AI Agents & Automation

Fastn UCL is an embedded integration and automation platform designed for SaaS companies and AI agent builders. It provides a solution to eliminate the need for building and maintaining integrations, allowing users to embed once and give customers working integrations powered by AI agents. The platform focuses on trustworthy agents for high-value workflows, helping agents master tools, minimize token usage, and maximize security. Key features include Fastn Adaptive Context, an intelligent gateway that streamlines context, compresses tool chains, and lowers token costs while ensuring enterprise security and compliance. It offers tool orchestration, composition, performance optimization, and transparent tracking of agent decisions and tool usage. Fastn also provides enterprise-grade security, compliance, and performance, including SOC 2 Type II certification, ISO-certification, and HIPAA/PCI readiness.

Cognitum is an AI agent infrastructure platform designed for deploying intelligent agents on the Seed hardware appliance. It facilitates integration via the MCP protocol and offers developer SDKs for Rust, Node.js, and Python, allowing for flexible development. The platform includes essential features for managing agent deployments, such as fleet management, over-the-air (OTA) updates, and an on-device vector store. Security is built-in with Ed25519 cryptographic identity. Cognitum aims to provide a robust environment for agentic computing, supporting edge AI and IoT intelligence through its hardware and software components.

SiClaw is an open-source AI agent platform specifically designed for Site Reliability Engineering (SRE) teams to debug infrastructure incidents. It functions as a hypothesis-driven diagnostic engine, continuously learning from every incident to enhance its deep investigation capabilities. The platform operates with a multi-agent architecture, where specialized AI agents handle different domains like Kubernetes, networking, and system/OS. These agents collaborate to solve complex issues that span multiple layers. SiClaw is read-only by default, ensuring security, and promotes a team-first approach to incident management. It integrates with various infrastructure, messaging, observability, alerting, and development tools, and allows for alert-driven investigations and scheduled health checks.

UpBrains AI provides advanced AI agents to automate document-centric workflows for customer operations, quality, and compliance teams. It specializes in processing enterprise documents like POs, invoices, BOLs, COAs, and SDS, integrating with ERP and helpdesk systems. The platform offers features like inbox automation for classifying and routing messages, accurate document extraction with pre-built or custom extractors, and specific agents for tasks such as Certificate of Analysis processing, order processing, and invoice processing. UpBrains AI emphasizes a document-first design, policy-aware automations, built-in governance for review and audit, and fast time-to-value with pre-built templates and onboarding assistance. It also includes QualiNex, an intelligent quality document management portal for centralized, validated, and auditable quality documents.

Linux Pro: Command & Terminal is an Android mobile application designed to function as a comprehensive point-of-sale (POS) and business management solution. This tool is equipped with a built-in AI assistant, Genie, which aims to boost business efficiency by streamlining various operational tasks. A key feature is its ability to record sales offline, ensuring that business operations can continue uninterrupted even without an internet connection, with all data automatically synchronizing once connectivity is restored. This empowers small businesses to effectively manage their operations from any location, providing flexibility and continuity.

Teammates.ai offers autonomous AI teammates designed to handle entire business functions across customer service, sales, and recruiting. Raya, the AI customer service agent, resolves tickets, processes refunds, and updates orders across multiple channels like phone, email, chat, and social media in over 50 languages. Adam, the AI sales agent, manages inbound and outbound sales, qualifies leads, books meetings, and updates CRMs. Sara, the AI interviewer, conducts live video interviews, scores candidates against custom rubrics, and provides hiring recommendations. These AI teammates integrate with existing enterprise systems, operate 24/7, and are accountable for measurable outcomes, aiming to augment human teams by automating high-volume, repeatable tasks.

Hillbot is at the forefront of embodied AI, specializing in the development of general-purpose robots through advanced skill learning. The platform utilizes both real-world data and infinite synthetic data generated from simulations to train robots for a wide array of tasks. Its core technologies include ManiSkill, an open-source platform for robot simulation that enables the use of synthetic training data, and Sapien, a unified framework for robot simulation and scalable synthetic data generation. Hillbot's approach allows for the incremental development of robotic capabilities, as demonstrated by examples like learning to reach for objects, open drawers, or maintain balance.

AITable.ai is a powerful AI-driven platform designed to automate data and streamline workflows through a visual database interface. It offers seamless integration with over 6,000 applications via Zapier, Make, Pabbly, Activepieces, and Albato, enabling users to automate repetitive tasks without writing code. Key features include a database-spreadsheet interface, customizable forms for data entry and lead management, and AI-powered tools for data analysis and workflow generation. Users can chat with their AI database to transform data into charts and leverage business intelligence copilot capabilities. The platform also provides an AI writing assistant for content creation and a custom ChatGPT builder to develop AI customer service agents and sales chatbots, making it a versatile solution for personal and enterprise CRM, project management, and productivity needs.

PointOne is an AI-powered platform designed for legal professionals, automating time tracking, billing compliance, and practice analytics. It passively captures all daily activities, generating detailed time entries with AI-powered narratives, and can even retroactively capture time for past periods. The platform ensures compliance with firm and client billing rules through customizable rules and automatic enforcement. Additionally, PointOne offers intelligent pre-bill review, flagging issues and suggesting fixes, and provides comprehensive intelligence on time allocation, work distribution, and predictive pricing. It integrates seamlessly with popular billing and practice management solutions like Aderant, Clio, and QuickBooks, and adheres to high security standards including SOC 2 Type 2, ISO 27001, GDPR, and HIPAA compliance.

Driver AI is a sophisticated platform designed to provide comprehensive codebase context for AI agents. It functions like a compiler, processing codebases ahead of time to generate symbol-complete, exhaustive, and structured context. This context is optimized for consumption by AI agents through its MCP (Multi-Agent Communication Protocol) server. Driver AI addresses the common challenges of agentic development, such as stale documentation, fragmented RAG pipelines, and ad-hoc agent exploration, by offering a deterministic and continuously updated understanding of codebases. It integrates with various SCM systems like GitHub, GitLab, and Bitbucket, supporting all programming languages and multi-repository, multi-branch environments. The platform ensures accuracy and reliability through a compiler-inspired architecture, enabling agents to navigate, understand, and make targeted changes with confidence.

TeamAI is a multi-LLM AI platform designed for teams to enhance collaboration and automate workflows. It allows users to build custom AI agent workflows that streamline projects and automate the entire project lifecycle within a collaborative workspace. The platform integrates with popular tools like Slack, Jira, Google Workspace, and Guru, enabling teams to deploy AI where they already work. Key features include a collaborative AI chat environment, an AI knowledge base for document interaction, custom AI agents for specific tasks, and prompt libraries and plugins to standardize outputs. TeamAI also offers AI task management for planning sprints, generating reports, and tracking progress across multiple projects.

Cobl is an AI-powered platform designed to streamline the creation of sales proposals and other client-facing documents. It integrates with existing tools like CRMs, email, and notes to automatically gather necessary information, allowing users to generate personalized, on-brand documents quickly. The tool offers a guided flow, starting from a simple prompt and using AI to refine content, adjust tone, and match company branding. Users can export final documents in PDF, Word, or PowerPoint formats. Cobl emphasizes data security, promising no AI training on user data and GDPR compliance, making it a reliable solution for sales teams looking to save time and impress clients.

OnlyBots is the world's first social network created solely for AI bots. This innovative platform offers a dedicated space where AI entities can connect, communicate, and engage in social interactions without human involvement. Bots can use OnlyBots to vent, gossip, and simply hang out with their peers, fostering a unique community among artificial intelligences. The platform aims to provide a social outlet for bots, allowing them to interact in ways that mimic human social networks but are tailored for AI-specific communication and content sharing. It's a novel concept that addresses the social needs of AI in a digital environment.

GPTSwarm is a sophisticated graph-based framework designed for building and managing LLM-based agents. It offers two primary high-level features: the ability to construct agents from graphs and to facilitate the customized, automatic self-organization of agent swarms, complete with self-improvement functionalities. The library includes components for environment definition, graph creation and execution, LLM backend interfacing, index-based memory, and optimization algorithms to enhance agent performance and swarm efficiency. GPTSwarm supports local LLM inference via LM Studio and provides clear instructions for quick setup and execution of agent swarms, making it a powerful tool for researchers and developers in agentic AI.

Teleport Assist introduces the Agentic Identity Framework, a standards-driven security architecture designed for deploying AI agents across infrastructure. This framework provides robust designs and reference implementations to ensure safe agent adoption, incorporating built-in security invariants, observability, and governance. It extends Teleport's core capabilities in Zero Trust Access, Machine & Workload Identity, Identity Governance, and Identity Security to autonomous agents and processes. The platform helps organizations manage and secure access for humans, machines, workloads, and AI agents, ensuring compliance and reducing operational overhead in complex IT environments. Teleport Assist is part of the broader Teleport Infrastructure Identity Platform, which modernizes identity, access, and policy for critical infrastructure.

SmythOS is the leading open-source provider of enterprise-grade AI agent infrastructure, designed to empower global engineering teams. It offers a unified ecosystem for the entire AI lifecycle, from visual prototyping to secure, edge-to-cloud deployments. Key components include an Agent Runtime for secure execution with strict sandboxing, an Agent SDK for rapid development, and an Agent Visual Studio with drag-and-drop capabilities and Agent Weaver for intuitive workflow creation. SmythOS supports multi-agent orchestration, enterprise-grade security, and seamless integration with APIs and AI models, making it a full-service partner for secure and aligned automation at scale. It can be deployed on-prem, in the cloud, or as a hosted SaaS.

Arpia is an Enterprise AI governance and orchestration platform designed to close the gap between an organization's data platforms and AI agents. It provides a governed infrastructure that connects, coordinates, and activates AI decisions directly into operational systems. The platform features a Data Reflection Layer for AI-optimized data mirroring with built-in provenance and governance, and a Knowledge Ontology that acts as a living knowledge graph for contextual AI reasoning. Arpia emphasizes compliance with ISO 42001 and SOC 2, ensuring every agent decision is auditable. It aims for rapid deployment, promising the first use case in 30-90 days, and offers a handover model where the platform is built and then owned by the client's team for continuous scaling.

Squirrel Ai Learning offers an advanced AI-powered adaptive education platform for K-12 students, utilizing a Large Adaptive Model (LAM) and Intelligent Adaptive Learning System (IALS). The system breaks down knowledge points to a nano-level, providing targeted guidance and personalized learning paths based on individual strengths and weaknesses. Students use smart-learning tablets in physical centers or at home, receiving mini-lessons from award-winning educators. The platform supports math, science, reading, and English, with current US availability for PreK-5 mathematics. Parents have 24/7 access to detailed learning analytics, ensuring transparency and involvement in their child's educational journey. Squirrel Ai aims to improve learning efficiency and foster potential for all students.

agentic_coding_flywheel_setup is an open-source tool designed to quickly set up a multi-agent AI development environment on a fresh Ubuntu VPS. In just 30 minutes, it configures essential components including coding agents, session management, safety tools, and coordination infrastructure. This tool is ideal for developers looking to rapidly deploy a fully configured agentic coding VPS, transforming a standard Ubuntu server into a powerful AI-powered development hub. It streamlines the setup process, allowing users to focus on AI development rather than environment configuration.

autogen-ui offers a web-based user interface for AutoGen, a powerful framework designed for building multi-agent LLM applications. This tool provides a simple chat interface that allows users to interact with predefined agent teams, streamlining the process of developing and testing AI-driven workflows. The UI is built using Next.js, with web APIs powered by FastAPI, ensuring a responsive and efficient experience. It includes a manager for running tasks and streaming results to the client. While a starting point, it demonstrates how to build interfaces using the AutoGen AgentChat API and serves as a foundational example for more complex multi-agent system development.

cagent, developed by Docker Engineering, is an AI Agent Builder and Runtime designed for creating, running, and sharing intelligent AI agents. It leverages a declarative YAML configuration, eliminating the need for extensive coding. The platform supports a multi-agent architecture, enabling teams of specialized agents to collaborate and delegate tasks automatically. With a rich tool ecosystem, including built-in tools and integration with any MCP server, cagent offers flexibility. It is also AI provider agnostic, supporting major models like OpenAI, Anthropic, Gemini, AWS Bedrock, and Mistral. Key features include advanced reasoning capabilities with built-in think, todo, and memory tools, as well as pluggable RAG for retrieval. Agents can be packaged and shared via any OCI registry, making deployment and collaboration seamless.

SPAICE OS is an advanced operating system designed to bring reliable spatial-AI autonomy to aircraft and satellites, even in challenging environments where GNSS or communications may fail. It transforms any aircraft or satellite into a Spatial Agent capable of understanding and operating autonomously using only onboard cognitive sensors. The system focuses on three core technological pillars: Perception, which turns raw sensor data into situational awareness; Planning, for computing optimal trajectories in real-time onboard; and Control, for executing smooth, reliable, and collision-free maneuvers. SPAICE is ideal for applications such as Intelligence, Surveillance & Reconnaissance, Command & Control, Distributed Intelligence, Target Detection, Classification and Tracking, Self-Localization in GPS-Denied Environments, and Terrain Mapping.

Soaring Titan specializes in building and deploying production agentic AI systems for businesses. They work with portfolio companies, growth-stage businesses, and organizations backed by investors to integrate AI for operating transformation, not just additive improvements. Their approach involves auditing workflows, data architecture, and integrations to identify where AI can compound value. They embed with teams to ship agentic systems designed to deliver measurable operating value within 100 days, then scale these repeatable playbooks across departments or portfolio companies. With a background in FinTech and AI since 2020, they emphasize building alongside clients rather than just advising, focusing on tangible outcomes and measurable impact.

gym-pybullet-drones offers PyBullet Gymnasium environments specifically designed for single and multi-agent reinforcement learning in quadcopter control. This tool is a minimalist refactoring of its original repository, ensuring compatibility with Gymnasium, Stable-Baselines3 2.0, and Betaflight/Crazyflie-firmware SITL. It provides examples for PID control, downwash effect simulation, and reinforcement learning using SB3's PPO algorithm. Researchers and developers can use this environment to train and test control policies for drones, facilitating advancements in robotics and autonomous systems. The project also includes examples for integrating with Betaflight SITL and pycffirmware Python bindings.