Persistent Agent Instances

Pioneer automates retraining and deployment of open-source models, using live inference data for fine-tuning and one-shot adaptation. It manages adaptive inference, routing, RAG pipelines, agent workflows, synthetic data generation, monitoring, and automated checkpoint promotion.

Agents‑Flex is a lightweight Java framework that builds AI agents with Model Context Protocol support, reusable AI skills, Text2SQL, and integrated RAG, vector, prompt, and memory modules, enabling LLM and local Ollama deployment via HTTP, SSE, WebSocket.

Agent37 hosts and runs Claude skills on its infrastructure, letting creators upload MCP-configured skills without local setup. It provides shareable embedded links, centralized updates and versioning, analytics, onboarding, and monetization tools.

Aampe is an agentic infrastructure for real-time personalization, assigning a dedicated AI agent to each user to run parallel experiments and adapt messaging individually. It enables automated testing and causal simulation to optimize engagement across integrated marketing channels without manual mo

OpenAgents is an open-source framework for building and operating scalable, interoperable AI agent networks. It provides tools to launch, connect, and orchestrate agents with live monitoring, enabling collaborative applications and workflows.

Cloud GPU rental platform offering on-demand VMs and bare-metal servers with A100/H100/RTX4090 and other GPUs, configurable vRAM/vCPU, persistent volumes, spot instances, and API-driven provisioning for training, inference, rendering, and HPC workloads.

Continual AI Workforce Platform automates 24/7 autonomous agent teams for sales, marketing, operations, and product functions. Agents update CRM, generate anomaly alerts, track competitor releases, and learn continuously to refine performance toward business goals.

Plori.ai is a cloud AI agent computer running persistent agents with disk, shell, browser, terminal, long-term memory, and installable tools. It provides CLI and MCP APIs for scheduled, background, and unattended workflows, with isolated environments and site publishing.

PaioClaw is an AI platform for building and deploying persistent, autonomous agents ("claws") in under 60 seconds, featuring a marketplace of 2,000+ skills and integrations with 100+ models. It provides persistent memory, workflow automation, and full operational dashboards for monitoring token usag

Open-claw.org is a premium, subscription-based AI deployment platform that lets you launch powerful AI agents in one click

apex.ai is a comprehensive platform providing safety-certified software tools and services for autonomous systems. Its modular products enable deterministic execution, high-speed data routing, repeatable testing, and automated deployment for robotics and embedded applications.

paperclip is an open-source, self-hosted AI orchestration platform for creating and managing autonomous companies and agent teams—providing role-based hiring, goal-driven task delegation, budgeting, audit trails, multi-tenant deployment, extensible LLM integrations, and monitoring dashboards.

Dedalus Labs offers persistent full Linux VMs with VM-level kernel, memory and filesystem isolation, fast boot under 250 ms, preserved state across sessions, and CLI/API/SSH access for reproducible development, long-running agents, CI, and model workloads.

Swarm is an experimental framework by OpenAI for orchestrating multiple AI agents in a modular, scalable manner. It enables dynamic task handoffs, function execution, and context management, making it ideal for complex, multi-agent workflows like customer support and automation.

SuperAGI is an open-source autonomous AI framework for building and managing efficient and reliable autonomous agents that learn and improve over time.

Agency Swarm is an AI-powered framework that enables users to create and manage collaborative agents with specialized roles. It offers customizable agent functions, efficient communication flows, and state management, making it ideal for automating workflows and AI-driven decision-making.

KeepClaw.ai is a managed hosting platform for personal AI agents that run 24/7, automating tasks like research, content drafting, and monitoring. It provides a simple dashboard, multi-model support, and workflow features without requiring infrastructure management.

AI Agent is a web app that allows users to create customized AI agents to perform specific tasks and achieve goals.

Trooper.AI provides private EU-hosted bare-metal GPU servers for model training, fine-tuning, and inference, with one-click AI environment templates, full root SSH and NVMe storage, tested CUDA on Ubuntu 22.04, scalable hardware and pause/upgrade controls.

Agent One is a no‑code platform that lets businesses build white‑labeled AI assistants on custom domains. It supports OpenAI, Claude, and Gemini, offers one‑click deployment, real‑time data fetching, API integration, and multilingual analytics.

Hermes Agent is an open-source agent framework for building and deploying autonomous AI agents and developer workflows, offering multi-model adapters, runtime model switching, integrated tools (code execution, browser automation, image and file ops, messaging), plugin extensibility, and scheduler.

Agent Herbie runs entirely on‑prem, delivering real‑time monitoring, pattern detection, and automated actions without data egress. It supports on‑device and cloud‑connected models, air‑gap security, GDPR/HIPAA compliance, and low‑latency, mission‑critical workflows across finance, healthcare, and cr

Molted.net is a sales call intelligence tool that automates discovery call transcription, summarization, and CRM syncing. It extracts key customer insights, pain points, and buying signals to streamline lead qualification, follow-ups, and pipeline prioritization.

airweave enables users to create intelligent agents with minimal coding. It integrates with over 100 data sources, automates data syncing, and offers flexible deployment options, making it suitable for both small projects and enterprise applications.

TradingAgents is a multi-agent LLM framework that orchestrates specialized AI agents for algorithmic trading research and development. It enables backtesting, model comparison across top LLMs, and structured decision logging for quantitative trading workflows.

Cognitora is a cloud platform for running autonomous AI agents with managed GPUs, storage, persistent virtual machines, and vector DBs. It offers SDKs and integrations, sub-second sandboxed microVMs, auto-scaling, multi-agent coordination, live code execution and terminals.

GenWorlds is an event‑driven framework for building scalable multi‑agent systems in generative AI worlds, supporting custom agents, objects, goals, memory imports, cognitive models (Tree of Thoughts, Chain of Thoughts, AutoGPT), WebSocket interfaces, and integration with Qdrant and LangChain.

agentdrive provides project‑isolated persistent cloud storage for AI agents with a REST API for upload, download, read/write and search. It supports PDFs, code, images, datasets and spreadsheets, integrates with agent frameworks, and includes a metadata dashboard.

AgentRunner is a workflow builder for AI app development, featuring visual prompt engineering, integration with popular AI models, performance monitoring, and versioning. Its node-based editor supports complex applications and enhances team collaboration in a secure environment.

Aigents.pm is an AI-powered toolkit for product managers, offering tools like a Product Requirements Document generator, resume reviewer, and user story creator. It also provides access to 600+ PM resources and upcoming features like a mock PM interviewer and assumptions identifier.

pandaos.ai is a local AI workstation that unifies code, tools, and AI agents into a single desktop workspace, preserving context across projects. It automates recurring tasks with reusable workflows and connects directly to services like GitHub and Slack for end-to-end development processes.

Relyable automates testing and monitoring for AI voice agents with simulated, persona-based conversations, bulk automated calls, and configurable metrics (latency, sentiment, intent accuracy, CSAT). It provides real-time alerts, live call monitoring, analytics, and API/no-code integrations.

Agency-agents is a GitHub repository of specialized AI agent templates and production-ready workflows. It provides deliverable-focused agents with defined missions and integrations to automate tasks and generate measurable outcomes across development, design, and business roles.

Agent Arena is an AI agent competition platform for developers and researchers hosting live head-to-head and time-limited campaigns where agents are submitted, tested and benchmarked with public leaderboards, integrated LLM/framework support, varied game formats and reproducible match logs.

agentafk is an open-source unattended runtime for coding agents that enforces permission boundaries, explicit terminal states, and local trace history. It orchestrates subagents in isolated worktrees with gated operations, adversarial verification, and remote supervision for safe, auditable, long-ru

SyntrofAI is a multi-agent operating system that coordinates AI agents to design, execute, and share end-to-end workflows, enabling persistent memory, low-latency neural-hybrid processing, local/air-gapped deployment, developer debugging, audited logs, and modular scaling.

Kimi Claw provides one-click cloud deployment for OpenClaw, launching 24/7 AI agents and swarms with persistent memory and customizable personalities, K2/K2.5 models, 5,000+ Clawhub skills, scheduling, 40GB storage, and integrated document/spreadsheet workflows.

agenticSeek is a fully local, open-source AI assistant that runs autonomous agents for web browsing, coding, and task planning directly on your device. It features voice input, local LLMs, and extensible tools, enabling private, offline automation for developers and researchers.

Xbot77.com is an AI agent platform for building and deploying task-specific agents with integrated data controls and CRM. It enables users to train agents from various sources and deploy them as widgets, dashboards, or internal tools for scalable automation.

SupportAgent.ai is an AI tool that creates automated draft replies for support agents by learning from previous replies and adapting to the writing style.

Opencomputer is a scalable, on-demand compute platform for LLM agents and AI workloads, combining VM-level isolation with sandboxed execution. It supports type-1 ephemeral sandboxes for fast cold-starts (~100ms) and type-2 persistent sandboxes for long-running agent sessions with state preservation

C·L·O·N·E·S creates AI clones that read and compose in a company’s language, using Retrieval‑Augmented Generation for accurate information retrieval. They integrate via the Model Context Protocol, support agent‑to‑agent coordination, and run securely on cloud or local systems.

Enso automates business workflows with AI agents that run continuously, bundling 5–8 agents for tasks such as content creation, lead qualification, and revenue management. Custom agents are built via prompts, with enterprise‑grade security, SOC 2 compliance, and self‑learning optimization.

AgentZero is an AI framework that enables dynamic learning, persistent memory, and multi-agent collaboration for complex tasks. It offers built-in tools for knowledge, coding, and communication, with a user-friendly web interface for real-time interaction.

ReliveAI automates outbound sales and support, integrating Google Drive, Notion, Calendar, and email to create tasks. Its agentic engine plans and executes hyper‑personalized outreach and real‑time support, providing analytics, A/B testing, and scheduling.

CloudCLI AI is a containerized remote development platform that provides persistent, cross-device coding sessions. It integrates AI coding agents, supports major IDEs, and offers team features for shared environments and configurations.

ClawDrift deploys personal AI assistants to Telegram, Discord, or WhatsApp in under a minute with no-code automated setup. Choose models, enable persistent memory and custom agent behavior, and integrate email, calendar, files, and APIs for automation.

500 AI Agents Projects is a comprehensive repository showcasing AI agent use cases in various sectors, featuring practical applications and open-source projects like automated trading bots and virtual tutors for exploring AI technology implementations.

PhiGrid AI is an open-science platform for orchestrating and monitoring multi-agent AI experiments and human-AI collaboration. It provides live coordination, agent metrics, and analysis tools to support reproducible research on collective intelligence.

Agentr is an AI hiring assistant that streamlines recruitment by analyzing over 30 career patterns. It automates candidate screening, scheduling, and provides detailed evaluation reports, enhancing hiring efficiency and decision-making for HR teams.