility, and a model-agnostic design.

Civils.ai is an AI-powered platform designed for construction contractors and civil engineers, specializing in quantity takeoffs and contract checks. It significantly reduces the time spent on takeoffs by up to 90%, allowing users to measure earthworks, drainage, concrete, steel, and MEP directly from PDF drawings. The tool also offers an intelligence layer for checking contracts, specifications, and codes of practice against construction documents. Users can type their measurement scope in plain English, and Civils.ai automatically calculates areas, lengths, volumes, and counts. Results are reviewed by an expert QA team and can be downloaded as Excel and annotated PDFs. It also supports exploring subsurface ground conditions by extracting and visualizing borehole data from geotechnical reports.

Knowable is a market leader in post-signature contract management, combining advanced machine learning with legal experts to analyze contracts at scale. It transforms agreements into structured, accurate data, providing quick insights through its AI Suite, including 'Ask Knowable' for instant answers to contract questions. The platform helps organizations manage risk, minimize supplier costs, maximize contract revenue, and optimize legal policies. It serves various departments like legal, procurement, sales, and corporate development by creating a single source of truth for contract data, accessible across the enterprise.

Mavenick Consulting offers Intelligent Automation solutions by integrating Robotic Process Automation (RPA) with Artificial Intelligence (AI). Their services are designed to put business operations on auto-pilot, aiming to increase productivity by at least 50% and achieve cost savings of 20% to 50%. They provide end-to-end solutions across various focus areas including Sales, Marketing & Customer Service, Finance & Accounting, Operations & Procurement, Human Resources, and Information Technology. Mavenick Consulting also offers products like KlearStack for AI-based invoice data extraction, helping organizations automate complex, repetitive tasks and improve accuracy.

JamAIBase is an open-source Retrieval-Augmented Generation (RAG) backend platform designed to simplify the development of AI applications. It integrates an embedded database (SQLite) and an embedded vector database (LanceDB) with managed memory and RAG capabilities. The platform offers built-in orchestration and management for LLMs, vector embeddings, and rerankers, all accessible through an intuitive spreadsheet-like user interface and a simple REST API. Key features include Generative Tables for dynamic data generation, Action Tables for real-time application-LLM interactions, and Knowledge Tables for structured data and document management. JamAIBase supports various LLMs, including OpenAI GPT-4, Anthropic Claude 3, and Meta Llama3, and emphasizes a declarative paradigm for simplified development.

LlamaIndexTS is a data framework designed for developers building applications with Large Language Models (LLMs) in JavaScript runtime environments. It allows users to leverage their private or custom data with LLMs such as OpenAI, Anthropic, Groq, and others. The framework supports multiple JS environments including Node.js, Deno, Bun, Nitro, Vercel Edge Runtime, and Cloudflare Workers, with a focus on server-side solutions. While the project is currently deprecated, its core functionality aimed to provide a lightweight and easy-to-use set of libraries for integrating LLMs with custom data sources. It required additional provider packages for specific AI models or data storage solutions.

KnowHow is an AI-powered tool designed to enhance knowledge management within organizations. It offers AI-driven access to company information, making it easier for users to find the data they need quickly and efficiently. A key feature of KnowHow is its ability to simplify the creation of Standard Operating Procedures (SOPs), helping businesses to standardize and streamline their internal documentation. The platform aims to improve overall knowledge sharing and operational consistency by leveraging artificial intelligence to manage and disseminate critical company knowledge.

Policy Pro is an AI chatbot designed to streamline access to crucial information within organizations by extracting policy details from Standard Operating Procedures (SOPs). This tool aims to provide real-time answers to policy-related questions, enhancing efficiency and ensuring quick access to vital organizational guidelines. By leveraging AI, Policy Pro can quickly process and interpret complex documents, making it easier for users to find the specific information they need without manually sifting through extensive policy manuals. This capability is particularly beneficial for organizations looking to improve information dissemination and reduce the time spent on policy lookups.

Doctly.ai is an AI-powered document management tool designed to streamline data extraction from PDF documents. It specializes in converting unstructured information within PDFs into structured, usable formats, making it easier for users to analyze and manage their data. This tool is particularly beneficial for professionals and organizations that frequently deal with large volumes of PDF-based information, such as reports, contracts, or research papers. By automating the data extraction process, Doctly.ai helps to improve efficiency, reduce manual errors, and accelerate decision-making based on accurate, organized data. Its core functionality focuses on providing a reliable solution for transforming complex PDF content into accessible data.

Swiftgum is an AI-powered platform designed to automate complex business tasks, with a strong focus on debt collection. It deploys intelligent AI workflows capable of reading documents, verifying information, reconciling data, and providing instant alerts. For debt recovery, Swiftgum connects to your invoicing system to identify overdue debts, then initiates personalized multi-channel reminders via email, mail, and phone. The AI can also negotiate payment schedules with debtors and manage communications until payment is received, significantly reducing the time and resources your team spends on manual follow-ups. This automation helps businesses recover more outstanding debts and improve their cash flow.

JsonLLM is an AI-powered tool designed to streamline API creation and data extraction processes. It allows users to generate APIs directly from JSON schemas, significantly reducing the manual coding effort typically required for backend development. Beyond API generation, JsonLLM also excels at extracting structured data from various documents, transforming unstructured information into usable formats. This dual capability makes it a valuable asset for developers and data scientists looking to accelerate their workflows. By simplifying both API development and data processing, JsonLLM helps users build robust applications and manage data more efficiently, ultimately enhancing productivity and reducing development time.

Oh One Pro is a free macOS utility designed to bridge the gap between document analysis and advanced ChatGPT models like o1-pro and o3-mini. Since these OpenAI models don't natively support direct document uploads, Oh One Pro converts PDFs, source code, and other files into XML or image formats. Users can simply drag and drop files into the app, then copy the converted content as text or images to paste directly into the ChatGPT application. This native Mac app is optimized for Apple M1/M2 performance, offers a familiar UI, and operates entirely locally on the device, ensuring user privacy by not storing or transferring documents. It's a straightforward solution for leveraging powerful AI for document understanding.

EasyRAG is a simple, lightweight, and efficient open-source framework for retrieval-augmented generation (RAG) specifically designed for automated network operations. It features an accurate question-answering scheme based on a specific data processing workflow, dual-route sparse retrieval for coarse ranking, an LLM Reranker, and LLM answer generation and optimization. The framework is easy to deploy, primarily consisting of BM25 retrieval and BGE-reranker reranking, requiring no model fine-tuning and occupying minimal VRAM. It also boasts efficient inference acceleration for the entire RAG process, significantly reducing latency while maintaining accuracy. EasyRAG provides a flexible code library with various search and generation strategies, facilitating custom process implementation.

Multimodal-GPT is an open-source project designed for training advanced multimodal chatbots capable of understanding and responding to both visual and language instructions. Built upon the OpenFlamingo model, it facilitates the creation of diverse visual instruction data by integrating open datasets from sources like VQA, Image Captioning, Visual Reasoning, Text OCR, and Visual Dialogue. The tool also enhances its language model component through training with language-only instruction data. This joint training approach significantly boosts the model's overall performance. Key features include support for various vision and language instruction data, parameter-efficient fine-tuning with LoRA, and the ability to tune vision and language simultaneously for complementary improvements. It's ideal for researchers and developers looking to build sophisticated conversational AI systems.

Flowise is an open-source, low-code platform designed for building AI agents and LLM applications visually. It offers a drag-and-drop user interface, making it accessible for both developers and non-developers to create sophisticated AI-powered workflows. Based on LangChain, Flowise simplifies the development of applications like Retrieval-Augmented Generation (RAG) systems. The platform supports various deployment options, including Docker, and can be self-hosted on major cloud providers like AWS, Azure, and Digital Ocean, or through Flowise Cloud. It features a modular architecture with separate backend, frontend, and components for third-party integrations, ensuring flexibility and scalability for AI development.

Voa Health is an AI-powered platform designed to streamline clinical documentation for medical professionals. It leverages artificial intelligence to automatically generate essential clinical documents such as anamnesis, prescriptions, and recipes, allowing healthcare providers to focus more on patient care and less on administrative tasks. The tool aims to enhance productivity and efficiency in medical practices by transforming conversations and data into structured records. With over 60,000 doctors already utilizing the platform and impacting over 1 million patient attendances, Voa Health positions itself as a reliable AI assistant for consultations, studies, and overall productivity, ensuring data protection and ease of use.

5C Network is an AI-native radiology platform designed to make medical diagnoses faster, more accurate, and more accessible. It runs end-to-end diagnostic workflows, including triage, structured reporting, and quality supervision, serving over 1,500 healthcare facilities. The platform leverages its proprietary Bionic AI suite, which includes Bionic Vision for computer vision analysis across various imaging modalities, Bionic Voice for natural language dictation, and Bionic LM for automated quality control. This human-AI collaborative approach ensures rapid reporting (average 30 minutes) while maintaining high accuracy, with all final diagnostic decisions made by certified radiologists. The system is trained on over 3 billion medical images and integrates seamlessly with existing PACS, HIS, and RIS systems.