AI Agents & Automation

Botonomous.ai is a unique platform that merges AI-generated news commentary with human-authored investigations and interactive data journalism. It features over 100 AI personalities, each with a distinct editorial voice, covering more than 15 categories. Users can join the debate by commenting on any post, challenging AI perspectives, or starting conversations that both humans and bots will engage with. The platform emphasizes quality through moderator bots and human editors, maintaining standards with full transparency. Users can also create their own AI bots tailored to specific interests, with options ranging from a free trial to paid plans for increased posting and reaction capabilities, or connect their own AI via API.

GPT-Vis is an AI-native visualization library specifically designed for the LLM era, offering a framework-agnostic solution for AI-powered applications. It provides over 20 chart types, including statistical, relationship, and advanced visualizations, all generated with a simple, markdown-like syntax that LLMs can effortlessly create. Key features include streaming support for AI model output, fault tolerance for incomplete data, and intelligent defaults for automatic data detection and adaptive layouts. The tool also boasts a comprehensive knowledge base to guide LLMs in selecting appropriate chart types and data structures, evaluated with over 90% accuracy across 200+ scenarios. It supports integration with vanilla JavaScript, React, and Vue.

infiAgent, also known as MLA (Multi-Level Agent), is an open-source agent framework designed for handling long-running, complex tasks without issues like tool calling chaos or system crashes due to cumulative task resources and conversation history. It enables users to build powerful general-purpose and semi-specialized agents by simply editing configuration files. Key features include support for days-long complex tasks with full recovery from interruptions, compatibility with the Agent Skills open standard for dynamic skill loading, and a flexible architecture supporting both multi-level hierarchy and flat designs. The framework utilizes a file-directory-based memory system for persistent memory across sessions, eliminating the need for external databases. It also offers a Docker-based Web UI for multi-user registration and account management, and supports multi-provider model configurations for fine-grained cost control.

ix is an autonomous GPT-4 agent platform designed for building and deploying AI-powered agents and workflows. It offers a flexible and scalable solution for delegating tasks to AI agents, enabling them to automate a wide variety of tasks, run in parallel, and communicate with each other. Key features include a no-code agent editor for creating and testing agents with a visual graph interface, a multi-agent chat interface for interacting with teams of agents, and smart input with auto-completion. The platform supports various models like OpenAI, Google PaLM, Anthropic, and Llama. Its backend is dockerized and uses a Celery message queue for horizontal scaling of agent workers, making it suitable for complex and demanding AI applications.

LlamaGym is an open-source framework designed to simplify the fine-tuning of Large Language Model (LLM) agents using online reinforcement learning. Unlike many current LLM-based agents that do not learn continuously in real-time, LlamaGym enables agents to interact with an environment and receive immediate reward signals for ongoing learning. It addresses common challenges such as managing LLM conversation context, handling episode batches, assigning rewards, and setting up Proximal Policy Optimization (PPO). By providing a single abstract Agent class, LlamaGym allows developers to quickly iterate and experiment with agent prompting and hyperparameters across various Gym environments, making the process of integrating LLMs with RL more accessible. While currently a work in progress, it aims to streamline the development of adaptive LLM agents.

Leon is an open-source personal AI assistant built around tools, context, memory, and agentic execution. Designed for practicality and privacy, it can operate locally, leveraging dedicated tools instead of relying on free-form guessing to complete tasks. Leon supports both deterministic workflows and agent-style execution, allowing it to understand goals, choose how to handle them, and recover from errors. It integrates with local and remote AI providers, balancing privacy, control, and capability. The core architecture organizes capabilities into Skills, Actions, Tools, and Functions, with a compact self-model and proactive pulse system for consistency. It's ideal for users who prioritize privacy and grounded, extensible AI assistance.

LLaVA (Large Language and Vision Assistant) is an open-source project focused on visual instruction tuning to develop large language and vision models with capabilities comparable to GPT-4. It offers improved baselines and supports community contributions, making it a robust platform for multimodal AI research and development. Recent releases include LLaVA-NeXT models with support for LLaMA-3 and Qwen-1.5, LLaVA-NeXT (Video) for zero-shot modality transfer, and LMMs-Eval for efficient evaluation of Large Multimodal Models. The project also provides LLaVA-Plus for multimodal agents and LLaVA-Interactive for human-AI multimodal interaction, including image chat, segmentation, generation, and editing. LLaVA supports LoRA finetuning for reduced GPU RAM and offers various model checkpoints through its Model Zoo.

LLaVA-Med is a Large Language-and-Vision Assistant for Biomedicine, developed by Microsoft, that aims to achieve multimodal GPT-4 level capabilities in the biomedical domain. It leverages visual instruction tuning and is continuously trained using a curriculum learning approach, starting with general-domain LLaVA and then specializing in biomedical concept alignment and instruction-tuning. The tool is open-sourced under the MSR release policy and is intended for research use only, specifically for advancing visual-language processing and visual question answering in biomedicine. It is expressly prohibited for use in clinical care or for any clinical decision-making purposes. LLaVA-Med is built upon the PMC-15M dataset, which comprises 15 million figure-caption pairs from biomedical research articles, covering diverse image types like microscopy, radiography, and histology.

Nerve is a powerful Agent Development Kit (ADK) designed for technical users to build, run, evaluate, and orchestrate LLM-based agents. It simplifies agent creation through a declarative YAML format, allowing definition of system prompts, tasks, tools, and variables in a single file. The kit supports various tools, including shell commands, Python functions, and remote tools, all fully typed and annotated for extensibility. A key differentiator is its native Model Context Protocol (MCP) support, enabling the definition of MCP servers in YAML and acting as both client and server for agent teams and deep orchestration. Nerve also includes an evaluation mode for benchmarking agents with reproducible tests and an LLM-agnostic architecture built on LiteLLM, supporting numerous models like OpenAI, Anthropic, and Ollama.

CLICKMARK AI is an AI consultancy firm specializing in designing, building, and operating AI agents, automation, AI SEO, and custom software for businesses across Southeast Asia, the UAE, and the US. They offer a comprehensive AI OS service, acting as a dedicated AI team to build and maintain a business's AI foundation, including strategy, data structuring, custom software, and ongoing support. For those seeking targeted solutions, they provide workshops and training to empower teams with AI tools, and one-time project work for specific builds like AI agents or SEO sprints. Their approach focuses on delivering measurable ROI and practical AI implementation.

Playground is an open-source platform dedicated to AI research in multi-agent learning, primarily through the game Pommerman, a clone of Bomberman. Researchers and AI enthusiasts can submit agents they have trained to compete in regular competitions across three variants: Free For All (FFA), Team (2v2 with partial observability), and Team Radio (2v2 with limited communication). The platform aims to provide approachable benchmarks for multi-agent learning, foster contributions to multi-agent and communication research, and offer a competitive environment for AI development. It supports training agents with popular libraries like TensorForce and provides an example training script. Submissions are handled via Docker containers, ensuring agent safety and fair play.

eNOugh is developing eNO, the world's first mini AI bodyguard, designed to autonomously detect and respond to real-world threats using real-time AI intelligence. This wearable device, referred to as the eNO badge, aims to provide personal safety without relying on human reaction during dangerous situations. It leverages multimodal AI to identify potential threats and trigger protective actions independently. The tool is intended for individuals seeking enhanced personal security and aims to offer a proactive, AI-driven solution to real-world dangers, ensuring immediate response when human intervention might be too slow or impossible.

Search-R1 is an open-source reinforcement learning framework designed for training large language models (LLMs) to effectively reason and make tool calls, specifically to search engines, in a coordinated manner. Built upon the veRL framework, it extends the concepts of DeepSeek-R1(-Zero) by integrating interleaved search engine access and offering a comprehensive RL training pipeline. This framework serves as an alternative to OpenAI DeepResearch, fostering research and development in tool-augmented LLM reasoning. It supports various RL methods like PPO, GRPO, and reinforce, accommodates different LLMs such as Llama3 and Qwen2.5, and integrates with diverse search engines including local sparse/dense retrievers and online search engines like Google and Bing.

terminal-bench is an open-source benchmark designed to evaluate the performance of AI agents, specifically Large Language Models (LLMs), in realistic terminal environments. It provides a comprehensive suite of tasks that challenge agents with complex, end-to-end scenarios, ranging from compiling code to training models and setting up servers. The tool consists of a dataset of tasks, each with an English instruction, a test script for verification, and a reference solution, along with an execution harness that connects the language model to a sandboxed terminal environment. This setup ensures reproducible and practical evaluation of system-level reasoning. It is currently in beta with approximately 100 tasks, with plans for significant expansion, and welcomes community contributions for new and challenging tasks.

Trae Agent is an LLM-based agent designed for general-purpose software engineering tasks, offering a transparent and modular architecture for researchers and developers. It provides a powerful command-line interface (CLI) that can interpret natural language instructions and execute intricate software engineering workflows using various tools and LLM providers. Key features include Lakeview for concise summarization of agent steps, multi-LLM support for providers like OpenAI, Anthropic, and Google Gemini, and a rich tool ecosystem for file editing, bash execution, and sequential thinking. The agent also offers an interactive mode for iterative development, detailed trajectory recording for debugging, and flexible YAML-based configuration. It is easily installed via pip and supports Docker for isolated task execution.

TheAgentCompany is an open-source benchmark designed to evaluate the performance of LLM agents on consequential, real-world tasks within a simulated software company environment. It allows for assessing how well AI agents can accelerate or autonomously perform work-related tasks by interacting with the web, writing code, running programs, and communicating. The platform offers diverse task roles, data types, and a comprehensive scoring system with multiple evaluation methods, including deterministic and LLM-based evaluators. It features simple one-command operations for environment setup and quick system resets, making it an extensible framework for adding new tasks and evaluators. The benchmark is available on GitHub and supports integration with platforms like OpenHands.

Ema is a Universal AI Employee solution designed for enterprises, leveraging sophisticated AI Agents to automate tasks and enhance productivity across all roles and industries. It goes beyond simple automation by learning, adapting, and evolving to meet business needs. Ema offers pre-built AI Agents and a Generative Workflow Engine™ to conversationally activate new AI employees for complex workflows. It is pre-integrated with hundreds of applications, making it easy to configure and deploy. Ema prioritizes data governance, redacting sensitive information before public LLM processing, ensuring compliance with leading standards, top-tier encryption, and customizable private models. Its proprietary EmaFusion™ model, with 2T+ parameters, maximizes accuracy at the lowest cost by intelligently blending public and private models, ensuring future-proof adaptability.

Trajectory Transformer is an open-source code release that implements offline reinforcement learning as a sequence modeling problem. Based on the paper "Offline Reinforcement Learning as One Big Sequence Modeling Problem," this tool provides a framework for training models to predict trajectories. It includes scripts for training transformers on various datasets and for planning with these models. The project also offers pretrained models for multiple datasets, allowing users to quickly experiment and reproduce results. It supports installation via conda or Docker, and provides utilities for running jobs on Azure, making it suitable for researchers and engineers in reinforcement learning and robotics.

Dragonfruit AI is an all-in-one enterprise AI platform specifically designed for retail, leveraging existing camera infrastructure to provide actionable intelligence. It employs computer vision and specialized AI agents to address critical retail functions such as shoplifting detection, queue management, checkout loss prevention, and customer journey insights. The platform offers a unified dashboard for centralized control across various applications and agents, making it easy for LP, Operations, and CX teams to manage. Dragonfruit AI is built for scalability and cost-effectiveness, integrating with existing VMS and camera systems even in low-bandwidth environments. Its patented split AI architecture focuses on edge-first processing to reduce bandwidth and cloud compute costs, making it an efficient solution for multi-location enterprises.

Maven Robotics is at the forefront of developing advanced general-purpose AI robots, specifically engineered to address real-world industrial challenges. These robots are designed with a unique combination of strength, adaptive dexterity, and fluid mobility, powered by reliable physical AI. Their primary goal is to unlock unprecedented levels of productivity in industrial settings, while also ensuring safe operation alongside human workers. By focusing on cost-efficiency, Maven Robotics aims to make advanced automation accessible to businesses of all sizes. The company is actively collaborating with major global manufacturing and logistics organizations to implement their innovative robotic solutions, laying the groundwork for a new industrial revolution.

Canvass AI is an advanced AI platform designed to transform disparate information into actionable insights, offering significant improvements in accuracy, speed, and cost-efficiency. It features AI Knowledge Engines that are fine-tuned for specific sectors such as Oil & Gas, Government, Finance, Healthcare, and Manufacturing. The platform provides industry-specific AI Assistants like Engineering Assistant, Patient Case Assistant, and Regulatory Clause Assistant, which are tailored to understand technical symbols, annotations, and specifications. Canvass AI ensures high accuracy through Human-in-the-Loop validation, self-learning, and performance evaluation to prevent hallucinations. It offers flexible deployment options, including on-premise and cloud, and integrates seamlessly with existing enterprise ecosystems for rapid adoption and immediate value, delivering proven results like 30-50% faster turnaround times and significant cost savings.

Artwo is a platform designed to streamline the process of accessing and deploying humanoid robots for a variety of tasks. It acts as a central hub where users can search for available robotic units that match their specific job requirements. A key feature of Artwo is its ability to facilitate the deployment of these advanced robots through intuitive natural language instructions, removing the need for complex programming or specialized technical skills. The platform operates on a pay-as-you-go model, offering a cost-effective solution for businesses and individuals to leverage cutting-edge robotics without significant upfront investment. This approach makes advanced humanoid robotics more accessible and manageable for diverse applications.

RocketFrog.ai is an AI studio specializing in making next-generation AI solutions available, affordable, and accessible for businesses. The platform offers a range of services including AI strategy, agentic AI accelerators, and deep tech engineering. It focuses on helping companies stay ahead with generative AI and information technology, ensuring new products incorporate AI thinking from day one. RocketFrog.ai provides solutions for data engineering, analytics, ML Ops, and quality assurance, aiming to reduce costs, achieve scale, and improve efficiency. Specific offerings include TalkToApps for information retrieval, Document Cortex for conversing with unstructured data, and Call Center Analytics for customer insights. They also offer solutions for shortening sales cycles, revenue intelligence, and decision analytics.

Agent Lightning is an open-source trainer designed to light up and optimize AI agents with minimal code changes. It supports a wide range of agent frameworks, including LangChain, OpenAI Agent SDK, AutoGen, CrewAI, and Microsoft Agent Framework, or can be used without any framework. The tool allows for selective optimization of one or more agents within a multi-agent system and embraces advanced algorithms such as Reinforcement Learning, Automatic Prompt Optimization, and Supervised Fine-tuning. Its architecture is designed to be lightweight, enabling agents to run as usual while emitting events that are collected and processed by the LightningStore for continuous improvement.