Diff Sandbox AI Agent

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

Dust is an AI agent OS that deploys, orchestrates, and governs agents across departments, linking to knowledge bases, productivity tools, and data silos. It handles reporting, ticket routing, code review, onboarding, and contract review while meeting SOC 2, GDPR, and HIPAA.

Buda AI is a cloud-native workspace where teams build, run, and coordinate specialized AI agents for coding, sales, marketing, and operations. It centralizes agent-driven workflows with automation, integrations, and a marketplace to reduce manual handoffs and scale routine tasks.

Simulation-driven platform that evaluates and monitors AI agents across modalities with realistic multi-turn scenarios, CI/CD-integrated automated tests, configurable safety/policy guardrails, and analytics for failures, hallucinations, and performance to ensure production readiness.

GBOX provides browser, Android, and Linux sandboxes plus RL environments for training, testing, and reproducible evaluation of agents. It includes a UI-grounding model for interface automation, iterative prototyping, debugging tools, and developer documentation.

Verdent AI is a development environment for agentic coding that enables parallel execution of multiple agents in isolated workspaces. It streamlines workflow with context-switching, built-in clarification tools, and VS Code integration for faster, production-ready feature delivery.

Google Antigravity is an IDE for developers featuring tab autocompletion, natural language code commands, and configurable agents that monitor tasks. It offers cross-surface synchronization and a unified mission control view for managing multiple agents.

happycapy runs AI agents and skill modules directly in the browser, offering GUI and CLI interfaces, a skills store, browser automation, private sandboxed execution, live monitoring and action review, and developer extensibility for custom skills and workflows.

CodeAnt AI automates pull‑request review, static analysis, and governance, reducing review cycles by up to 80%. It scans codebases for SAST, SCA, secrets, IaC, and SBOM compliance, enforces test coverage and linting, delivering velocity and defect metrics IDEs, Git, CI/CD.

QA.tech automates end‑to‑end tests across web, mobile, and APIs with AI agents that simulate real users, reducing flakiness, delivering instant CI/CD feedback, logging detailed failures, and automatically updating test cases without infrastructure setup.

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

OpenFang.sh is an open-source agent operating system that orchestrates autonomous AI agents and capability packages across macOS, Linux, and Windows. It provides a secure, sandboxed runtime with built-in tools for tasks like research, monitoring, and automation, all managed through a native desktop

JanitorAI is a Character AI alternative without filters for chatting with various AI characters including NSFW AI friends. It has numerous chatbots with diverse themes, personalities and genres to explore.

Windsurf is an AI coding tool that enhances developer workflows with features like Cascade for code understanding, real-time error detection, integrated IDE plugins, and collaboration tools, enabling efficient coding, debugging, and project management.

Plandex is an open‑source terminal AI coding agent that manages large projects, offering diff‑review sandboxes, auto and step‑by‑step modes, multi‑file staging, rollback, debugging, and 2 million‑token context across models from Anthropic, OpenAI, and Google.

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.

Donovan provides a no‑code Agent Factory that builds and connects AI agents for mission‑critical government and defense workflows. It evaluates model performance, runs on classified, air‑gapped Kubernetes environments, and offers traceable reasoning with defense‑aligned guardrails.

CrewAI is an advanced open source AI agent framework that simplifies creation of complex automations using pre-built models and agents, or custom development with open source tools. Engaged community for sharing and support.

8080.ai is an AI development platform for building, orchestrating, and scaling multi-agent workflows that automate project planning, task decomposition, and sprint tracking. It provides a production-ready microservices architecture with Kubernetes deployment, a browser-based VS Code editor, and fron

Think Diffusion is an AI art tool that brings pro-level AI art capabilities to anyone with a browser in just a few clicks, providing top-tier models and ControlNet, and allowing for easy launch of additional virtual machines for simultaneous use.

SmythOS is an open‑source Agent Operating System that manages the AI agent lifecycle—from design to production—via visual studio, SDK, CLI, and secure sandboxed runtime. It supports multi‑platform deployment, orchestration, and enterprise‑grade security.

Texsandbox is a web-based AI LaTeX editor that simplifies document creation by converting natural language prompts into LaTeX drafts. It supports multilingual content, extensive TeX Live packages, and streamlines package management for enhanced usability across devices.

Upload a room photo, select style themes, and instantly generate photorealistic renders. Designers can edit furniture placement, textures, and colors. Virtual staging, clutter removal, and real‑estate before‑after visuals are included, with a sandbox for real‑time experimentation.

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.

Bind AI IDE is a code editor that runs 15+ AI models for automated generation and refinement of Python, React, Next.js, and Node.js. It offers GitHub sync, instant preview, Vercel deployment, and AI‑driven website building for rapid prototyping.

PromptSandbox.io is an OpenAI playground for developers and researchers to test, experiment and refine their AI models with pre-trained GPT models, a simple interface, and a community forum.

Refact.ai is an autonomous AI agent for IDEs (VS Code, JetBrains, Neovim) that analyzes entire projects, generates code, completes, debugs, and runs end‑to‑end tasks. It supports multiple LLMs, on‑prem or cloud hosting, and builds a knowledge base from interactions.

Sakura FM is a versatile app offering a combination interactive storytelling. Dive into diverse categories, explore AI virtual characters, and engage in text adventures. Whether it's romance, horror, or anime-themed experiences, Sakura FM provides a range of characters.

SimplAI is an agentic AI platform that allows users to create and deploy AI applications with minimal technical expertise. It features an intuitive interface, secure deployment options, and supports various industries for rapid prototyping and monitoring.

Canditech uses AI to generate role‑specific skill assessments from job descriptions, scoring technical, soft, and cognitive abilities. It offers anti‑cheating safeguards, video interviews, and ATS integration, enhancing candidate experience and hiring decisions across departments.

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.

Sudowrite is an AI writing tool that generates and suggests text for various writing tasks using GPT-3.

DFIRST AI is a marketing platform that lets users build custom campaigns via drag‑and‑drop, using AI agents for research, copywriting, visual creation, and data extraction. It integrates tools like Claude, Stable Diffusion, and SEMrush for competitive intelligence and real‑time optimization.

Seeko offers full‑cycle AI integration for mid‑market teams: an audit identifies high‑leverage automation, a sprint‑based program delivers production‑ready AI on the Clutch platform, and managed operations ensure ongoing optimization and compliance.

AI-powered chat tool that allows users to interact with a virtual girlfriend or boyfriend. Choose from over 5000 characters.

HammerAI is a private and free AI chat platform for creating and interacting with AI characters in role-play scenarios. The AI model runs locally in the browser for free, ensuring user privacy and security.

Frederick AI offers integrated coding, browser, and background agents that generate web apps from natural language, automate website interactions, schedule repetitive tasks, and share context in a workspace—helping startup teams prototype quickly and run continuous workflows.

Devin automates code generation, review, and fixes using AI agents. It schedules tasks, tracks dependency graphs, and integrates with CI/CD pipelines, boosting productivity and consistency across diverse codebases for engineering teams and organizations.

DreamGen is an uncensored role-play AI chat platform, offering AI NSFW creative freedom and extensive world-building capabilities for various fantacies with virtual AI characters including anime, realistic and more.

Scout is an AI‑agent platform that builds, launches, and optimizes sales agents for meeting prep, RFP drafting, and sales engineering. It integrates with Salesforce, Outreach, Slack, Notion, Google Suite, and pulls from documentation and custom databases for rapid, no‑code deployment.

The AI content checking tool uses image recognition technology with 93% accuracy rate to classify potentially indecent content and offers camera and blur protection. It can be accessed through GitHub and has a mobile demo available.

Maestro is an AI agent command center that orchestrates autonomous coding agents across desktop, CLI, and mobile, supporting multi-agent workflows, scheduling, Git-aware editing, remote control, real-time monitoring, and JSON/log outputs for automation.

Pi.dev is a terminal-based coding agent for developers and teams, offering TUI, RPC/SDK modes, extensible TypeScript modules and packages, multi-provider model authentication, session/context management, RAG/memory primitives, and CLI tooling for automation and integration.

OpenAI Codex CLI is a terminal-based, open-source coding agent that uses natural language to automate development tasks like code generation, testing, refactoring, and codebase understanding, with secure sandboxed execution and Git integration.

Sensei AI delivers real‑time, one‑second AI answers during live video interviews. It ingests resumes and personal stories to provide context‑aware responses tailored to job roles, integrates with Zoom, Teams, Meet, and supports over 30 languages with custom tone settings.

Raycast is an AI tool that can help developers write code faster, access a new layer of context, and accelerate tasks without any coding required.

Final Round AI is a desktop assistant that offers stealth, real‑time prompts during live interviews on Zoom, Google Meet, and coding platforms. It generates role‑specific STAR responses, provides mock practice, and delivers performance reports with actionable insights.

Betafish.j is an AI chess tool that allows users to play as white against an AI opponent with adjustable difficulty levels. It supports FEN, taking back moves and viewing source code.

Tracecat is an open‑source AI automation platform for security teams, enabling workflow automation across 200+ connectors. It offers sandboxed action execution, advanced control flow, human approval gates, and case management for structured incident response.

pre.dev automates end‑to‑end software development. It accepts ideas or repositories, generates architecture, writes and verifies code, then pushes to a feature branch. Integrations with GitHub, Slack, Jira via OAuth run agents in secure, multi‑stack sandboxes.