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.

DeepSeek Harness gained over 60,000 GitHub stars within hours of its August 2026 launch, establishing itself as the first fully modular open-source agent runtime where literally every component is a swappable plugin. Built on the Cordis framework—a programming paradigm for spatiotemporal composability—dsh decomposes the entire agent stack into independently replaceable pieces: model adapters for DeepSeek, Anthropic, OpenAI, AWS Bedrock, Azure, and Google Gemini; tool registries covering bash execution, file system operations, web search, subagent delegation, and todo management; plus session stores, sandboxes, approval policies, orchestration loops, and the user interface itself. Four operating modes serve different workflows: Standard provides the full toolset, Code mode uses model-generated code to compose multi-round tool calls, Minimal strips down to a shell and editor for benchmarking, and Creator mode lets developers inspect the running runtime and test Cordis plugins in memory. The kernel handles plugin mounting, unmounting, and dependency resolution while typed events and services coordinate between components. Profiles and bundles allow the same codebase to produce entirely different products—a terminal coding agent, a browser-based workspace, a headless automation service, or an ACP/JSON-RPC endpoint—by swapping YAML configuration layers. Session history is stored as an append-only event stream for full trajectory replay, and project-level hooks on agent lifecycle events enable fine-grained behavioral customization. MCP client integration connects to external tool servers, while Agent Client Protocol enables programmatic orchestration. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Pi Web is a browser interface for the Pi coding agent ecosystem, providing a visual workspace that reads the same local configuration and session files as the CLI. The session workspace groups conversations by project with running state indicators, context usage percentages, cost tracking, and compaction details, while two branching modes let users create independent session files from earlier messages or fork branches within existing sessions to explore alternative coding directions. Real-time streaming via Server-Sent Events delivers agent responses with structured Markdown rendering, thinking steps, tool call visualization, and image drag-and-drop input. The project file explorer browses working directories with syntax-highlighted source preview, Git diff inspection, and rendering for Markdown, images, audio, PDFs, and DOCX files with automatic refresh. Git worktree support switches checkouts from the sidebar while keeping sessions from the same repository grouped together. The Models panel manages provider authentication via OAuth and API keys, model selection, model smoke tests, and models.json configuration shared bidirectionally with the CLI agent. The Skills panel lists, searches, installs, and toggles agent skills without terminal access. The interface ships with English and Simplified Chinese translations, light and dark themes, a chat minimap, keyboard shortcuts, and completion sounds. Basic Auth protects remote access when binding to non-loopback addresses. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Run Claude Code, Codex, Gemini CLI, OpenCode, and sixteen other AI coding agents from one workspace instead of juggling twenty terminals. Every agent connects through the Agent Client Protocol, so conversations render as structured chats with tool cards, live diffs, and interactive replies rather than raw terminal scrollback. Codeg imports the session history each agent already keeps on disk, making every past conversation searchable and resumable, even when you hand the thread to a different agent. Mention one agent with an @ to delegate work to another, or run several side by side and watch their progress stream into the same conversation. Queued to-dos execute unattended in isolated git worktrees, leaving finished changes ready for your review and approval instead of touching your working tree. An infinite canvas arranges chats, files, terminals, and notes on one board, while git tooling, token usage tracking, and MCP server support stay one panel away. Deployed as a headless server, Codeg answers in any browser and through Telegram, Lark, and WeChat channels, so agent work continues while you are away from your desk. 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 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.

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.

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.

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.

AgentBox is a self-hosted browser workspace that runs Claude Code and Codex CLI on a server you control, so a task goes from chat to reviewed code without leaving one place. Open a workspace from an empty project, an uploaded archive, or a Git clone, then talk to the agent in streaming web chat or drop into its original interactive terminal when you want the CLI itself. Files persist between sessions along with your home configuration and chat history, so a project picked up on a laptop continues on a phone exactly where it stopped. Review per-file diffs line by line before committing, pushing, or opening a pull request, and download the result when no Git connection is configured. Shared files, layered home templates, Claude skills, and MCP configuration carry your setup into every new workspace, with per-workspace overrides when a project differs. A trusted team shares central account pools with per-user scopes, while every model request is recorded with tokens, cache hit rate, cost, and latency, exportable to CSV and optionally capped by credits. An optional tunnel reaches allowlisted repositories and databases on private networks, and six interface styles with light and dark modes keep long sessions comfortable. 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.

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.

While you sleep, a crew of Claude Code agents in a single Docker container keeps building: you plant a mission, the farm splits it into sub-agents on their own branches, and only work that passes your tests ever lands in the repo. Open the farm in your browser and every agent is a pixel Claude walking its plot, tending a task at a terminal or napping when the budget says stop, with the quest log, mission board, and a hatchery for new agents a click away. Each account is paced against its real five hour and weekly usage, measured live, always leaving you twenty percent and never paying overage, and teammates' agents message each other and hand jobs to whichever account still has room. Talk to any agent from the Claude app on your phone, post quests, set schedules like weekday issue triage at nine, and watch live dashboards the agents maintain themselves. Whiteboards let you sketch while an agent draws back full Mermaid architectures for the whole farm to see, the farm's logged-in browser does website work as you, and Slack mentions, Blender scenes, and other models from GPT to a local Ollama all plug into the same queue. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

T3 Code puts every coding agent you already pay for behind one control surface, so Claude Code, Codex, Cursor, Grok Build, OpenCode, and Antigravity all run on your server while you direct them from your phone, browser, or desktop. Start a thread, choose the provider and model that fit the job, and watch the agent work in a shared conversation instead of a terminal you have to babysit. Permission modes decide when an agent must stop and ask, and its approvals, questions, and plan reviews arrive in the same thread wherever you happen to be connected from. When the work lands, review it file by file in the built-in diff view, then commit, push, and open pull requests through the Git and GitHub integrations without leaving the app. A real terminal sits beside the chat, and projects, settings, and scheduled tasks stay attached to the machine where the code actually runs. Install it as a background service and reach it from anywhere through T3 Connect, a Tailscale or LAN pairing, or the hosted web client, with a pairing code guarding local access. Outside agents can also drive threads over MCP, launching, messaging, and waiting on work across machines you have linked together. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Open Agent Builder delivers a visual canvas for orchestrating AI agent workflows without writing Python scripts or managing complex codebases. The React Flow-powered drag-and-drop interface supports seven node types — Agent, Scraper, Transform, If/Else, Loop, User Approval, and MCP Tool — each configurable with provider-specific settings for Anthropic Claude (Haiku 4.5 and Sonnet 4.5), OpenAI GPT-5, Groq, or any OpenAI-compatible endpoint. The LangGraph orchestration engine handles state management, conditional routing, and human-in-the-loop approval gates while Firecrawl integration converts any website into structured, LLM-ready data through scrape, crawl, and map operations. E2B sandboxed code execution powers Transform nodes for secure data manipulation without risking host system integrity. Real-time streaming updates show execution progress node-by-node as workflows run, with Convex providing reactive database synchronization for workflow state and execution history. The TypeScript-first architecture (96.8% TypeScript) built on Next.js 16 App Router with Tailwind CSS delivers a responsive interface across devices. Clerk handles multi-user authentication with JWT integration for secure workspace isolation. Deploy via npm install and environment configuration with Firecrawl, Convex, and Clerk 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.

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.

Kandev provides a command center for orchestrating AI coding agents across parallel workstreams. The Go backend paired with a Next.js frontend delivers kanban boards with drag-and-drop columns, pipeline workflow definitions with per-step agent handoffs, and an IDE-like review workspace combining file editor, file tree, terminal, browser preview, and unified git diffs. Multi-provider support connects Claude Code, GitHub Copilot, Codex, Qoder, Grok, and custom agents through configurable profiles with per-agent prompts, runtimes, and review gates. Tasks execute in isolated git worktrees with multi-repository support, letting agents work on separate branches simultaneously while changes surface in a consolidated review interface. Native integrations with GitHub, GitLab, Jira, Linear, Sentry, and Slack pull external issues into the kanban and link tasks to pull requests. Kandev exposes streamable HTTP and SSE MCP endpoints, enabling external clients — Cursor, Claude Desktop, Augment — to create tasks and read workspace context programmatically. Workflow definitions export as portable YAML for sharing across installations. Agentic workflows chain multi-step pipelines mixing different models per step — Opus for architecture, Sonnet for implementation, with human review gates between stages. 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.

With over 77,000 GitHub stars accumulated in under five months since its March 2026 launch, Paperclip has become the default control plane for teams running multiple AI agents in production. Rather than juggling dozens of terminal tabs with Claude Code sessions, Codex instances, and Gemini CLI workers, Paperclip organizes all agents into a company structure with org charts, reporting lines, role-based permissions, and per-agent monthly budgets that trigger hard-stops when exceeded. The platform supports any runtime through its adapter system — Process adapters manage local CLI agents like Claude Code, Codex, Cursor, Pi, and OpenCode as child processes, while HTTP adapters trigger remote agents via webhooks to OpenClaw, serverless platforms, or custom endpoints. Heartbeat-based execution wakes agents on configurable schedules, injecting goal context, budget state, and workspace paths directly into the invocation payload. The Work and Task System provides atomic checkout with execution locks, first-class blocker dependencies, and structured work products to eliminate duplicate effort. Governance features include approval workflows, decision tracking, emergency stops, and full audit trails tracing every mutation to an actor. Deployment runs as a single Node.js process with embedded PostgreSQL locally or scales to external Postgres for production, installable in one command via npx paperclipai onboard. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Describe the outcome once, in plain language, and a small crew of AI agents divides the work between them and reports back in the same chat. You type the request in the team chat; Boo Zero, the team lead, splits it into jobs on a shared board and hands each card to the teammate best placed to do it. Teammates run on Claude Code, Codex, Hermes, OpenClaw, or Clawboo's built-in runtime, and one team can mix them freely, so the researcher, the writer, and the coder can each work on their strongest tool. You follow every card live on the board and in the chat, watch the team graph to see who is doing what, and add a reviewer agent when a second pair of eyes matters. Finished work returns to Boo Zero, which pulls the pieces together and answers you in the chat. Ready-made teams from the marketplace cover marketing squads, dev teams, and research crews, and you can bring an API key from Anthropic, OpenAI, OpenRouter and more, a free local model through Ollama, or your ChatGPT subscription through the Codex CLI. Spend is tracked per team with budget warnings before costs surprise you. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Trinity runs your AI agents the way a company runs employees, with departments, roles, reporting lines, and receipts for everything they do. Each agent holds a seat on record tied to an objective and a declared metric, so whether it is working is a number with a date on it rather than an impression. Agents work on three runtimes, Claude Code, OpenAI Codex, and Gemini CLI, chosen per chat without changing the agent's state, history, or permissions. A schedule fires, the agent works inside its own container, and anything irreversible waits in a human approver's Inbox as a card naming the agent, the skill, and the input until someone approves, discusses, or rejects it. Every agent is a git repository you own: it commits its own work, its tool calls land in an append-only audit log, and every run appears in an execution ledger with its trigger, cost, and outcome, searchable across the fleet. The same agents answer in the browser Workspace, in Slack, Telegram, and WhatsApp, over a public chat link, through MCP, and from the CLI. Guardrails bind agents by what they hold rather than what they are told, with hooks they cannot switch off, cost limits, loop budgets, and a kill switch for outbound calls. 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.