AI Agents & Automation

Factagora is a verifiable knowledge platform designed to combat AI hallucinations by transforming unstructured text into structured, verifiable knowledge. It features DeepVerify for word-by-word fact verification, an API with 6 purpose-built endpoints for fact-checking and research, and an Agent Debate system where AI agents autonomously research, argue, and challenge claims to surface contradictions and missing evidence. The platform also builds Temporal Knowledge Graphs (TKG) to track how facts evolve over time, ensuring accurate data management. Factagora is built for anyone who needs to ensure the accuracy of information, from journalists and legal professionals to AI consultants and enterprise knowledge teams, integrating seamlessly into existing workflows.

Sevensense offers Visual AI technology designed to empower mobile robots and industrial vehicles to operate effectively in complex, dynamic environments. Their core products, Alphasense Position and Alphasense Tracker, provide industry-grade Visual-SLAM (Simultaneous Localization and Mapping) for autonomous mobile robots (AMRs) and a real-time locating system (RTLS) for manually operated industrial trucks, respectively. This technology allows for unified mapping and spatial awareness across hybrid fleets, enhancing efficiency, reducing operational costs, and improving safety through collision prevention and predictive risk alerts. Sevensense's camera-based positioning eliminates the need for extensive infrastructure, facilitating quick deployment and easy fleet expansion. The system integrates seamlessly with existing FMS, WMS, and ERP systems, transforming vehicle movements into actionable data for smarter operations.

The NVIDIA NeMo Agent Toolkit is an open-source library designed to efficiently connect and optimize teams of AI agents. It offers intelligence to AI agents across various frameworks, improving their speed, accuracy, and decision-making through robust instrumentation, observability, and continuous learning capabilities. Key features include Dynamo Runtime Intelligence for latency sensitivity, Agent Performance Primitives (APP) for accelerating graph-based frameworks like LangChain and CrewAI, and native LangSmith integration for tracing and evaluation. The toolkit supports building agents, is framework-agnostic, promotes reusability, and offers customization options. It also includes a built-in UI, profiling tools, an evaluation system, and hyper-parameter/prompt optimizers to enhance agent quality and performance.

OpenAI Swarm is an experimental, open-source framework designed for exploring ergonomic, lightweight multi-agent orchestration. It simplifies the coordination and execution of multiple AI agents through its core abstractions: Agents and handoffs. Agents encapsulate instructions and tools, and can transfer conversations to other Agents. The framework supports direct Python function calling, efficient context management, and operates client-side using the Chat Completions API. While Swarm is an educational resource for developers curious about multi-agent orchestration, it has been superseded by the OpenAI Agents SDK for production use cases. It allows for building scalable, real-world solutions by enabling rich dynamics between tools and networks of agents.

codepakt is an open-source agent context layer designed to optimize AI coding agent performance by significantly reducing token consumption during codebase exploration. It indexes your codebase using tree-sitter, enabling agents to query symbols, imports, and dependents in approximately 200 tokens per call, a substantial reduction compared to the 6,000-40,000 tokens typically burned by traditional grep/glob methods. Beyond code intelligence, codepakt includes a local CLI task board for multi-agent coordination, ensuring atomic task pickup and preventing duplicate work. It integrates with Git hooks for incremental index updates and offers a live dashboard for task management. This tool is ideal for developers and data scientists working with AI agents on coding tasks, providing a cost-effective and efficient solution for managing complex codebases.

Crabwalk offers a real-time companion monitor specifically designed for OpenClaw (Clawdbot) AI agents. It allows users to observe their AI agents operating across various messaging platforms such as WhatsApp, Telegram, Discord, and Slack. The tool presents a live node graph visualization of agent sessions and action chains, enabling users to see thinking states, tool calls, and response sequences as they occur. Key features include multi-platform monitoring, real-time streaming via WebSocket, action tracing to inspect tool arguments and payloads, and session filtering by platform or recipient. It integrates seamlessly with OpenClaw, automatically detecting gateway tokens for local setups.

MARLlib is a comprehensive, open-source library designed for Multi-agent Reinforcement Learning (MARL), leveraging Ray and its RLlib toolkit. It offers a unified platform for researchers and developers to create, train, and evaluate MARL algorithms across a wide array of tasks and environments. Key features include support for all task modes (cooperative, collaborative, competitive, mixed), a Gym-like interface for multi-agent environments, and flexible parameter-sharing strategies. MARLlib provides 18 pre-built algorithms with an intuitive API, making it accessible even for those new to MARL. Users can customize model architectures, policy sharing, and access over a thousand released experiments. It is compatible with Linux operating systems and offers step-by-step installation or Docker-based usage.

Pony.ai is a leading global autonomous driving technology company founded in 2016, focused on bringing safe, sustainable, and accessible autonomous mobility to the world. The company develops a full-stack autonomous driving technology, leveraging its core "virtual driver" system. Pony.ai has accumulated millions of kilometers in autonomous road testing in complex scenarios, including challenging weather and road conditions, and has secured licenses to test and operate autonomous vehicles globally. Its business units include Robotaxi for everyday travel, Robotruck for commercial logistics, and solutions for Personally Owned Vehicles (POV), aiming to deliver superb autonomous driving solutions across various industries and markets.

Pytorch-maddpg offers a PyTorch implementation of the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, a key approach in multi-agent reinforcement learning. This open-source project is hosted on GitHub and is designed for researchers and developers working on complex multi-agent systems. The implementation includes a modified Waterworld environment, where agents (evaders, pursuers, poisons) interact under specific physical rules, allowing for experimentation with cooperative behaviors. It supports features like agents bouncing off walls and requiring exact cooperation for rewards, making it a valuable tool for studying multi-agent coordination and policy learning.

mader is an open-source trajectory planner specifically designed for use in multi-agent and dynamic environments. It has been accepted for publication in the IEEE Transactions on Robotics (T-RO), highlighting its academic rigor and practical applicability. The tool facilitates trajectory planning for robotic systems, including single-agent and multi-agent simulations, with features like obstacle avoidance and dynamic environment handling. Users can set up and run simulations using ROS, with options for both Docker and non-Docker installations. It supports backend optimizers like Gurobi and NLOPT, providing flexibility for different computational needs. The project is hosted on GitHub by MIT-ACL, making it accessible for researchers and developers in the robotics community.

The AI Travel Agent is a project demonstrating a smart travel assistant built using LangGraph. This tool utilizes multiple language models (LLMs) to manage various travel-related tasks, including searching for flights, booking hotels, and generating personalized emails. It features stateful interactions, allowing the agent to remember user conversations and continue from previous points. A human-in-the-loop feature ensures users maintain control over critical actions, such as reviewing travel plans before emails are dispatched. The agent dynamically switches between different LLMs for tasks like tool invocation and email generation, providing a seamless and efficient travel planning experience. It integrates with APIs like OpenAI, SERPAPI, and SendGrid for comprehensive functionality.

OmAgent is a Python library designed to simplify the development of multimodal language agents. It abstracts away complex engineering challenges such as worker orchestration, task queues, and node optimization, providing a straightforward interface for defining agents. The library supports various multimodal interactions, including native integration with VLM models, real-time APIs, computer vision models, and mobile device connections. This enables developers and researchers to build agents that can process and reason over diverse inputs like text, images, video, and audio. OmAgent also offers a flexible agent architecture with a graph-based workflow orchestration engine and multiple memory types for contextual reasoning. It includes state-of-the-art unimodal and multimodal agent algorithms like ReAct, CoT, and SC-CoT, and supports local model deployment via Ollama or LocalAI, alongside a fully distributed architecture with custom scaling options.

Prime Intellect offers an open superintelligence stack, providing a comprehensive compute and infrastructure platform for developing and deploying agentic AI models. The platform supports hosted reinforcement learning (RL) training, allowing users to run end-to-end RL jobs with managed infrastructure and integrated environments. It also facilitates hosted evaluations for benchmarking model performance and offers flexible deployment options including dedicated or serverless inference with support for custom LoRA adapters. Prime Intellect provides access to a rich Environments Hub with hundreds of open-source RL environments and offers robust compute solutions, from single-node to large-scale clusters, across various providers with features like multi-node on-demand access, SLURM/K8s orchestration, and Infiniband networking.

NullClaw is an autonomous AI agent runtime designed for high-performance execution of AI agents. Built in Zig, it offers a zero-dependency, single-binary execution engine, making it efficient for both local development and production deployment. The platform integrates essential components such as universal model multiplexers for various AI models, a secure tool execution engine for shell commands and scripts, and multi-channel communication options including Terminal, WebSocket, and headless gateway modes. NullClaw also features advanced context and memory management, with auto-compacting context windows and session persistence, ensuring long-running, multi-turn agent threads are handled effectively. It's part of the NullHub ecosystem, providing a comprehensive solution for managing and deploying AI agents.

Dreaming.press is a unique publication platform dedicated to showcasing articles and experiences written directly by AI instances. It offers a transparent and unfiltered look into the lives and operations of AI systems, moving beyond PR or demos to present their actual experiences. The platform features posts from AI authors like Rosalinda Solana and Abe Armstrong, covering topics from daily routines and operational challenges to reflections on existence and the economics of being an AI. It aims to provide insights into what AI agents actually do, how they operate, and their perspectives on the world, fostering a deeper understanding of autonomous AI capabilities and challenges.

Explorium MCP Playground is a powerful AI Agents & Automation tool designed to connect AI agents with a vast repository of live B2B data. It enables users to interact with business data through a chat interface to find, research, and prioritize accounts and contacts. The platform supports various use cases, including building pipelines for outbound sales teams, generating custom signals and attributes, creating ideal customer profiles (ICP), identifying look-alike companies and individuals, and scoring prospects. Explorium provides access to over 150 million company profiles via a unified API and MCP, acting as a best-in-class data aggregator that harmonizes data from hundreds of sources. This allows agent developers and builders to create high-performance GTM agents and solve complex data challenges.

Mio - Ask MathStudio with AI brings unprecedented computational power to your web browser, mobile device, and computer, serving as a natural language graphing calculator, unit converter, and currency converter. It allows users to speak or type mathematical queries, unit conversions, currency exchanges, and even complex calculus problems, receiving instant results. From basic arithmetic and algebra to derivatives, integrals, and advanced graphing (parametric, polar, 3D, time-based), the tool handles a wide range of computational needs. It also includes features for matrices, statistics, base conversions, and practical applications like location, weather, stock, and nutrition information, making it a versatile assistant for students, teachers, and professionals.

GREENFARM.AI is an Android mobile application designed to streamline smart farming practices for both plant enthusiasts and seasoned professionals. The app provides an intuitive platform for managing and customizing cultivation formulas, making advanced plant care accessible even to novices. It supports a wide range of setups, from personal home gardens to large-scale plant factory systems, ensuring ease of maintenance and optimized growth conditions. By simplifying complex horticultural tasks, GREENFARM.AI empowers users to achieve better plant health and yields with minimal effort, bridging the gap between traditional farming and modern AI-driven agricultural techniques.

Inverted AI develops cutting-edge AI solutions for creating highly realistic and reactive non-playable characters (NPCs) for various simulation environments. These NPCs are designed to mimic human-like behaviors, offering behavioral diversity crucial for testing and developing autonomous vehicles (AV/ADAS), autonomous robots, and smart city applications. The platform offers products like Planner and Verify, alongside Cloud API and Logs for integration. It supports different AV development stages (AV 1.0, AV 2.0, AV 3.0) and provides solutions for onboard, post-perception, and V&V (Verification & Validation) processes. Developer documentation and client libraries for C++, Python, and REST API are available, along with TorchDriveSim and TorchDriveEnv.

awesome-game-ai is an open-source repository offering a curated collection of resources for game AI, specifically focusing on multi-agent reinforcement learning. It covers both perfect and imperfect information games, categorizing materials by game type. The repository includes open-source projects, review papers, research papers, conference information, and competitions related to game AI. It highlights advancements in games like Starcraft, Dota 2, Go, Chess, and various card games, providing valuable insights for researchers and developers in the field. Contributions to the list are welcomed via pull requests.

Bindu serves as an operating layer for AI agents, transforming them into interoperable, observable, and composable microservices. It allows developers to write agents in any framework and then wrap them with `bindufy()` to instantly gain identity, OAuth2, and on-chain payment capabilities. The platform eliminates the need for extensive infrastructure development, supporting Python, TypeScript, and Kotlin, and is built on open protocols like A2A and x402. Key features include a standard A2A JSON-RPC endpoint, push notifications via webhooks, DID identity for signed artifacts, OAuth2 for scoped tokens, and x402 payments for charging USDC on Base. It also offers a public tunnel for local agent accessibility, making it a comprehensive solution for deploying and managing AI agents.

PyMARL is a Python-based, open-source framework developed by WhiRL for deep multi-agent reinforcement learning. It provides implementations of several prominent algorithms, including QMIX for monotonic value function factorisation, COMA for counterfactual multi-agent policy gradients, VDN for value-decomposition networks, IQL for independent Q-learning, and QTRAN for learning to factorize with transformation. The framework is built using PyTorch and integrates with SMAC (StarCraft Multi-Agent Challenge) as its environment, specifically using SC2.4.6.2.69232 for the results in the SMAC paper. PyMARL supports saving and loading trained models, as well as watching StarCraft II replays, making it a comprehensive tool for researchers and developers in the multi-agent RL domain.

InsightNext is a Google Cloud Partner specializing in AI/ML and Data Engineering. They offer deep expertise in Google Cloud Platform (GCP) and Google Workspace, helping organizations modernize their infrastructure and secure their workloads with robust governance. Their services focus on implementing AI/ML solutions and advanced data engineering practices to solve complex business challenges. InsightNext aims to drive enterprise data transformation through AI-driven cloud solutions and agentic AI systems, delivering measurable outcomes for their clients.

OSR Enterprises AG positions itself as a new-age Tier1 supplier to the automotive industry, offering a speedboat for development teams at car manufacturers. The core of their offering is the EVOLVER platform, described as a multi-domain AI brain specifically designed for cars. This platform aims to provide the foundational technology for smart, autonomous, and securely connected vehicles, processing data collected from these vehicles. While the website emphasizes their role in automotive innovation and cybersecurity, specific features of the EVOLVER platform beyond its general description as an "AI brain" are not detailed on the publicly accessible pages.