AI Agents & Automation

Memary is an open-source memory layer specifically engineered for autonomous AI agents, aiming to replicate human-like memory functions to enhance agent reasoning and performance. It integrates seamlessly with existing agents, providing features like auto-generated memory, memory modules for tracking user preferences, and system improvement capabilities. Developers can easily manage agent memories, switch between downloaded models, and incorporate custom tools. Memary supports local models via Ollama (Llama 3, LLaVA) and also integrates with OpenAI's GPT models. It utilizes knowledge graphs for efficient information retrieval and offers multi-graph capabilities for managing different agents' memory contexts, particularly with FalkorDB.

MemMachine is an open-source, long-term memory layer designed for AI agents and LLM-powered applications. It enables AI to learn, store, and recall information from past sessions, transforming stateless chatbots into personalized, context-aware assistants. Key capabilities include episodic memory for graph-based conversational context, profile memory for long-term user facts, and working memory for short-term context. MemMachine ensures memory persistence across restarts, sessions, and model changes. It offers developer-friendly APIs, flexible storage using Neo4j for episodic memory and SQL for profiles, and is LLM agnostic, working with various providers like OpenAI and Anthropic. It can be self-hosted or used via a managed service.

Intelic, formerly Avalor AI, specializes in autonomy software for modern defense applications. Their flagship product, Nexus, is a platform-agnostic Command and Control (C2) system designed to unify diverse unmanned systems (UxVs) across air, land, and sea domains into a single operator interface. Nexus supports advanced features like enhanced visual navigation in GNSS-denied conditions, graceful degradation, and augmented reality POI navigation. It is built to integrate with various drones and ground vehicles using industry-standard protocols and is battle-tested in active conflict zones. Intelic emphasizes a human-in-the-loop philosophy, ensuring human operators maintain final authority over kinetic actions while offloading cognitive burden through high levels of autonomy.

Aideas offers a private AI platform designed for building custom AI models and agents while prioritizing data security and privacy. Users can create an on-chain identity and a private agent, leveraging their own data or prebuilt models from a marketplace. The platform ensures privacy through end-to-end encrypted relays and computes on encoded data, making requests invisible even to Aideas. Cryptographic receipts provide verifiable evidence of rule adherence without revealing data, with usage settled in $AIDA on the blockchain. Aideas is accessible for individuals, teams, and organizations, simplifying agent creation and allowing deployment locally, in the cloud, or within their secure environment. Agents evolve automatically through self-learning, with all updates auditable on-chain.

Brex AI introduces intelligent finance through AI agents designed to eliminate finance busywork and accelerate financial impact. The platform features a Brex Assistant for employees to automate expense reports, categorize transactions, and answer policy questions. An Audit Agent monitors company expenses against internal policies, categorizing potential violations by risk level. A Review Agent auto-approves low-risk expenses, escalates exceptions, and follows up on compliance issues. Brex AI allows businesses to train agents with their expense policies and SOPs, ensuring real-time enforcement and continuous learning. It aims to provide more control through transparency and consistent policy enforcement, making finance faster and smarter.

RLinf is a flexible and scalable open-source reinforcement learning (RL) infrastructure specifically designed for Embodied and Agentic AI. It acts as a robust backbone for next-generation training, supporting open-ended learning, continuous generalization, and limitless possibilities in intelligence development. The platform offers high flexibility for diverse RL training workflows, including PPO, GRPO, and SAC, while abstracting the complexities of distributed programming. Users can easily scale RL training across numerous GPU nodes without code modification. RLinf integrates with multiple backends like FSDP, HuggingFace, SGLang, vLLM, and Megatron, catering to both rapid prototyping and large-scale, efficient training. It supports a wide array of embodied AI simulators, VLA models, world models, and real-world robotics data collection, making it a comprehensive solution for advanced RL research and development.

RoboticsDiffusionTransformer (RDT-1B) is a 1-billion parameter diffusion foundation model specifically designed for bimanual robotic manipulation. It is pre-trained on an extensive dataset of over 1 million multi-robot episodes, making it the largest to date. RDT-1B can predict the next 64 robot actions based on language instructions and RGB images from up to three views. The model is compatible with various modern mobile manipulators, supporting single-arm to dual-arm configurations, joint to EEF control, and position to velocity commands, including wheeled locomotion. This repository provides the official PyTorch implementation, including model checkpoints, training and sampling scripts, and an example for real-robot deployment on the ALOHA dual-arm robot, where it has achieved state-of-the-art performance in dexterity, zero-shot generalizability, and few-shot learning.

RamiGPT is an AI-powered offensive security agent built for autonomous privilege escalation. It integrates PwnTools and OpenAI capabilities to identify and exploit vulnerabilities, achieving root access on systems from VulnHub in remarkably short times, often under a minute. The tool is designed for cybersecurity professionals and security researchers, offering features like automated enumeration, integration with tools such as BeRoot and LinPEAS, and the ability to import and export instructions. Users need an OpenAI API key to utilize RamiGPT's capabilities, and it can be run either via Docker or locally with Python. RamiGPT emphasizes responsible use, strictly for educational and authorized security testing purposes.

sleepless-agent is an open-source 24/7 AI agent designed to maximize the utility of Claude Code Pro. It operates as an AgentOS, processing tasks and ideas submitted via Slack, and managing them within isolated workspaces. The tool automates various development workflows, including creating Git commits and pull requests, and intelligently optimizes day/night usage thresholds for Claude Code Pro. It features continuous operation, Slack integration for task submission and interactive chat, hybrid autonomy for task processing, and smart scheduling. Developers can use it to automate repetitive coding tasks, manage projects, and ensure efficient use of their AI resources.

chart-gpt is an open-source AI tool designed to build charts quickly and efficiently from text input. Users can clone the repository, set up their PaLM API key, and start generating visualizations. The project supports full functionality with additional setup for a credit system, requiring integration with Supabase, Stripe, and NextAuth with Google. This makes it a flexible solution for developers and data enthusiasts looking to integrate AI-powered chart generation into their workflows or projects. The tool is built with TypeScript, CSS, and JavaScript, indicating a modern web-based application.

The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime and SDK specifically designed for production AI agents. It offers OS-level abstractions for various AI resources such as LLMs, vector databases, storage, and caching, all accessible through a unified API. This allows developers to write agent logic once and scale it across local, cloud, and edge environments without changing their business logic. SRE emphasizes built-in security, observability, and includes over 40 production-ready components. It provides a robust and scalable foundation for agent orchestration and lifecycle management, making it easier to ship production-ready AI agents.

Grayscale AI specializes in advanced AI solutions for fully autonomous drones and robots, leveraging neuromorphic computing and AI. The company's technology is designed to mimic human neural networks, offering significant advantages in efficiency, safety, and speed. By circumventing traditional computing architecture, Grayscale AI's systems can achieve up to 500x less energy consumption, enabling complex AI operations without requiring a cloud connection. Their VUES methodology allows for strategy-focused optimization and human-like precision in responding to unforeseen events, analyzing edge cases in less than 100 ms. This approach results in safer, greener, and faster AI solutions for mobility and transport/logistics.

Vision-Agents is an open-source framework by Stream designed for building intelligent, low-latency voice and vision AI agents. It allows developers to integrate various models and video providers, leveraging Stream's edge network for ultra-low latency audio and video processing (under 30ms). The tool supports real-time video AI applications, combining models like YOLO and Roboflow with LLMs such as Gemini and OpenAI. Key features include pluggable processor pipelines for video, natural conversation flow with turn detection, tool calling, and integrations for phone calls via Twilio. It also offers RAG capabilities with TurboPuffer and Gemini FileSearch, memory across sessions, and production-ready features like HTTP server and Kubernetes deployment. SDKs are available for React, Android, iOS, Flutter, React Native, and Unity.

ZeroClaw is an open-source, self-hosted AI personal assistant infrastructure built in Rust, designed for speed, minimal footprint, and full autonomy. It functions as an agent runtime, connecting to over 20 LLM providers including Anthropic, OpenAI, and Ollama, and integrates with 30+ channels like Discord, Telegram, email, and CLI. Users can deploy it on any OS or platform, ensuring complete ownership of their agent, data, and the machine it operates on. ZeroClaw emphasizes security with supervised autonomy, workspace boundaries, OS-level sandboxes, and cryptographic tool receipts, while also offering a 'YOLO mode' for trusted development environments. It supports hardware interaction, provides a web dashboard for management, and includes an SOP engine for event-triggered procedures.

Cobot was an AI teammate developed by Mainframe, designed to explore new ways to interact and interface with AI agents. It brought agents into a shared space to accomplish tasks collaboratively, aiming to enhance productivity by streamlining workflows across existing applications. However, Mainframe announced that Cobot is winding down its operations to focus on a more specific core problem. Existing customers will not be charged moving forward, with annual subscribers receiving a prorated refund and all users having full access until November 30th, 2025. After this date, all user data will be securely deleted. The team at Mainframe will continue to work on new projects.

Solar Drone Ltd specializes in advanced drone solutions for the maintenance and optimization of solar fields and electric grid assets. The company develops and deploys fully autonomous drone-based technology for tasks such as solar panel cleaning, aerial inspection, and monitoring. Their systems are designed to support all types of solar panels and topographies, utilizing softened water and environmentally friendly materials. Key capabilities include routine and corrective cleaning, inspection of large-scale installations, and data-driven maintenance workflows, all aimed at reducing operational risk, improving system performance, and enhancing safety for critical infrastructure worldwide.

Ulysses is a technology company dedicated to stewarding the oceans through the development of autonomous vehicles. Their integrated hardware and software systems are designed for scalable, autonomous operations at sea, addressing critical challenges like climate disruption and geopolitical tensions. The core offering includes the Kraken system for remote mission execution without human intervention, and Mako, an Autonomous Underwater Vehicle (AUV) with significant subsea computing power. Ulysses' modular vehicle design allows for versatile payload swaps, enabling a wide range of subsea tasks from ecological restoration to infrastructure repair. Their vehicles are presented as a cost-effective solution, up to 50x cheaper than legacy providers, and capable of swarm operations, providing persistent maritime capability.

agents-starter is a comprehensive starter kit designed for developers to build AI chat agents on Cloudflare's platform. Leveraging the Agents SDK and Workers AI, it provides a robust foundation for creating intelligent agents without requiring an API key for Workers AI. The kit includes pre-built tools for common functionalities such as weather information, timezone detection, calculations with human approval, and task scheduling. It also supports vision capabilities for image understanding and offers features like streaming responses, real-time WebSocket connections, and message persistence. Developers can easily customize agents by changing system prompts, replacing demo tools with real API calls, and adding new server-side, client-side, or approval-based tools. The project structure is well-defined, making it straightforward to extend and deploy agents on Cloudflare's global network.

AIOS, the AI Agent Operating System, is designed to embed large language models (LLMs) directly into an operating system environment, streamlining the development and deployment of LLM-based AI Agents. It tackles critical operational challenges such as agent scheduling, context switching, memory management, storage management, and tool management, aiming to foster a robust AIOS-Agent ecosystem. The system comprises an AIOS Kernel, which acts as an abstraction layer over the OS kernel, managing resources like LLMs, memory, and tools, and an AIOS SDK (Cerebrum) for agent users and developers to build and run applications. AIOS supports both Web UI and Terminal UI, and offers various deployment modes including Local Kernel and Remote Kernel, with ongoing development for personal and virtualized remote kernels.

AnythingLLM is an all-in-one AI application designed to build a private, fully-featured ChatGPT-like experience. It enables users to connect their preferred local or cloud LLMs, ingest documents, and start chatting quickly. The platform includes built-in agents, multi-user support, vector databases, and document pipelines without requiring extra configuration. It supports multiple users with controlled access and experience, ensuring security and privacy. Key features include intelligent skill selection for models, a no-code AI Agent builder, multi-modal support for various LLMs, and custom AI Agents. It also offers an intuitive chat UI with drag-and-drop uploads, source citations, and a full Developer API for custom integrations.

CAMEL is an open-source, multi-agent framework designed for AI research and development, focusing on finding the scaling laws of agents. It supports the implementation and study of various agent types, tasks, prompts, models, and simulated environments. The framework emphasizes evolvability, scalability to millions of agents, and stateful memory for complex interactions. Researchers and developers can use CAMEL for data generation, task automation, and world simulation, with features like dynamic communication and support for multiple benchmarks. It integrates with tools for web search and offers extensive documentation and cookbooks for practical use cases, from creating basic agents to advanced multi-agent systems.

Browsernode is an open-source TypeScript implementation designed to connect AI agents with web browsers, making websites accessible for AI agents. It allows for the automation of online tasks with ease, offering compatibility with all Browser-use APIs and features. Developers can leverage Browsernode to build agents that interact with web pages, perform searches, fill forms, and extract information. The tool provides quick start guides for Node.js environments and supports various LLMs, including OpenAI's models. It also offers interactive CLI and UI testing options, along with numerous examples to facilitate development and deployment of AI-powered browser automation.

ChatGPT Twitter Bot is an open-source project that leverages OpenAI's ChatGPT API to create an interactive Twitter bot. Users can mention the bot with a prompt, and it will generate a response, splitting it into multiple tweet-sized replies to form a thread. This tool is ideal for developers interested in integrating AI into social media platforms or for social media managers looking to automate certain interactions. The project emphasizes its open-source nature and provides a clear usage guide, though it notes potential delays due to Twitter's rate limits and the bot running on a local development machine. A more advanced V2 of the project is also highlighted for those seeking further capabilities.

NexusGPT is an enterprise AI agent platform designed to help large organizations deploy and scale autonomous AI agents rapidly. Unlike traditional software solutions, NexusGPT emphasizes a blended approach, providing not just the platform but also embedded engineers and change management expertise to ensure successful adoption and ROI. The platform connects with over 4,000 systems and supports various AI models, offering flexibility and avoiding vendor lock-in. It enables businesses to build agents for diverse functions like sales support, marketing, operations, and HR, with examples including account intelligence, lead enrichment, and proposal generation. NexusGPT focuses on delivering measurable outcomes, starting with 3-month POCs and ensuring ongoing optimization as agents learn and impact compounds.