{"slug": "show-hn-personal-jarvis-an-open-source-alternative-to-grokbot", "title": "Show HN: Personal Jarvis an open-source alternative to GrokBot", "summary": "Personal Jarvis launched as a free, open-source AI workspace that runs on a user's own computer, centered on a voice orchestrator that connects conversations to agents, coding sessions, desktop actions, and user-selected services. The desktop app supports Windows, macOS, and Linux, installs via PowerShell or a curl/bash script, requires Python 3.11+ and Git, and lets users choose hosted providers, local models, or mixed setups, with plugins, skills, and MCP servers available for extension. Hosted models, coding subscriptions, and optional services are billed by their respective providers, while supported local models require no cloud model account.", "body_md": "Talk to Jarvis. Work with your agents. Bring your tools, models, and knowledge together.\n\n  An open-source workspace for conversations and the work that follows.\n\n**Personal Jarvis is an open-source AI ecosystem that runs on your own computer.**\nAt its center is Jarvis, a voice orchestrator that connects a conversation to\n[agents](#jarvis-agents), [coding sessions](#coding-workspace), desktop actions,\nand the services you choose to connect. Speak naturally or type a message:\nJarvis can answer, use a tool, or delegate work while you follow the conversation\nand inspect what happens. The desktop app brings those conversations, your team,\nand their results into one workspace on Windows, macOS, and Linux.\n\nThe workspace extends beyond the conversation. Build persistent specialists with\ntheir own instructions and recurring routines. Use [Jarvis Voice](#jarvis-voice-dictation)\nto dictate into other apps. Connect [plugins, skills, and MCP servers](#plugins-skills-and-mcp),\nwork alongside coding CLIs, keep knowledge in a [local Markdown wiki](#memory-and-knowledge),\nand open generated reports, pages, and files in [Artifacts](#artifacts-and-run-history).\nThese are connected parts of the same application: a request can start with your\nvoice, continue with an agent, and leave behind something you can read, use, or edit.\n\n**Choose the models and services that fit your work.** Jarvis supports hosted\nproviders, [local models](#local-models), and mixed setups. Your selected provider\nsupplies the intelligence; Jarvis manages application state, tool access,\napprovals, and execution. Local speech and model options can keep supported\nwork on your hardware. Cloud models and connected services receive the content\nneeded for their requests; running the app locally does not make every integration\noffline. See [privacy and local data](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/privacy-safety-and-support/privacy-and-local-data.md)\nand [how the system fits together](#how-it-works).\n\n[Website](https://personaljarvis.ai) · [Getting started](#your-first-steps-in-the-desktop-app) ·\n[Documentation](#documentation) · [GitHub](https://github.com/PersonalJarvis/PersonalJarvis) ·\n[YouTube](https://www.youtube.com/@PersonalJarvis) ·\n[Discord](https://discord.gg/x7USduHxbc) · [X](https://x.com/Ruben_Luetke) ·\n[Instagram](https://www.instagram.com/personaljarvis/)\n\n**Windows — PowerShell**\n\n```\nirm https://raw.githubusercontent.com/PersonalJarvis/PersonalJarvis/main/install/install.ps1 | iex\n```\n\n**macOS and Linux**\n\n```\ncurl -fsSL https://raw.githubusercontent.com/PersonalJarvis/PersonalJarvis/main/install/install.sh | bash\n```\n\nThe installer checks Python 3.11+ and Git, offers to install missing prerequisites through the host package manager, installs the applicable desktop components, registers the desktop launcher, and opens the app. Language, wake phrase, and provider setup happen in the app. OS permissions and hardware capabilities affect voice and desktop control. Re-running the installer updates an existing installation.\n\nPersonal Jarvis is free and open source. Hosted models, coding subscriptions, and optional services are billed by their respective providers. Supported local models do not require a cloud model account.\n\n[Full installation, platform requirements, and uninstall instructions](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/install/README.md).\n\nStart a **Voice Chat**, tap the voice bar, or use your configured wake phrase.\nYour speech and Jarvis's replies appear in the conversation. Start a normal\n**Chat** when you prefer a keyboard.\n\nJarvis brings the workspace into reach: ask an agent to research a topic, work with a coding session, find something in memory, or use a connected tool. Available actions depend on your providers, installed tools, and permissions. Computer use needs a desktop and the required OS permissions.\n\nChoose your voice and model access in the app. The voice path can use realtime audio or a speech-recognition, model, and speech-output pipeline. Your selected provider determines the available capabilities; execution and approvals remain under Jarvis's control.\n\n<sub>“Hey George” → listening → conversation. The desktop window and navigation stay in view.</sub>\n\nThe demos on this page are **Remotion recreations of the interface with\nillustrative conversations**, not live recordings or response-time benchmarks.\nThe wake phrase and listening transition above are animated to explain the\ninteraction. Click a GIF for its sharper 60 fps video, or use the\n[still previews and reproducible source](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/scripts/readme-video/README.md).\n\n[Voice conversations](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/voice-conversations.md) ·\n[Wake phrase and audio](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/audio-and-wake-word.md) ·\n[Models and providers](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/providers-and-api-keys.md)\n\n1. **Open Personal Jarvis.** The installer opens the desktop app for you. Later,\nfind**Personal Jarvis** in Windows Search, macOS Spotlight, or the Linux\napplication menu. You do not need to keep a terminal open.\n2. **Complete the in-app setup.** Choose your language, review device permissions,\nand choose a wake phrase or a keyboard shortcut. The assistant name follows\nyour chosen phrase:**Hey George** is the example above, not a required name.\n3. **Connect model access.** Open**API Keys & Providers** to connect and test a\nsupported provider, or configure a local model. Chat needs a ready model;\nvoice additionally needs a working realtime connection or speech pipeline.\n4. **Start a conversation.** Use**New chat** to choose**Chat** or**Voice Chat** .\nFor voice, wait for readiness and use your wake phrase, shortcut, or the voice\nbar. Try:*\"Help me plan a small project. Ask me what you need to know.\"*\n5. **Build out your workspace.** Add a specialist under**Agents** , connect a\nservice in**Plugins / Skills / MCP** , or open**Jarvis Voice** for dictation.\nFind generated files in**Artifacts** and recurring work under**Scheduled** .\n\nThe sidebar keeps these areas within reach. **More** opens additional views,\nincluding knowledge, coding tools, settings, and help. Voice Chat is a conversation\nwith Jarvis; **Jarvis Voice is speech-to-text for the app you are already using**.\n\n[First-run setup](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/start-here/first-run-setup.md) ·\n[First chat](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/start-here/start-your-first-chat.md) ·\n[First voice conversation](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/start-here/start-your-first-voice-conversation.md) ·\n[Desktop tour](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/start-here/desktop-app-tour.md)\n\n## Manual installation and headless use\n\n```\ngit clone https://github.com/PersonalJarvis/PersonalJarvis.git\ncd PersonalJarvis\npython -m venv .venv\n```\n\nActivate with `.\\.venv\\Scripts\\Activate.ps1` on Windows or\n`source .venv/bin/activate` on macOS/Linux, then run:\n\n```\npip install -e \".[full]\"\njarvis          # Desktop app\njarvis serve    # Headless API and browser UI\n```\n\nFor a minimal server installation, use `pip install personal-jarvis` and\n`jarvis serve`. Open the local address reported at startup; the default is\n`http://localhost:47821`. Remote browser microphone access requires HTTPS.\nSee the [headless deployment guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/headless-vps-deployment.md).\n\nBuild a team you can return to. Each agent has an identity, a direct conversation, standing instructions, and access to the tools you grant it. Pick a connected model or supported agent account for the work, and keep the conversations in one workspace.\n\n<sub>An illustrative agent conversation, from brief to draft. The GIF plays once and holds the reply; click to replay the video.</sub>\n\n- **Talk directly to a specialist.** Select an agent from the roster and continue its chat.\n- **Give it a standing brief.** Configure its instructions, model access, and tools.\n- **Set up recurring work.** Per-agent routines expose instructions, scheduling, and execution history.\n- **Inspect its work.** Read messages and tool activity, and open produced files in Artifacts.\n- **Explore the world view.** The workspace also has a visual map of the team.\n\nPersistent agents and isolated coding missions have different lifecycles. Coding missions can use worktree isolation and critic review; an ordinary agent chat is not a new isolated worktree on every message.\n\n[Agent guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/jarvis-agents.md) ·\n[Agent learning](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/agent-society/self-learning.md) · [Routines](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/routines.md)\n\n**Speak into the app you already use.** Hold your dictation shortcut or toggle\nhands-free recording, then insert the transcript into the focused text field.\nDictation is speech-to-text; Voice Chat is a conversation with Jarvis.\n\nThe **Jarvis Voice** section brings together dictation history, your dictionary,\nshortcuts, language settings, and speech-provider setup. Optional cleanup improves\nthe transcript, translation writes into a selected language, and Prompt Mode can\nturn a dictation into a structured prompt. Review and recover entries in history\nwhen you need to revisit a transcript.\n\nChoose local speech recognition to process audio on your machine. Provider-backed cleanup or translation can still send text to the configured provider.\n\n[Dictation guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/dictation.md) ·\n[Speech dictionary](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/speech-dictionary.md) ·\n[Languages and voices](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/languages-and-voices.md)\n\nUse local models, hosted providers, or a mixture. **Local models** helps you\ndiscover the local server, see available models, configure their roles, and\ncheck readiness. Text generation, tools, and image input have different model\nrequirements.\n\n| Part | Local option | \n|---|---|\n| Model and tools | Ollama or a compatible local OpenAI-style endpoint. Tool support depends on the model. | \n| Speech recognition | On-device Whisper or Nemotron, with the corresponding engine and model installed. | \n| Speech output | On-device Piper voices. | \n| Realtime conversation | A compatible self-hosted realtime server; experimental, with its own hardware requirements. | \n\nDownloads, hardware needs, languages, and capabilities vary by model. External APIs, hosted coding accounts, connected services, and telephony still send the relevant work to those services.\n\n[Local AI setup](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/local-ai-providers.md) ·\n[Provider setup](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/providers-and-api-keys.md)\n\nBring supported coding CLIs into **Agentic IDE** with a project folder and live\nterminal panes. Work with tools such as Claude Code or Codex using the access\nsupported by that tool, and keep their sessions visible alongside the rest of\nJarvis. Terminal and chat views provide different ways to follow the work.\n\nPanes have call signs so you can address a particular session through Jarvis:\n*\"Tell T1 to run the tests\"* or *\"What is T2 working on?\"* Return to the workspace\nto inspect output, respond to a prompt, or take over manually. A terminal becoming\nidle is not proof that its result is correct; inspect its changes and validation.\n\nOrdinary command-line connections are managed separately from interactive coding\npanes. **CLIs & CLI Test Hub** helps discover, configure, and test those tools\nbefore you ask Jarvis to use them.\n\nConnect the workspace to the tools you already use, and extend how Jarvis works\nwithout replacing the assistant. The **Plugins / Skills / MCP** hub separates\nthree complementary kinds of extension:\n\n| Extension | What it adds | Learn more | \n|---|---|---|\n| **Plugins** | Connections to supported services and their tools, with their own setup and connection state. | [Plugin guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/plugins.md) | \n| **Skills** | Reusable instructions for a task or workflow, with explicit activation and configuration. | [Skill guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/skills.md) | \n| **MCP servers** | Tools supplied by local or remote Model Context Protocol servers, according to granted access. | [MCP connections](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/mcp-connections.md) | \n\nConnect the services you need and inspect their status in the app. A tool being\nlisted does not establish that its account is connected or that a particular\naction will succeed. Authentication requirements and permissions vary by\nintegration. For a self-hosted example, see\n[connecting Home Assistant](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/connect-home-assistant.md).\n\nKeep reusable knowledge in the **Knowledge Wiki**, a local Markdown vault with\npages, links, and a visual memory map. It gives facts and notes a place beyond a\nsingle conversation, and lets you browse the material that later work can use.\nYou can also connect the vault to Obsidian.\n\nProfile information, contacts, and standing instructions add different kinds of context. Use them to describe preferences and people, and shape the assistant's behavior. They are editable parts of your workspace, so you do not need to repeat the same background in every prompt.\n\n[Wiki and memory](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/knowledge-and-sharing/wiki-and-memory.md) ·\n[Obsidian](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/knowledge-and-sharing/connect-obsidian.md) ·\n[Profile and contacts](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/profile-and-contacts.md) ·\n[Instructions and persona](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/instructions-and-persona.md)\n\nRecurring work belongs in a schedule. Use agent routines for a specialist's recurring brief and the scheduling views to manage tasks and inspect their run history. Instructions, timing, and previous executions stay visible so you can change the work as your needs change.\n\nWorkflows and app commands provide additional ways to trigger supported actions. Scheduling depends on the relevant Jarvis runtime being available and the required providers and connections being ready; saving a schedule is not a completed run.\n\n[Routines](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/routines.md) ·\n[Tasks and reminders](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/tasks-and-reminders.md) ·\n[Workflows and commands](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/workflows-and-commands.md)\n\nJarvis can interact with desktop applications through the configured computer-use path. Screen context supplies visual information; computer use goes further and can act through the mouse and keyboard. Desktop access and the required OS permissions are necessary, and actions pass through the configured safety policy.\n\nOptional messaging channels and Twilio calling extend the ways requests and\nconversations reach the system. These need their own supported accounts and setup.\nCalling is a hosted-service capability, not an offline feature; the\n[phone-call guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/phone-calls.md) covers\nnumbers, credentials, and webhooks.\n\n[Computer use](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/computer-use.md) ·\n[Screen context](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/screen-context.md) ·\n[Permissions](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/privacy-safety-and-support/permissions.md)\n\nA conversation can produce something you keep. **Artifacts** brings generated\nreports, documents, pages, images, and other files together for preview and\ndownload. Follow the output back to the work that produced it, then open or reuse\nit outside Jarvis.\n\nSession history and **Run Inspector** help explain what happened: recorded turns,\ntool activity, timing, and errors. **Spend** shows recorded provider usage and\navailable cost information, including supported coding-session usage. Coverage\ndepends on what each provider and execution path reports.\n\n[Outputs and files](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/outputs-and-files.md) ·\n[Sessions and Run Inspector](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/sessions-and-run-inspector.md)\n\nThe desktop is a **React/TypeScript interface inside a pywebview window**, backed\nby a **Python/FastAPI application**. REST endpoints handle application operations;\nWebSockets deliver live state and activity. Headless mode exposes the API and\nbrowser interface without the native desktop shell.\n\nThe execution path follows the request and available capabilities. A simple answer can stay in the conversation; a service action needs an available tool; longer work can run through an agent or mission lifecycle. Persistent agent chats and worktree-isolated missions remain distinct.\n\n| Boundary | Technical role | \n|---|---|\n| **Protocols** | Shared contracts in `jarvis/core/protocols.py` separate orchestration from provider and platform implementations. | \n| **Event bus** | Typed, immutable events carry trace IDs so components exchange activity without direct coupling. | \n| **Streaming providers** | Brain, speech, and harness interfaces stream output; realtime sessions handle live audio through their selected provider. | \n| **Tool executor** | A central execution path applies the risk policy and approval requirements before an action runs. | \n| **Mission lifecycle** | Coding missions can use isolated Git worktrees, progress events, critic review, cancellation, and retained output. | \n| **Extension points** | Provider plugins use Python entry points; MCP servers and connected services contribute tools through their adapters. | \n| **Persistence** | Conversations and run records use dedicated stores, the Knowledge Wiki uses local Markdown, and credentials use the secret-storage layer. | \n\nFor the current live-voice path, see [GPT-Live](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/gpt-live.md). For deeper\nengineering detail, read the [architecture overview](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/architecture-overview.md),\n[architecture decisions](https://github.com/PersonalJarvis/PersonalJarvis/tree/main/docs/adr/), and [OS parity](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/os-parity.md).\n\nConfigure providers and credentials in the app. Keys use the operating system's\ncredential store when available, with supported environment/file fallback for\nother setups. Keep secrets out of chat, `jarvis.toml`, and version control.\nThe [configuration example](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/jarvis.toml.example) documents advanced settings.\n\nWake-word listening runs locally. Your speech and model providers determine where subsequent audio, text, and tool context are processed. The Knowledge Wiki stays in local files; integrations receive the information needed for the actions you ask them to perform.\n\nTool execution uses a risk policy with **safe, monitor, ask, and block** tiers.\nPermissions, approvals, and run history let you inspect and control actions.\n\nFor scripts and other agents, the CLI reaches the same application API:\n\n```\njarvis system status\njarvis --json brain status\njarvis api <tag> <op>\n```\n\n[CLI guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/jarvis-cli.md) ·\n[Control API](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/reference/control-api-reference.md) ·\n[Safety and approvals](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/privacy-safety-and-support/safety-and-approvals.md) ·\n[Privacy](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/privacy-safety-and-support/privacy-and-local-data.md) ·\n[Security policy](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/SECURITY.md)\n\nOpen **Docs** in the app for searchable product guides, or follow the topics here.\n\n| Guide | Contents | \n|---|---|\n| [Getting started](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/start-here/welcome-to-personal-jarvis.md) | Installation, first conversation, and desktop tour. | \n| [Dictation](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/everyday-use/dictation.md) | Shortcuts, history, cleanup, and speech input. | \n| [Plugins](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/plugins.md) | Connect services and inspect their status. | \n| [Skills](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/skills.md) | Reusable instructions and workflows. | \n| [MCP](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/extend-and-automate/mcp-connections.md) | Local and remote tool servers. | \n| [Local AI](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/personalize-and-connect/local-ai-providers.md) | Model setup and capability checks. | \n| [Troubleshooting](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/product/privacy-safety-and-support/troubleshooting.md) | Setup, connection, and device problems. | \n| [Architecture](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/architecture-overview.md) | Components, data flow, and provider boundaries. | \n| [GPT-Live](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/gpt-live.md) | The native live-voice path and tool execution. | \n| [Agent learning](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/agent-society/self-learning.md) | Private, evidence-backed learning for persistent agents. | \n| [Routines](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/routines.md) | Scheduling and recurring work. | \n| [OS parity](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/os-parity.md) | Platform coverage and limitations. | \n| [Contributor guide](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/CONTRIBUTING.md) | Development setup and pull requests. | \n| [Architecture decisions](https://github.com/PersonalJarvis/PersonalJarvis/tree/main/docs/adr/) | Design decisions and their context. | \n| [README media source](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/scripts/readme-video/README.md) | Provenance, example data, still previews, and rendering commands. | \n\nFollow the project on the [website](https://personaljarvis.ai),\n[X](https://x.com/Ruben_Luetke), and\n[Instagram](https://www.instagram.com/personaljarvis/).\n\nQuestions, ideas, and bug reports are welcome on [Discord](https://discord.gg/x7USduHxbc)\nand [GitHub](https://github.com/PersonalJarvis/PersonalJarvis/issues/new/choose).\nWatch walkthroughs on the [Personal Jarvis channel](https://www.youtube.com/@PersonalJarvis).\n\nRead [CONTRIBUTING.md](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/CONTRIBUTING.md) before a pull request. Hardware reports,\nprovider integrations, accessibility improvements, and native-language feedback\nare especially useful. AI-assisted contributions are welcome; review focuses\non the change and its evidence. Repository contributions are written in English.\nReport vulnerabilities privately through [SECURITY.md](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/SECURITY.md).\n\nThank you to everyone who contributes. This wall is updated from commit history.\n\n[Apache 2.0](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/LICENSE): free to use, modify, and distribute, including commercially.\nSee [NOTICE](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/NOTICE), [licensing details](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/docs/licensing.md), and\n[trademark guidance](https://github.com/PersonalJarvis/PersonalJarvis/blob/main/TRADEMARK.md). Releases through version 1.6.0 retain their\noriginal MIT license.", "url": "https://wpnews.pro/news/show-hn-personal-jarvis-an-open-source-alternative-to-grokbot", "canonical_source": "https://github.com/PersonalJarvis/PersonalJarvis", "published_at": "2026-09-24 16:43:35+00:00", "updated_at": "2026-09-24 16:59:48.812420+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-tools", "agent-protocols", "ai-products"], "entities": ["Personal Jarvis", "Jarvis", "GitHub", "Windows", "macOS", "Linux", "Python 3.11", "Git"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/show-hn-personal-jarvis-an-open-source-alternative-to-grokbot", "markdown": "https://wpnews.pro/news/show-hn-personal-jarvis-an-open-source-alternative-to-grokbot.md", "text": "https://wpnews.pro/news/show-hn-personal-jarvis-an-open-source-alternative-to-grokbot.txt", "jsonld": "https://wpnews.pro/news/show-hn-personal-jarvis-an-open-source-alternative-to-grokbot.jsonld"}}