OpenCode puts a capable coding agent in a browser tab, so a project on your server can be worked on from any device. Start a session, describe the change, and watch the agent read files, edit code, and explain what it did in plain language. A review panel lists every changed file with unified or split diffs, a file tree, and a git changes view, so nothing lands without a look. Sessions open as tabs, run in parallel, and keep a searchable history per project. The model picker spans more than 200 providers plus free hosted models, and any OpenAI compatible endpoint can be added from a config file, which keeps local and self-hosted models in reach. Settings offer top tabs, side tabs, or an inbox layout, optional permission auto-accept, steer or queue behavior for follow-up prompts, timeline detail levels, themes, and fonts. Extensions cover MCP servers, plugins, and skills, and custom agents and commands capture the team's habits. One-time pairing links connect a new browser or app to the server 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.

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.

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.

Instead of babysitting three coding agents in three terminal windows, you describe the work once and let Mikka run the team: its Coordinator bot plans the job, dispatches runs to Claude Code, Codex, or Cursor on your connected machines, and only interrupts you when a decision is actually yours. Every piece of work lives in a thread with its own conversation, so dispatched runs appear as cards that report progress, ask questions, and flag blocks while you watch, reply, or stop them from the web, desktop, or phone. Unclear requests come back as choice cards before anything runs, and finished work moves through review and verification runs, back to a fix run when a check fails, then to acceptance where the pull request merges as you. Runs use leases and checkpoints, so a machine that drops mid-task hands the work to another connected computer with the same repository. You can create your own bots beside the Coordinator, each with its own chat, memory, and threads, and answers can arrive as charts, tables, stat cards, and task chips with sources cited. Daemons connect over SSH or from the desktop app, other agents drive Mikka through MCP, and Telegram or Slack messages reach the Coordinator too. 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.

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.

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.

A team of coding agents, run in parallel from your desk, your browser, and your phone: Vicoa is an agentic IDE and control center, so one developer can steer a whole fleet instead of babysitting terminal tabs. Run 40+ coding agents side by side in one workspace: Claude Code, Codex, OpenCode, Gemini, Cursor, GitHub Copilot, Kimi, and more are built in, and 30+ additional agents connect through the Agent Client Protocol. Each agent gets its own git worktree and branch, so several can change one repository without overwriting each other, and every session's status sits in one list. Connect Mac, Windows or Linux machines, a VPS, or a remote server, pick where each session runs, and bring existing subscriptions or API keys. Start a session at your desk and steer it from the iOS or Android app on the train: approve a step, answer a question by dictation, or review the live git diff and file tree from your phone, with push notifications when an agent needs a decision or finishes. Plan work on the task board and start a session straight from a task, schedule cron automations that pick work up on their own, and share a live session link so teammates can watch or prompt alongside you. Host the backend and realtime server yourself with Docker, or drive everything from the CLI. 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.

Garcon gives developers one browser workspace for running several coding agents at once, steering their work live, and turning reviewed changes into commits. Tile up to four resizable windows, move chats between them, and place live sessions on durable canvases that show delegated children, handoffs and parentage. Turn that activity into a tag-driven delivery board, or create tickets first and open chats from them with the project, priority, assignee and discussion already attached. Queue instructions, reorder them, answer agent questions, approve tool calls, pause work, interrupt a run or stop it without losing the transcript. Exchange labelled messages between chats, delegate bounded tasks to child agents, and bring final results back into the parent conversation. Browse and edit files, open terminals, inspect reasoning and tool calls, then stage individual lines, hunks, files or folders before committing and pushing. Search transcripts, save filters, pin or archive chats, export Markdown or XML, schedule prompts for later, and review token use and estimated API cost by day, agent and model. Connect trusted remote executors when work belongs on another machine, and open the same workspace from a phone when an agent needs a decision 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. GPL-3.0 licensed.

Ask for a job in plain words and an agent with its own private computer does it: it reads files, runs commands, calls connected apps, and reports back in the chat. Every user gets a persistent sandbox workspace, so one person's files and commands never touch another's. Type a new message mid-run and the agent picks it up without stopping, or press Stop at any time. For bigger jobs the agent starts sub-agents that work side by side, each on a model of its choice, and the chat shows what each one is doing. Skills teach it repeatable methods in the open Agent Skills format; upload a zip, write one by hand, or let the agent write its own, and use them from a slash menu. The Connections page links Linear, Notion, Jira, Stripe, and other apps through one-click OAuth sign-in, or any MCP server by address. Scheduled tasks run on a repeating or one-time schedule, and each run becomes a readable chat. Small personal apps like a to-do cockpit or budget view appear in the sidebar, and charts, plans, and forms can render right inside answers. A files browser, an artifacts panel, a command menu, light and dark themes, and a phone layout round out the interface. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

Every major model provider behind one ChatGPT-style interface: LibreChat spans OpenAI, Anthropic, Google, Azure, AWS Bedrock, Vertex AI, Groq, Mistral, OpenRouter, DeepSeek, and any OpenAI-compatible endpoint including local Ollama. You can switch models mid-conversation and compare providers without changing tools. Its Agents framework builds no-code custom assistants with tool access via Model Context Protocol servers, file search over uploaded documents through an optional pgvector-backed RAG service, and a sandboxed Code Interpreter that executes Python, JavaScript, Go, C++, Java, PHP, and Rust. Artifacts render React components, HTML, and Mermaid diagrams directly in chat, and image generation works through DALL-E and other configured providers. Multi-user support is enterprise-grade, with OAuth, SAML, LDAP, and two-factor authentication, per-user conversation history in MongoDB, and Meilisearch-powered search across all messages and files, plus reusable presets, forkable threads, and persistent memory across conversations. The economics favor teams: instead of a ChatGPT Plus seat per person, everyone shares one instance billed per API token, with access to every provider rather than one - and providers see individual API calls, not your accumulated organizational knowledge. Deployment is Docker Compose; API keys and endpoints are configured through .env and librechat.yaml.

Large language models get a polished front end that can run fully offline: Open WebUI is the self-hosted front end of choice. It talks to local model runners, primarily Ollama, and to any OpenAI-compatible API, so LM Studio, vLLM, Groq, Mistral, OpenRouter, and cloud providers all plug into the same chat interface and can be mixed per conversation. RAG is built in: upload files to knowledge bases or reference them in chat with the # command, backed by a choice of nine vector databases (ChromaDB and PGVector officially maintained) and multiple extraction engines including Tika and Docling, with hybrid BM25-plus-vector search and cross-encoder reranking. Web search results from providers like SearXNG, Brave, and Tavily inject directly into conversations. Extensibility comes from Python tools and functions that run inside the chat, a Pipelines plugin framework, and native MCP support. Multi-user features include RBAC, SSO, and group permissions, and the instance itself exposes an OpenAI-compatible API your own apps can call.

Your coding agents are scattered across a laptop, a server, and whatever machine you left running at home, and Agenvo is the self-hosted relay that lets one AI assistant reach all of them through a single MCP endpoint. Ask ChatGPT on your phone to check on Codex running on your server, or have an agent in Herdr on your laptop fix a failing test, from wherever you are. Connectors for Herdr, Codex app-server, Paseo, and Lody dial out to the relay over WSS, so the computers running agents need no inbound ports, no VPN, and no port forwarding. Your assistant sees the agents running in Herdr without restarting them, resumes Codex threads later, and starts new work where it fits: a Codex thread on the server, or Codex, Claude, or Devin in a Herdr pane. When an agent finishes a turn, waits for input, or exits, the relay pushes a change event back, so a watching assistant or ChatGPT dot reads the output and takes the next step. Closing the chat or losing the network does not stop the agents; connectors reconnect on their own, and your assistant picks up from each agent's current state. Deploy the relay on a single VPS with Docker or on Cloudflare, authorize MCP clients with OAuth over Streamable HTTP, and discover targets and method schemas with search before calling execute. 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.

Your pi agent is mid-refactor on the server at home, you are on a train with only a phone, and Pi-Remote is the self-hosted relay that puts that live session in your browser so the work does not wait for your desk. Output, tool calls, and status changes sync in real time, with incremental catch up after a reconnect, and the session itself never leaves the local pi process. Send messages while pi is busy and they queue or steer, with delivery confirmed; switch the model or thinking level, compact the context, fork or clone a session, and walk the session tree, all executed locally. Several machines share one relay, and the UI lists each device, its online state, and its sessions, and can start a new session on the device you pick. Link a device by scanning a QR code, checking the 2 digit code on the confirmation page, and approving with the admin token. Desktop and mobile get separate layouts with six skins in Cursor, Claude, and Codex looks, dark and light, and token and cost usage updates in the status area. At home the relay can run serverless over the LAN, with a Cloudflare Tunnel switched on when you leave; on a server it runs under systemd or Docker Compose, and a device stays reachable only while its attach window is open. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.