{"slug": "openbot-how-to-run-a-team-of-ai-agents-on-your-computer", "title": "OpenBot: How to Run a Team of AI Agents on Your Computer", "summary": "Synthetify Labs released OpenBot, a source-available desktop app that runs a team of AI agents locally on macOS, Windows, and Linux. The app uses a local-first architecture with per-agent workspaces, a SQLite database for conversation history and task queuing, and isolated browser sessions, and it connects to existing subscriptions or API keys from providers including Codex, Claude Code, Gemini, Grok, and local models via Ollama and LM Studio. Shared channels coordinate agents through crash-safe FIFO message queues that enforce a single task owner at a time, and a marketplace catalog lists 27 narrowly scoped agents.", "body_md": "Everyone has been part of a school group project where each member wrote their section alone at home without talking to anyone else. The night before the deadline, someone pasted everything into a single document. The result was an academic Frankenstein: the introduction ignored the conclusion, every section cited sources differently, and arguments contradicted each other right on the page.\n\nDespite rapid progress in language models, most of our day-to-day work with AI still repeats that exact dynamic. We open a chat window, ask a question, copy the response, and close the tab. The next second, all project context and reasoning vanish.\n\nIt feels like hiring a brilliant freelancer with severe amnesia: they have to relearn your entire business from scratch before every single task.\n\nFor one-off questions, that transactional relationship works fine. For ongoing workflows—code maintenance, product launches, support triage, or operational monitoring—the real leverage comes from accumulating context over weeks. That is the shift **OpenBot**, a source-available project by Synthetify Labs, puts into practice by replacing the disposable chatbot with a resident operational team right on your computer.\n\nOpenBot's core difference isn't launching yet another proprietary model. The desktop app is built on a **local-first** architecture and follows a *Bring Your Own Plan* model: instead of charging token markups, it connects to the AI subscriptions and API keys you already pay for—or to local model servers running on your own hardware.\n\nRather than relying on ephemeral cloud threads, every team member gets a continuous technical environment on your machine built on four pillars:\n\n`~/OpenBot/Agents/<agent-id>`) preserves source files, drafts, and accumulated context across sessions and restarts.`openbot.db`) logs conversations, session bindings, reactions, and queued tasks, with automatic compaction before long threads overflow the model's context window.`openbot_browser`, each agent operates isolated browser sessions capable of staying logged into tools you already use—such as GitHub, Figma, Notion, Linear, or admin dashboards.\nIn practice, the source-available codebase in `nightly-labs/openbot` (under the *PolyForm Noncommercial 1.0.0* license, free for personal use on macOS, Windows, and Linux, with remote access via web, iOS, and Android) turns AI from an isolated utility into a permanent deskmate.\n\nWith context preserved on disk, agents no longer live in solitary tabs—they coexist in **shared channels**, much like a `#launch` room, except populated by humans and models from different vendors working side by side.\n\nIn the same thread, an agent backed by **Codex** can investigate a bug, another on **Claude Code** writes tests or reviews the patch, while a third on **Gemini** or **Grok** organizes release notes. The ecosystem also supports **OpenCode** (including free models with no account required), **Cursor**, **Cline**, **Muse Code**, **Pi**, Inception's **Mercury** models, any agent compatible with the **Agent Client Protocol (ACP)**—such as Goose, Qwen Code, and GitHub Copilot CLI—and 100% local models via **Ollama** and **LM Studio**.\n\nWorking together in a persistent space unlocks a decisive shift: **strict specialization**. Instead of a generic assistant doing everything adequately, the official OpenBot Marketplace catalog features **27 agents** with narrow scopes and explicit boundaries:\n\nPutting brilliant specialists in the same room creates an obvious risk: without a protocol, everyone talks and edits files at the same time.\n\nTo prevent collisions, OpenBot channels run on crash-safe **FIFO message queues** (*First In, First Out*) with strict state control. At any given moment, there is only a **single task owner**.\n\nA real workflow shows how this engine turns without human micromanagement:\n\n`~/OpenBot/Shared/Transfers` alongside an `.openbot-transfer.json` manifest recording authorship, recipients, size, and a SHA-256 checksum.\nAn assistant that only acts when you type a command still demands constant mental overhead to remember, prompt, and follow up. To remove that friction, OpenBot attaches **scheduled routines** directly to resident agents.\n\nThink of them as classic cron jobs, except they wake up the full language model with access to local context, accumulated history, and authenticated browser tabs. *Chief of Staff* wakes on weekday mornings to cross-check your calendar, emails, and commitments and post a ~25-line briefing before your workday starts. *QA Tester* runs morning smoke checks against production, while *Ops Digest* sweeps Notion, Airtable, or Trello boards on Friday afternoons to flag overdue items.\n\nYet the most mature engineering detail in this architecture is the **silence rule**, implemented through the `routine_no_update` function. In immature automations, if nothing broke overnight, the bot still sends a cheerful message saying everything looks fine—flooding your phone with operational noise.\n\nA well-designed routine works like a smart alarm clock: it wakes up on its own, reads your emails, checks your flight status, and only wakes you up if boarding has been canceled.\n\nWhen an agent runs its routine in OpenBot and finds no anomalies or relevant updates, its instructions tell it to call `routine_no_update`. The channel stays completely silent, protecting human focus.\n\nGiving background agents access to local directories, a terminal, and an authenticated browser raises an inevitable security question. OpenBot's technical documentation is candid about this: after initial consent, local agents run with `danger-full-access` permissions and `approvalPolicy: never` inside the local environment.\n\nBecause local analysis and execution are unrestricted to avoid constant permission prompts, containment relies on two concrete barriers:\n\nIt is a pragmatic split between **analysis autonomy** and **execution autonomy**: your digital team prepares everything behind the scenes, while the bridge to the real world requires a human circuit breaker.\n\nIn the original deep dive published on **Blense**, you'll find the complete comparison table across all 14+ supported runtimes, the agent boundary matrix, architecture diagrams (FIFO queue and human circuit breaker), and remote WebRTC deployment details.\n\n👉 **Read the full technical dossier:** [OpenBot: How to Run a Team of AI Agents on Your Computer](https://blense.tech/posts/openbot-how-to-run-a-team-of-ai-agents-on-your-computer)", "url": "https://wpnews.pro/news/openbot-how-to-run-a-team-of-ai-agents-on-your-computer", "canonical_source": "https://dev.to/genildocs/openbot-how-to-run-a-team-of-ai-agents-on-your-computer-3i0j", "published_at": "2026-11-17 19:32:23+00:00", "updated_at": "2026-11-17 19:59:43.640551+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "developer-tools", "large-language-models", "agent-protocols"], "entities": ["Synthetify Labs", "OpenBot", "Codex", "Claude Code", "Gemini", "Grok", "Ollama", "LM Studio"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/openbot-how-to-run-a-team-of-ai-agents-on-your-computer", "markdown": "https://wpnews.pro/news/openbot-how-to-run-a-team-of-ai-agents-on-your-computer.md", "text": "https://wpnews.pro/news/openbot-how-to-run-a-team-of-ai-agents-on-your-computer.txt", "jsonld": "https://wpnews.pro/news/openbot-how-to-run-a-team-of-ai-agents-on-your-computer.jsonld"}}