<div align="center"> <img src="docs/assets/mascot.png" alt="Kernl" width="180">

Kernl

Agent teams that do your work — on your own machine.

Kernl is a self-hosted server that hands any LLM your real data — tasks, mail, calendar, finance, contacts — and runs teams of agents that act on it. No account, no cloud, nothing leaves the box.

<p> <a href="https://github.com/fastslack/kernl/stargazers"><img src="https://img.shields.io/github/stars/fastslack/kernl?style=for-the-badge&logo=github&color=ffd700" alt="GitHub stars"></a> <a href="https://github.com/fastslack/kernl/releases"><img src="https://img.shields.io/github/v/release/fastslack/kernl?style=for-the-badge" alt="Latest release"></a> <a href="./LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue?style=for-the-badge" alt="License"></a> <img src="https://img.shields.io/badge/MCP-native-6366f1?style=for-the-badge" alt="MCP native"> <img src="https://img.shields.io/badge/self--hosted-000?style=for-the-badge" alt="Self-hosted"> </p>

<a href="#-install-in-one-line"><b>Install</b></a> · <a href="#-watch-them-work"><b>Watch them work</b></a> · <a href="#-why-kernl"><b>Why Kernl</b></a> · <a href="#-mcp-integration"><b>MCP integration</b></a> · <a href="https://lifekernl.com"><b>Website</b></a> · <a href="https://github.com/fastslack/kernl/discussions"><b>Discussions</b></a>

</div>

🎬 Watch them work

<div align="center">

<a href="https://lifekernl.com"><img src="docs/assets/office3d.png" alt="Kernl's 3D agent building: an isometric floor plan of fourteen offices with agent avatars at their desks, meeting rooms, a reception, free lots and a warehouse with loading docks" width="900"></a>

_{<b>A real instance.</b> 84 agents across fourteen offices, plus a warehouse. Not a mockup and not a render — that is the <code>/agents-flow</code> view of a running Kernl, and the one-liner below gets you to it.}

</div> <!-- Captured from a running instance at /agents-flow with e2e/tests/readme-office3d-shot.json — rerun that suite to refresh the still, then copy the newest e2e/screenshots/readme-office3d-*.png over docs/assets/office3d.png. The scene takes ~40s to build, which is why the test waits on `.hq-search-btn` (it only exists once the world is mounted) instead of a fixed delay, and why it strips `.update-bar` before shooting: a version banner dates a screenshot the moment the next release ships. Caveat: the suite REPORTS A TIMEOUT even though it writes the screenshot correctly, about two minutes in. The run record comes back with zero actions and zero duration, so the runner is discarding the action log rather than the browser failing — the same "Test timed out after Nms" that dominates this project's e2e history. Judge the run by the PNG it leaves behind, not by its exit status. The README shows the still (office3d.png). The animated office3d.gif, no longer shown here, is rendered from the site repo's clips/kernl-office-16x9.mp4 (15s, 1920x1080). Note the crop: the source is a wide shot of the entire floor, and shrunk to fit a README column every agent label goes sub-legible and the DONE badges turn into specks — which defeats the point of showing it at all. The 2x centre crop keeps the labels and the badges readable, and the badges still land inside the cropped frame across all 15s. CROP="crop=960:540:480:270" ffmpeg -i clips/kernl-office-16x9.mp4 \ -vf "$CROP,fps=12,scale=900:-1:flags=lanczos,palettegen=max_colors=128:stats_mode=diff" pal.png ffmpeg -i clips/kernl-office-16x9.mp4 -i pal.png \ -lavfi "$CROP,fps=12,scale=900:-1:flags=lanczos[x];[x][1:v]paletteuse=dither=bayer:bayer_scale=3:diff_mode=rectangle" \ docs/assets/office3d.gif That lands at ~1.9 MB, which still loads before a first-time visitor has finished reading the headline above it. -->

---

⚡ Install in one line

curl -fsSL https://raw.githubusercontent.com/fastslack/kernl/stable/install.sh | sh

Debian/Ubuntu, Fedora/RHEL and macOS. The same command installs and updates — it reads the newest release and picks the build for your machine. On Windows, take the .msi from the latest release.

→ Dashboard at http://localhost:3086 · MCP endpoint at http://localhost:3086/mcp

Nothing to sign up for and no host paths to set. First run walks you through four steps, and one of them is connecting an AI — NVIDIA is free by default, or pick from eleven others, including local models through Ollama or LM Studio if you'd rather nothing left the machine at all. Chat and agents stay off until you connect one; the rest of the dashboard works either way.

<details> <summary><b>Prefer Docker?</b> (adds the bundled Neo4j graph brain)</summary>

git clone https://github.com/fastslack/kernl.git
cd kernl
docker compose up -d --build

# Kernl generates an API token on first boot. Grab it:
docker compose exec kernel cat /app/data/.kernel-auth-token

Paste that token once into the dashboard's login screen and you're in — it's kept in your browser and reused for every request. To pin your own instead, set KERNEL_AUTH_TOKEN (openssl rand -hex 32) in .env before the first up. The graph brain (Neo4j) and key-free web search come bundled in this path.

To let the Filesystem Commander browse a folder of your machine, and to run claude_code agents on your Claude Code login, set KERNL_FS_ROOT in .env and add the host overlay — then name the same files on every later compose command:

docker compose -f docker-compose.yml -f docker-compose.host.yml up -d

</details>

Your AI is brilliant — and amnesiac.

Every conversation starts from zero. Your LLM can't see your tasks, read your inbox, check your budget, or remember what you told it yesterday. And the cloud "AI assistants" that promise to fix that? They want your entire life uploaded to their servers.

Kernl fixes both.

What is Kernl?

Kernl is a self-hosted server that plugs your real life into any LLM through the Model Context Protocol (MCP) — tasks, contacts, email, finance, calendar, notes, health and more, behind one endpoint that Claude, Cursor or any MCP client can reach.

Then it goes past a data bridge: Kernl runs agents — autonomous teams (it calls them offices) that work in loops, call your tools, and finish jobs while you're away.

Everything runs on your machine. Your data never leaves the box.

_{For the depth, once you want a number: 103 tools live on a fresh install, rising past 290 as you enable more of the 71 bundled modules.}

<div align="center">_{<b>WORKS WITH</b>}<br>Claude · Cursor · OpenAI · NVIDIA · Gemini · Ollama · <b>any MCP client</b></div>

💬 Talk to your life

Point your AI at Kernl and ask it things it could never do before:

💸 "Did rent clear, and how much did I spend on food this month?" — reads your finance module.

📥 "Triage my inbox and draft replies to anything urgent." — reads your email, writes the drafts.

✅ "What's overdue, and what's due this week?" — straight from your real tasks + calendar.

🤖 "Spin up the dev office and clear the next three backlog items." — launches an agent team that works on its own.

Real data. Real actions. On your machine — not in someone else's cloud.

🔥 Why Kernl

| | | |---|---| | 🔒 Private by default | Self-hosted. Your tasks, email and finances never touch someone else's cloud. | | 🧠 Real memory | A graph-backed brain (Neo4j + GDS) links every module, so your AI finally remembers. | | 🤖 Agents that act | Not a chatbot — autonomous offices that work in loops and use your tools. | | 🔌 Any LLM, any client | NVIDIA (free), Gemini, Groq, OpenRouter, Anthropic, OpenAI, DeepSeek, Grok, MiniMax, Claude Code, or a local model via Ollama or LM Studio. Any MCP client connects. | | 🧩 Endlessly extensible | Everything is a module. Ship your own as a portable .kernl package. | | 📊 103 tools installed, 71 modules bundled | One surface for your whole life — not fifteen disconnected apps. Enable everything and you pass 290 tools. |

⚔️ Kernl vs. the usual options

| | Cloud AI assistants | A single MCP server | "Second brain" apps | Kernl | |---|:---:|:---:|:---:|:---:| | Your data stays on your machine | ❌ | ✅ | ⚠️ | ✅ | | Your real life — email, finance, tasks… | partial | one thing | ❌ | 71 modules | | Agents that act, not just chat | limited | ❌ | ❌ | ✅ | | Works with any LLM & MCP client | ❌ | ✅ | ❌ | ✅ | | Yours to extend & fork | ❌ | ⚠️ | ❌ | ✅ |

🧩 What's inside

Your life, addressable by your AI — tasks & projects, contacts/CRM, reminders, email (IMAP/SMTP), finance & budgets, calendar, notes, goals, health & training, shopping, travel, documents… 71 modules, every one exposed as MCP tools.

A fleet of agents — cooperating agents with chains, schedules and their own workspaces. Package a whole team as an installable .kernl office, and watch them work in a live 3D office view.

Pluggable everything

• LLM providers — 12 built in, connected from Settings → AI; keys stored encrypted.
• Sandbox drivers — run agent code in Docker, CubeSandbox, or your own driver.
• Channels — WhatsApp, Telegram, Slack, email, Mattermost and webchat on one notification bus.

Graph intelligence — optional Neo4j + GDS for cross-module relationship analysis.

🔌 MCP integration

Kernl speaks MCP over stdio and Streamable HTTP at the same time, so every client reaches the same tools.

<details> <summary><b>Claude Desktop / Cursor (stdio)</b></summary>

{
  "mcpServers": {
    "kernl": {
      "command": "bun",
      "args": ["run", "bin/mcp-server.ts"],
      "cwd": "/absolute/path/to/kernl/services/kernel"
    }
  }
}

</details> <details> <summary><b>Any HTTP client</b></summary>

The MCP HTTP transport is at http://localhost:3086/mcp by default (the official Streamable HTTP spec).

</details>

🛠️ Build your own

An extension is a folder (or a packaged .kernl) with a manifest.json plus any of: a backend module (new MCP tools + HTTP routes), agents & offices, agent-scoped skills, a theme, a channel, or a sandbox driver.

Keep operator-specific material — named agents, your WhatsApp, regional scrapers — private under services/kernel/assets/personal-agents/ (gitignored, ideal for a private submodule).

Full guide → docs/architecture/extension-points.md

📦 More install options

<details> <summary><b>Full stack — host-coupled mounts</b></summary>

WhatsApp no longer needs this: it is part of the standard docker compose up -d, which already runs the mtwRequest Rust server and the WhatsApp bridge, and the Linux, macOS and Windows packages bundle the same pair and run them as supervised children — no compose file needed there either. Either way, you link your phone from Settings → Channels → WhatsApp (QR or phone code) with nothing to configure. docker-compose.full.yml is only for building those two services from local source and for host-coupled mounts (so on-host claude_code agents can edit your sibling repos). Needs a few host paths in .env:

git clone https://github.com/fastslack/kernl.git
cd kernl
cp .env.example .env
$EDITOR .env   # set HOST_HOME, HOST_KERNEL_ROOT, HOST_PROJECTS_ROOT,
               # KERNEL_REQUEST_SRC, KERNEL_WHATSAPP_BRIDGE_SRC
docker compose -f docker-compose.full.yml up -d --build

</details> <details> <summary><b>Local dev — no Docker</b></summary>

git clone https://github.com/fastslack/kernl.git
cd kernl
bun install --cwd services/kernel   # requires bun >= 1.3
cp .env.example .env
b