With over 14,000 GitHub stars and 41 releases since its May 2026 launch, Prime Agent delivers a fundamentally different approach to AI coding agents by treating the agent's own operating environment as programmable state that improves through use. The Recursive Language Model architecture provides the model exactly one tool — a persistent IPython kernel — where file operations, shell commands, subagent delegation via rlm() function calls, and context management all happen through code rather than rigid tool-calling schemas. Subagents launch as independent sessions with their own model, kernel, and history, communicating results through agent_message.send() without blocking the parent. The Continual Harness stores supplemental prompts, memories, skill descriptions, and reusable subagent specifications as durable state that the /refine command updates through small, evidence-backed edits with full rollback by ID. Daemon-backed sessions keep running when the terminal disconnects, with automatic context compaction summarizing older messages while preserving recent state. The TUI provides an Agent View for monitoring, switching between, and steering multiple live sessions simultaneously. Autonomous mode operates within configurable turn, token, and time budgets with user-defined quality gates. Persistent goals, heartbeats, and scheduled prompts maintain continuity across terminal sessions. Compatible with Anthropic Claude, OpenAI, Google Gemini, local models via Ollama or vLLM, and Prime Inference endpoints. Install via a single curl command on Linux or macOS. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With 83,000+ GitHub stars and $18.8M in Series A funding, OpenHands delivers the leading open-source platform for AI coding agents that scored 68.4% on SWE-bench Verified with Claude Opus 4.6, outperforming Devin 2.0's publicly reported 45.8%. The Agent Canvas web UI organizes work into persistent conversations where agents edit files, run shell commands, browse the web, and execute multi-step development tasks inside isolated Docker sandbox containers. The observe-plan-act loop drives agent behavior: the Python controller manages LLM abstraction via LiteLLM routing to 100+ providers including OpenAI, Anthropic, Google, DeepSeek, Qwen, Llama, and local Ollama models. Built-in skills for code review, Docker management, PRD generation, repo-rules enforcement, release notes, and test running attach to conversations automatically via auto-discovery or trigger-based activation. The Automations system schedules recurring agent tasks with configurable templates for CI workflows, dependency updates, and documentation generation. MCP server integration enables agents to access external tools and data sources. The REST API powers an OpenAI-compatible endpoint for connecting agents to chat UIs, IDEs, and voice platforms. GitHub, GitLab, Slack, and Jira integrations enable pull request reviews, issue resolution, and team notifications. The SDK provides Python and REST APIs for embedding agents in custom tools with local or cloud execution, custom agent behaviors, and Kubernetes deployment. On RepoCloud, deploy OpenHands on a dedicated VPS with Docker socket access, persistent project storage, root SSH access, and complete control over your AI development infrastructure, all under the MIT license.

QM is Y Combinator's internal multiplayer agent infrastructure that shifts AI agents from personal assistants to shared company operating layer. The headless TypeScript core runs on Node.js with Fastify handling HTTP, Slack integration via Bolt, and a web UI built with Vite and Lit. PostgreSQL stores sessions, memory, queue state, and audit logs. Every person and every Slack channel gets an isolated sandbox with its own durable file system, installed tools that persist across runs, private memory, keychain view, permissions, and background crons. The harness-agnostic architecture routes agent tasks through Pi, OpenCode, Codex, or Claude Code without vendor lock-in, with production implementations swapping via a single wiring file. Three org-level security postures gate execution: Strict requires human approval for every tool call, Auto applies automated content screening, and Dangerous removes all pauses. Skills are scope-owned and shareable by grant, with admin-gated promotion to the entire organization and skill packs importable from Git repositories. The web apps feature lets agents spin up custom internal applications published to specific users. The qm CLI bootstraps operator-owned deployment directories with digest-pinned release images, infrastructure rendering, secret management, and live verification checks for Docker, Fly.io, or AWS ECS Fargate targets. On RepoCloud, deploy QM on a dedicated VPS with PostgreSQL persistence, Docker socket access, root SSH access, and complete control over your multiplayer agent infrastructure, all under the MIT license.

OpenRouter's most-used application by token volume — over 17 trillion tokens processed — Hermes Agent is an open-source autonomous agent built by Nous Research that lives on your server and gets more capable every day. Define a goal in natural language and Hermes plans sub-tasks, executes them through tool integrations, observes results, handles errors, and refines until the job is done or it genuinely needs your input. Persistent memory with full-text search and LLM summarization lets it recall context across sessions, and an agent-created skills system self-improves after complex tasks. A messaging gateway connects Telegram, Discord, Slack, WhatsApp, Signal, and 16 more platforms with cross-channel conversation continuity. A built-in cron scheduler runs daily reports, nightly backups, and weekly audits unattended. Subagent spawning parallelizes workstreams, and six terminal backends — local, Docker, SSH, Singularity, Modal, and Daytona — fit any infrastructure. Works with any LLM provider: Nous Portal, OpenRouter for 400+ models from 70+ providers, OpenAI, Anthropic, or your own endpoint. The API key you supply powers all LLM calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

A personal AI assistant that remembers what it learns and reaches you wherever you are — OpenClaw is an open-source agent gateway built by the OpenClaw Foundation with 247,000+ GitHub stars. It connects to 200+ LLM models through providers like Anthropic, OpenRouter, and OpenAI, and meets you on 21+ messaging channels: Telegram, Slack, Discord, WhatsApp, Signal, iMessage, Matrix, and more. Persistent memory with full-text search lets the agent recall context across sessions, and a self-improving skills system means it gets more capable the longer it runs. Voice wake words and talk mode enable hands-free interaction on macOS, iOS, and Android. A live canvas provides an agent-driven visual workspace. Built-in browser automation, cron scheduling for unattended tasks, and subagent spawning for parallel workstreams round out the toolset. The gateway architecture keeps all sessions, credentials, and conversation history on your own server — nothing transits a third-party cloud unless you choose to connect one. The API key you provide for your chosen LLM provider powers the underlying calls; billing goes through your own account. Running on a dedicated VPS with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

With 15,500 GitHub stars and over 1,100 forks, Plandex delivers a terminal-based AI coding agent purpose-built for the complex, multi-file tasks that overwhelm single-file AI assistants. The Go-powered server maintains a cumulative diff review sandbox that quarantines all AI-generated changes from your project files until you explicitly approve them — enabling 20-file refactors where you cherry-pick good changes and reject bad ones without touching git. A 2M token effective context window loads only what each step requires, while tree-sitter project maps index repositories exceeding 20M tokens across 30+ programming languages, providing structural awareness of class hierarchies, function signatures, and import graphs without burning tokens on full file content. The configurable model pack system assigns different models to different roles — Claude for planning, GPT for coding, Gemini for summarization — supporting Anthropic, OpenAI, Google, OpenRouter, Azure OpenAI, AWS Bedrock, DeepSeek, Perplexity, and Ollama for local models. Full auto mode handles end-to-end autonomous workflows including high-level planning, context loading, implementation, terminal command execution, and automated debugging of both terminal and browser applications. The interactive REPL provides fuzzy auto-complete, version-controlled sandbox branching, rewind to any previous point, and Git integration for commit message generation. The Plandex Server exposes 60+ REST API endpoints for programmatic orchestration across organizations, projects, plans, and branches. Deploy via Docker Compose for self-hosted operation with your own API keys. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenCode Manager is a mobile-first command center for AI coding agents. Install the PWA on your phone or tablet and you get real-time streaming chat, multi-repository Git operations, and scheduled automation right in your pocket. Git integration handles SSH-authenticated repo cloning, worktree management, unified diffs, and branch operations across all your projects in one dashboard. Chat with coding agents through Server-Sent Events streaming that supports slash commands, @-mentions for files, Plan and Build modes, and Mermaid diagram rendering for architecture discussions. Schedule reusable prompts to run against any repository on intervals or cron expressions, with each run tracking history and linking to sessions so you can pick up exactly where automation left off. MCP server configuration adds local and remote HTTP servers with OAuth support, plugging into the broader Model Context Protocol ecosystem. A dedicated assistant workspace provides an isolated AI environment with auto-provisioned skills for managing schedules, notifications, and settings. Multiple AI providers are supported including Anthropic, GitHub Copilot, and OpenAI-compatible services, each configurable with custom system prompts and granular tool permissions. Push notifications alert you to session events, agent questions, errors, and task completions across all managed repositories.

Agent Zero equips large language models with a persistent virtual Linux desktop, letting autonomous AI agents write code, research the web, and execute multistep tasks without supervision. Operating within an isolated container, the system opens an interactive XFCE graphical desktop in your browser canvas where the agent interacts with GUI applications like Blender and terminal sessions directly. Its embedded browser features interactive annotation tools, letting you click web elements to inspect stylesheet hierarchies, extract component markup, or submit automated testing instructions. You can cowork on spreadsheets, presentations, and Markdown specifications in real time alongside the agent, preserving document revisions through snapshot time travel. A multi-tier memory architecture backed by FAISS vector indexing and SearXNG web discovery retains problem-solving context across projects, while hierarchical delegation spins up specialized subordinate agents to parallelize complex engineering audits. The platform connects seamlessly to commercial LLMs via OpenAI, Anthropic, or OpenRouter, runs private local models through Ollama, and integrates custom toolkits via the Model Context Protocol and community Plugin Hub. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

PilotDeck introduces a WorkSpace-first architecture where each project receives its own isolated file system, memory store, and skill set, preventing context bleed between parallel tasks. White-box memory makes generation, extraction, storage, and retrieval fully visible, letting users audit, edit, pin, and rollback individual entries when the agent misremembers, while Dream Mode consolidates memory fragments during idle windows. Smart Routing auto-detects task difficulty and sends complex calls to flagship models like Claude Sonnet or GPT-4o while routing simple requests to lighter models, achieving claimed 70% cost savings through on-device and cloud co-orchestration with TokenSaver tiering and sticky session binding. Always-on background execution keeps agents running after the user closes the browser, with Discovery and Cron-based scheduling for recurring workflows. The platform natively supports the Model Context Protocol for first-class MCP server integration, community skills via ClawHub on npm, lifecycle hooks intercepting PreToolUse and UserPromptSubmit events, and custom memory store providers. Multi-provider fallback automatically switches to backup providers on timeout or rate-limit errors. The WebSocket and HTTP gateway serves web, CLI, desktop, and Feishu IM channels from a single configuration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

While ordinary chatbots sit idle between prompts, Agenvoy runs around the clock on your own machine, turning one-sentence requests into finished research, files, and reports. Say what you need once and it builds the missing tool itself, tests that tool inside a sandbox, saves it, and reaches for it again the next time a similar job appears. Recurring work becomes a schedule in plain words; a morning briefing, a watched folder, or a weekly report then runs unattended, and a long task interrupted mid-run resumes from its checkpoint instead of starting over. Ask questions about your own files and it searches them like a private archive, transcribing audio and video into text it can quote back to you. Each task is routed to the model tier that fits it, a light model for lookups and a heavy one for hard reasoning, across subscription logins, API keys from eleven providers, or a local Ollama that never phones home. Commands run in a sandbox with the network off until you approve a call, sensitive paths ask before they open, and credentials wait in the system keychain instead of the chat history. You drive it from the terminal, the browser dashboard, or Telegram and Discord when you are away from the desk, and it lends its sandboxed tools to Claude Code and Codex over MCP. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

II-Agent is an autonomous AI agent platform that ranked first on the GAIA benchmark by combining multi-step task planning with a full-stack execution environment spanning research, coding, browsing, and content creation. The platform runs a React frontend on port 1420 backed by FastAPI on port 8000, with PostgreSQL for persistence, Redis for task queuing, and MinIO for S3-compatible file storage, all deployable via Docker Compose. Users switch between Anthropic Claude, OpenAI GPT, and Google Gemini mid-conversation using bring-your-own-key authentication. Task domains include deep research with source triangulation, website and mobile app generation from prompts, storybook creation with illustrations, video and image generation via Google Veo and Imagen, presentation building with live collaborative editing, and document manipulation covering PDF extraction, Excel formulas, Word editing, and PowerPoint creation. Built-in connectors integrate Gmail, Slack, GitHub, Notion, Google Calendar, Discord, Dropbox, and Canva for workflow automation. A sandboxed code interpreter runs Python while browser automation with vision capabilities handles web interactions. Custom skills let teams package and reuse workflows. Context management handles up to 120,000 tokens with intelligent window sizing. 3,400+ GitHub stars. Apache-2.0 licensed.

Codeman is a self-hosted mission control for AI coding agents that runs Claude Code, Codex, OpenCode, Gemini, Copilot, and five more agent CLIs in persistent sessions you can watch and steer from any browser, phone included. Sessions live in tmux, so agents survive server restarts, network drops, and laptop sleep, with full scrollback replay when you return. Run up to twenty sessions as tabs or in a six-up tile grid, each streaming its real terminal with token and cost tracking, and tabs that blink when an agent goes idle or needs an answer. Idle detection re-prompts stalled agents, and when a subscription usage limit hits, Codeman parses the reset time, waits it out, and resumes the run unattended. Subagents appear as floating live windows tethered to their parent session, with real-time transcripts, token counts, and status badges. Agents can drive Codeman too, through a bundled skill, CLI verbs, and an MCP server that let one agent start, prompt, and collect answers from workers in other CLIs. Run a project in an isolated Docker container or on another machine over SSH, preview agent-created files in the browser, and reach everything from your phone with QR login and push notifications, or over Tailscale with a real certificate. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Kortix Suna is an AI management system where autonomous agents run on isolated Linux sandbox computers, producing finished deliverables that humans review through a change request workflow before anything merges. With 20,000+ stars, it positions itself against Claude Cowork and ChatGPT Work by storing every agent persona, skill, memory artifact, and connector in a git repository: versioned, diffable, and shared across an organization. Each session launches a dedicated sandbox with full terminal access, Playwright-controlled Chromium, writable filesystem, and internet connectivity. Over 3,000 app connectors are available through MCP, OpenAPI, GraphQL, and raw HTTP, with credentials brokered server-side so tokens never enter the sandbox. Skills (reusable markdown-plus-script packages encoding company workflows) load automatically into every session, compounding institutional knowledge over time. Bring-your-own-key model routing through LiteLLM connects to OpenAI, Anthropic, Google, Mistral, or local models without vendor lock-in. The deployment runs as a single Docker Compose stack bundling the Next.js frontend, FastAPI backend, Supabase, Redis, and Caddy with automatic TLS certificates. Enterprise features include SAML/OIDC SSO, SCIM provisioning, RBAC, and audit logging. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Elastic License 2.0.

PandaDOS is a self-hosted control plane that turns Claude Code and Codex into long-running coding agents you direct through an issue queue from any browser, instead of babysitting a terminal. You file an issue with the outcome and acceptance criteria, and PandaDOS clarifies missing requirements, plans the work, picks the agent, and drives implementation, verification, and delivery in stages. Three approval levels, cautious, balanced, and automatic, decide which actions proceed alone; safe reversible steps continue automatically while destructive, irreversible, production, or secret-related decisions always come back to you. The browser workspace shows the real agent conversation, a native terminal, project files, Git history and diffs, and an execution summary, so you can inspect or intervene at any moment from a phone or laptop. Agents run on local or SSH-connected executor machines inside tmux sessions, and work sharing one repository is serialized while independent projects proceed in parallel without conflicting edits. Modules keep one assigned agent and durable project knowledge, so context from finished issues carries into the next task instead of evaporating when a chat ends. Teams can sign in through Feishu, ask the project manager questions in chat, and receive subscription notifications and approval cards on their phones. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache-2.0 licensed.

With over 2,700 GitHub stars, Auto Company is the first open-source framework that runs a fully autonomous AI company 24/7 — 14 specialized agents modeled after Jeff Bezos (CEO strategy), Werner Vogels (CTO architecture), Charlie Munger (critical analysis), DHH (full-stack engineering), Kelsey Hightower (DevOps), Seth Godin (marketing), and eight more domain experts collaborate through dynamic squad formation to ideate products, write code, deploy infrastructure, and execute marketing campaigns without human intervention. The five-layer architecture separates execution, orchestration, cognition, workflow routing, and observability, while the consensus memory pattern uses a single markdown file as a relay baton between cycles — no vector databases, no Redis, no embeddings required. A bash loop invokes Claude Code or OpenAI Codex CLI every 30 seconds, each cycle selecting 2-5 agents from the 14-person pool based on task context. Over 30 reusable skills handle specialized tasks from frontend design to competitive analysis and deployment automation. Circuit breakers trigger cooldown after consecutive errors, rate-limit detection auto-sleeps on API throttling, and sandbox rollback protects against destructive changes. The Python-powered web dashboard displays real-time cycle status, cost tracking per cycle averaging under $2, and agent activity visualization, with CLI control via make start, stop, monitor, pause, and resume. Supports macOS via launchd, Windows via WSL with systemd, and native Linux deployment. The npx create-auto-co command scaffolds a new AI company in seconds. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Hand a task to an AI teammate the way you would hand it to a person: describe the work, then follow along and step in when it matters. UseAgent runs Claude Code, Codex, OpenCode, and Pi inside isolated Linux workspaces, each with your repositories, a terminal, a real browser, and a desktop you can open and take over. Start work from the web app, by mentioning an agent in Slack, or through the API, and get pull requests, documents, spreadsheets, presentations, and research back as usable files. Four engines share one thread and one event format, so you can compare how Claude Code and Codex each handled the same bug, then switch engines on the next reply without losing history, files, or memory. Risky operations pause at approval gates, and a decision resumes the run with a one-shot, argument-bound capability instead of blanket trust. Every step, tool call, and approval is stored as an append-only event log in your Postgres, replayable after the fact and durable across restarts mid-task. Teach the workspace your procedures by importing versioned skills from GitHub and pinning playbooks to tasks, while knowledge pages and optional team memory stay beside the work, inspectable and correctable. Recurring tasks run on schedules with full history. Provider keys stay on your server and never enter an agent sandbox. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. AGPL-3.0 licensed.

OpenAgentCore puts Codex, Claude Code, and MiniMax Code behind one self-hosted Agents API, so your applications start agent sessions through the official OpenAI SDK while the work runs on machines you control. Set OPENAI_BASE_URL to your installation and issue a Project API key, and the same client code that talks to OpenAI now talks to your Core. Each session runs a native harness, exactly as it runs on a developer's machine, with the model provider, model ID, and protocol you configure per harness or per session. Choose where sessions execute: microsandbox nodes you operate, Docker, E2B, or a self-hosted workstation, VM, or container connected by the oac-daemon with a credential scoped to one environment. Idle microsandbox sessions release their compute and resume on a compatible node with workspace files intact, so long investigations do not rent a machine while they sleep. The Web console walks operators through setup, tracks sessions and turns, manages models and credentials, and issues keys, while the separate Core API serves operators and the Agents API serves applications. Durable execution state in PostgreSQL keeps events, results, and schedules recoverable across restarts. Sandbox providers, workspace filesystems, harnesses, and model providers all plug in through defined protocols, so every layer can be replaced on its own. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Moltis gives individuals and teams a completely private personal AI agent server that bridges conversational assistants to everyday messaging platforms while executing real-world computing tasks inside secure execution environments. Users can interact with autonomous agents across Telegram, Discord, WhatsApp, Slack, Matrix, and browser interfaces to draft correspondence, automate research, and schedule recurring cron tasks. The system coordinates multi-agent delegation by spinning up specialized sub-agents with dedicated roles for code generation, pull request reviews, quality assurance testing, and technical documentation. Built-in sandboxing isolates tool operations within container boundaries or WebAssembly modules, ensuring shell commands, web scraping routines, and script executions cannot alter underlying operating system files without explicit permission. Native Model Context Protocol integration allows operators to attach external data endpoints, database connectors, and custom command-line utilities without rewriting core routing logic. Persistent memory preserves conversational context and document embeddings across multiple sessions, allowing assistants to recall prior discussions, user preferences, and project guidelines indefinitely. Administrators can configure granular tool approvals, manage WebAuthn passkey authentication, and review real-time WebSocket communication logs through an embedded control panel. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.