English

The Best Local AI Agents: Run an AI Assistant on Your Own Hardware

Seven local AI agents ranked on how well they run with Ollama, vLLM, LM Studio or llama.cpp, and how much of your data stays on your own machine.

At a glance

At a glance
BotLicenseChat apps
Agent ZeroMIT19.8KYesYesTelegram, WhatsAppFree
QwenPawApache-2.037.5KYesNoTelegram, iMessage, Discord, SlackFree
ZeroClawMIT OR Apache-2.033.3KYesYesTelegram, WhatsApp, DiscordFree
nanobotMIT49.9KYesNoTelegram, WhatsApp, Discord, SlackFree
KhojAGPL-3.038.1KYesYesNoneFree
RakazoApache-2.07.5KYesYesTelegram, WhatsApp, iMessage, SlackFrom $10/mo
OpenClawMIT394.2KYesNoTelegram, WhatsApp, iMessage, Discord, SlackFree
GitHub stars as of Nov 8, 2026

Checklist

Checklist
Agent ZeroQwenPawZeroClawnanobotKhojRakazoOpenClaw
Open-source licenseYesYesYesYesYesYesYes
Runs local modelsYesYesYesYesYesYesYes
Sandboxed by defaultYesNoYesNoYesYesNo
No telemetry by defaultNoNoYesYesNoYesNo
Lives in your chat appsYesYesYesYesNoYesYes
Works while you're awayYesYesYesYesYesYesYes

Every agent we list can talk to a local model. That isn’t the same as being a good local AI agent. With a hosted model, your prompts, files and memory snippets leave your machine on every turn. Going fully local means the model, the search, the speech and the memory all run on hardware you own, and very few agents get you all the way there.

How we ranked them

This list weighs local operation over everything else:

  • Local runtimes supported. Ollama, vLLM, LM Studio, llama.cpp. More options means it fits the hardware you already have.
  • What else stays local. Web search, speech-to-text, text-to-speech and embeddings. An agent that runs the model locally but sends every search to a cloud API still leaks what you’re working on.
  • No telemetry and a sandbox, from the checklist in the table above, because local-first users usually care about both.
  • Setup effort and maturity.

A note on hardware: the agents themselves are light. The model is what needs RAM and a GPU, and a capable local model is a much bigger requirement than any agent on this list. Start by checking which model your machine can run, then pick the agent.

1. Agent Zero

Agent Zero goes furthest toward a fully local setup. It supports Ollama, LM Studio, llama.cpp, vLLM and oMLX (installation docs), web search runs through a bundled SearXNG instance instead of a search API, and speech-to-text and text-to-speech can run locally through built-in Whisper and Kokoro plugins (plugins). The agent works inside its own Docker container, isolated from your computer unless you grant access.

Its only telemetry is an update check that sends your version and a hashed instance ID; you can turn it off in settings. Plan for at least 2 GB of RAM for Agent Zero itself, before the model.

Agent Zero web UI showing a request to write a kickoff plan, the agent's collapsed steps for writing and verifying the file in the terminal, and a summary table of the plan
Agent Zero completing a first task in its web UIgithub.com

2. QwenPaw

QwenPaw, from Alibaba’s AgentScope team, ships its own llama.cpp runtime, so it can run fully offline with no API key and no separate Ollama install (models docs). The team also publishes small QwenPaw-Flash models trained for agent tasks. Ollama and LM Studio work too.

It ranks below Agent Zero on safety defaults: the command sandbox is off, and the documented quick-start command qwenpaw init --defaults accepts anonymous install telemetry automatically. Run the interactive qwenpaw init instead to opt out.

QwenPaw web console with a new chat, model picker set to qwen3.5-plus, and a sidebar listing Channels, Sessions, Cron Jobs, Heartbeat, Files, Skills, Tools, MCP and Agent Management
QwenPaw's web consolegithub.com

3. ZeroClaw

ZeroClaw is the cleanest choice if you already run Ollama or another OpenAI-compatible model server. It has no telemetry, an OS sandbox on by default, and provider fallback chains, so a local model can be first in line with a hosted one behind it, or with nothing behind it at all. As one Rust binary it runs on small boards like a Raspberry Pi, next to a model server on a bigger machine.

ZeroClaw homepage headline: The personal AI agent you actually own, one lightweight Rust binary on your machine with your keys or your local models
ZeroClaw's homepagezeroclaw.com

4. nanobot

nanobot supports Ollama, vLLM and LM Studio out of the box (providers), sends no telemetry, and keeps memory as plain Markdown files in ~/.nanobot, which is easy to inspect and back up. Its WebUI makes a local setup pleasant to use. Turn on its bubblewrap or Seatbelt sandbox before letting a local model run shell commands; it’s off by default.

nanobot WebUI new-topic screen with Apps, Skills, Automations and Channels in the sidebar, project-grouped topics, and a composer with permission and microphone controls
nanobot's bundled browser WebUIgithub.com

5. Khoj

Khoj is the specialist: an AI second brain that indexes your notes and documents and answers from them. It can run fully offline, with GGUF models through llama.cpp and embeddings generated on your machine, and it also supports Ollama, LM Studio and vLLM (setup). A GPU (CUDA, ROCm, Vulkan or Apple Metal) helps.

It ranks fifth because development has slowed (no release since March 2026), it has no chat-app channels, and it sends anonymized usage telemetry until you set KHOJ_TELEMETRY_DISABLE=True.

Khoj web app home with a greeting, agent shortcuts for Khoj, Legal, Simplify and Professor, a message box with attach and microphone buttons, and suggestion cards for Paint, Finance and Automation
The Khoj web app's start screendocs.khoj.dev

6. Rakazo

Rakazo, which we make, runs local models through Ollama or LM Studio (self-hosted models), sends no product analytics from a self-hosted install, and gives each bot a sandboxed computer. It ranks here because its local support is narrower than Agent Zero’s or QwenPaw’s: two local runtimes, and none built in. It’s also in beta. See the Rakazo review.

Rakazo web app with a chat with a bot called Chief and a side panel showing the bot's live browser screen, a Take control button and routines
A Rakazo bot chat with its computer screen beside itgithub.com

7. OpenClaw

OpenClaw works with Ollama, LM Studio and vLLM (Ollama provider), so it belongs on any local list, and its huge plugin ecosystem is a reason to pick it. But for local-first users the defaults pull the wrong way: a daily update check is on (update.checkOnStart: false stops it) and commands run on your host until you turn on sandboxing. If you want OpenClaw with local inference and a locked-down sandbox, NemoClaw wraps it with Ollama, vLLM or NVIDIA NIM routing, at the cost of 8 GB of RAM and an alpha label.

WhatsApp chat with an OpenClaw assistant giving casual travel advice to a user in Marrakech
Chatting with OpenClaw in WhatsAppdocs.openclaw.ai

Running the agent and the model on different machines

PicoClaw shows a useful pattern. Its agent needs as little as 10 MB of free RAM and runs on $10 boards and old phones, but it still needs network access to reach the model (hardware docs). Point it, or ZeroClaw, at an Ollama or vLLM server on a desktop with a GPU, and you get an always-on agent on a tiny device with all inference on your own network. PicoClaw didn’t make the ranking because the project says not to use it in production before v1.0.

For a broader view, see the best self-hosted AI agents.

Best picks

  1. Agent Zero

    Free

    Free, MIT-licensed AI agent that runs in its own Docker Linux workspace with a terminal, browser and desktop apps, and chats on Telegram and WhatsApp.

    Runs in its own Docker container with local models, but sends telemetry by default.

    Strengths

    • Free and MIT licensed, with frequent releases (v2.11 to v2.15 between late August and early November 2026)
    • The agent works in its own Linux workspace with a terminal, browser, desktop apps and LibreOffice, isolated from your computer unless you grant host access
    • Web search runs through a local SearXNG instance, and speech-to-text and text-to-speech can run locally
    • Projects keep memory, files, secrets, instructions and model choices separate per job, with workspace snapshots you can roll back
    • Built-in Telegram, WhatsApp and email channels, a scheduler, MCP and a community Plugin Hub with 200+ plugins

    Weaknesses

    • Needs Docker, and the container image is a full Linux desktop environment rather than a small service
    • No built-in image generation; the docs show teaching it an image API yourself
    • By default it checks for updates with Agent Zero's server, sending your version and a hashed instance ID
    • Code runs in the same container as Agent Zero itself today; per-task sandboxes are only a v3 prototype
    • WhatsApp works by linking a phone account through a Baileys bridge, which needs Node.js, rather than the official WhatsApp Business API
    Visit Agent Zero

  2. QwenPaw

    Free

    Free, Apache-licensed personal AI agent from Alibaba's AgentScope team, formerly CoPaw, with a web console, memory, multiple agents and many chat apps.

    Many chat apps and local models, but no sandbox and telemetry on by default.

    Strengths

    • Runs fully offline with a built-in llama.cpp runtime and purpose-trained QwenPaw-Flash models, no API key needed
    • Several independent agents, each with its own memory, skills and heartbeat, that can work together
    • Layered security: Tool Guard, File Guard, skill scanning, access policies and an optional kernel-level sandbox
    • Broad chat coverage, especially for Chinese platforms such as DingTalk, Feishu, WeChat and QQ, alongside Telegram, Discord, Slack and iMessage
    • Well-documented web console for channels, cron jobs, heartbeat, skills, MCP and files

    Weaknesses

    • The command sandbox is off by default, and inside Docker it falls back to no isolation
    • The recommended setup command accepts anonymous install telemetry automatically
    • No WhatsApp channel, and iMessage works only on a Mac with a third-party helper and Full Disk Access
    • Desktop apps are still in beta, and the project moves fast, with frequent beta releases
    Visit QwenPaw

  3. ZeroClaw

    Free

    Personal AI agent in one Rust binary, MIT or Apache-2.0, with local or cloud models, 30+ channels, approval gates and an OS sandbox on by default.

    Meets every check: one Rust binary, approval gates and an OS sandbox on by default, no telemetry, local models.

    Strengths

    • Safe defaults: the recommended profile asks before medium-risk actions, blocks high-risk ones, keeps files in the workspace and runs tools in an OS sandbox
    • One small Rust binary with one config file, running on macOS, Linux, Windows and boards like a Raspberry Pi
    • More than 30 channels, plus a web dashboard for chat, memory, config and cron
    • Provider fallback chains, local models through Ollama, and cryptographic receipts for tool calls
    • States plainly that it sends no telemetry and needs no cloud account or license server

    Weaknesses

    • Slack, iMessage, Signal and several other channels are not in the standard release; you build from source with extra features to get them
    • `zeroclaw quickstart` only sets up the model provider; channels and risk profiles mean editing the TOML config file
    • The Docker sandbox backend isn't picked automatically under the default native runtime
    • Model costs are on you
    Visit ZeroClaw

  4. nanobot

    Free

    Free, MIT-licensed personal AI agent in Python with a browser UI and terminal app, scheduled tasks, memory, and chat on Telegram, Discord, Slack and more.

    Small, readable Python with a good web UI and no telemetry, but shell commands aren't sandboxed by default.

    Strengths

    • Free and MIT licensed, with a small Python core that is meant to be read and modified
    • Polished bundled WebUI with projects, file diffs, an MCP app catalog and an automations calendar, plus a terminal UI
    • Many chat channels, including Telegram, Discord, Slack, WhatsApp, WeChat, Feishu, Teams, Matrix and email
    • Scheduled automations, long-running goals and a heartbeat that reports only useful results to your last chat
    • Works with local models through Ollama, vLLM or LM Studio

    Weaknesses

    • Shell commands are not sandboxed by default; the bubblewrap or macOS Seatbelt sandbox must be turned on, and Windows has none
    • Model costs are on you, and voice messages need a separate transcription provider such as Groq or OpenAI
    • No native mobile or desktop app; on a phone you use the WebUI in a browser or a chat app
    • Missed scheduled runs are not replayed and interrupted subagent tasks are not relaunched after a restart
    Visit nanobot

  5. Khoj

    Free

    AGPL-licensed, self-hosted AI second brain that chats over your notes and documents with web search, custom agents and scheduled research emails.

    Good at chatting over your own notes and documents, but development has slowed, it has no chat-app channels and telemetry is on by default.

    Strengths

    • Searches and chats over your own notes and documents, including Markdown, Org-mode, PDF, Word, Notion and GitHub
    • Works with local models through Ollama, LM Studio, vLLM or offline llama.cpp, and generates embeddings on your machine
    • Custom agents with their own persona, knowledge, chat model and tools
    • Automations run a query on a schedule and email you the result
    • Generated code runs in a local Terrarium sandbox that the Docker Compose setup starts for you

    Weaknesses

    • Development has slowed: no release since March 26, 2026, the last commit was on August 2, 2026, and the team now focuses on other products
    • The hosted Khoj Cloud, and with it the WhatsApp bot, shut down on April 15, 2026, so self-hosting is the only way to use it
    • AGPL-3.0 requires you to share your changes if you offer a modified version to others over a network
    • Sends anonymized usage telemetry by default until you set KHOJ_TELEMETRY_DISABLE
    • Scheduled emails need Resend and authentication set up when self-hosting, and no chat apps such as Telegram or Slack are supported
    Visit Khoj

  6. Rakazo

    From $10/mo

    Open-source, self-hostable platform for persistent AI bots that each get a job, a computer, memory and routines, using the model you choose.

    Our own product. Meets every check: Apache-2.0, sandboxed bot computers, no telemetry by default, any model you connect.

    Strengths

    • Open source (Apache-2.0) and fully self-hostable, including with local models
    • Choice of model per bot, including existing Claude or ChatGPT subscriptions
    • Bots keep working on schedules and triggers with their own cloud computer
    • Approval controls over which actions a bot may take on its own

    Weaknesses

    • Still in beta, with frequent releases
    • You supply and pay for the model on the hosted plans, unless you buy Rakazo credits
    • Telegram, WhatsApp and iMessage/SMS are only available when self-hosted
    • More setup than a single chat app
    Visit Rakazo

  7. OpenClaw

    Free

    Free, MIT-licensed personal AI agent that runs on your own computer and takes orders from WhatsApp, Telegram, iMessage, Slack and 20+ other chat apps.

    The biggest ecosystem and every chat app, but sandboxing is off and telemetry is on by default.

    Strengths

    • Free and MIT licensed, with no paid tier
    • Runs on your own hardware, and state, memory and credentials stay there
    • Works in 29 chat channels, including WhatsApp, Telegram, iMessage, Slack, Discord and Microsoft Teams
    • Model-agnostic: 64 model and media providers, plus local models
    • Large ecosystem of skills and 142 official plugins, and very active development

    Weaknesses

    • Model costs are on you and can run high: testers and users have reported spending over $100 in a day with expensive models
    • Sandboxing is off by default and the agent can run commands on the host unless you turn on approvals
    • Setup and upkeep expect comfort with the command line; maintainers warn it is risky for non-technical users
    • Broad access to email, messages and the system makes prompt injection and malicious third-party skills a real risk
    Visit OpenClaw

Features

Features
Agent ZeroQwenPawZeroClawnanobotKhojRakazoOpenClaw
Web searchYesYesYesYesYesYesYes
Image generationNoYesYesYesYesYesYes
Voice modeYesYesYesYesYesYesYes
File uploadsYesYesYesYesYesYesYes
MemoryYesYesYesYesYesYesYes
Takes actions for youYesYesYesYesYesYesYes
App integrationsYesYesYesYesYesYesYes
Works on its ownYesYesYesYesYesYesYes
Messages you firstYesYesYesYesYesYesYes
Runs several botsYesYesYesYesYesYesYes

Sources

Agent Zero

  1. agent0ai/agent-zero on GitHub (MIT, README, safety model)
  2. Agent Zero releases (v0.2 in June 2024 to v2.15 on November 1, 2026)
  3. Agent Zero homepage
  4. Agent Zero docs: Installation (Launcher, A0 Install, Docker, local models)
  5. Agent Zero docs: VPS deployment (hardware requirements)
  6. Agent Zero model provider list
  7. Agent Zero update check code (version and hashed ID sent to api.agent-zero.ai)
  8. Agent Zero built-in Telegram integration plugin
  9. Agent Zero built-in WhatsApp integration plugin
  10. Agent Zero built-in plugins (scheduler, notify user, email, SearXNG search, Whisper STT, Kokoro TTS)
  11. Agent Zero docs: Memory guide
  12. Agent Zero docs: Agent Profiles
  13. Agent Zero docs: API integration (adding image generation yourself)
  14. Agent Zero v3: A Sneak Peek Inside the Sandbox (August 17, 2026)
  15. Agent Zero LLM API (Venice.ai proxy for A0T token stakers)

QwenPaw

  1. agentscope-ai/QwenPaw on GitHub (Apache-2.0, README with install options and telemetry)
  2. QwenPaw documentation
  3. QwenPaw v1.1.0 release notes: CoPaw rebrands to QwenPaw
  4. copaw on PyPI (first release February 2026)
  5. QwenPaw docs: Channels
  6. QwenPaw docs: Models (cloud providers, llama.cpp, Ollama, LM Studio)
  7. QwenPaw docs: Security (Tool Guard, File Guard, sandbox)
  8. QwenPaw source: security.sandbox_enabled defaults to off
  9. QwenPaw docs: Heartbeat
  10. QwenPaw docs: Multi-agent
  11. QwenPaw docs: Comparison (voice and video interaction)
  12. QwenPaw docs: Desktop application (beta)
  13. QwenPaw docs: Plugins (GPT Image 2 image generation plugin)
  14. QwenPaw Qwen-Image tool plugin (image generation and editing)

ZeroClaw

  1. zeroclaw-labs/zeroclaw on GitHub (MIT OR Apache-2.0, v0.8.7, README)
  2. ZeroClaw website
  3. ZeroClaw docs: Sandboxing
  4. ZeroClaw source: risk presets (Balanced, recommended, has the sandbox on)
  5. ZeroClaw docs: Channels overview (default and standard release bundles)
  6. ZeroClaw docs: You own it (no telemetry)
  7. ZeroClaw docs: Docker and containers
  8. ZeroClaw source: tools (image generation, screenshot, web)

nanobot

  1. HKUDS/nanobot on GitHub (MIT, v0.4.1, README)
  2. nanobot documentation
  3. nanobot release archive (officially launched February 2, 2026)
  4. nanobot docs: Chat apps
  5. nanobot docs: Providers and models (Ollama, vLLM, LM Studio)
  6. nanobot docs: Configuration (security, exec sandbox off by default, transcription, Langfuse)
  7. nanobot docs: Automations and heartbeat
  8. nanobot docs: Concepts (heartbeat delivery, subagent recovery)
  9. nanobot docs: Memory and Dream
  10. nanobot docs: Multiple instances
  11. nanobot docs: Deployment (Docker, services, Render)
  12. nanobot source: skills installer runs with DISABLE_TELEMETRY

Khoj

  1. khoj-ai/khoj on GitHub (AGPL-3.0, README)
  2. Khoj releases (latest 2.0.0-beta.28, March 26, 2026)
  3. Khoj commit history (last commit August 2, 2026)
  4. Khoj Cloud Has Been Sunset (April 15, 2026)
  5. Khoj homepage (Open Paper, Pipali and the Khoj app)
  6. khoj-assistant on PyPI (first release 0.1.0, August 2, 2022)
  7. Khoj docs: Self-host setup (Docker, pip, model providers)
  8. Khoj docs: Ollama
  9. Khoj docs: Telemetry
  10. Khoj docs: Privacy
  11. Stop sending client IP in telemetry so it matches the privacy docs (#1382)
  12. Khoj docs: Automations
  13. Khoj docs: Code execution (Terrarium sandbox)
  14. Khoj docs: Agents
  15. Khoj docs: Image generation
  16. Khoj docs: Voice
  17. Khoj docs: WhatsApp (bot tied to Khoj Cloud)
  18. Khoj server settings (memory feature enabled and on by default)

Rakazo

  1. Rakazo homepage
  2. Rakazo pricing
  3. Rakazo privacy policy
  4. Rakazo on GitHub (README and license)
  5. Rakazo changelog
  6. Rakazo releases
  7. Rakazo docs: Image and video generation
  8. Rakazo docs: Memory
  9. Rakazo docs: Connect apps
  10. Rakazo docs: Routines
  11. Rakazo docs: Chat apps
  12. Rakazo docs: Messaging apps (self-hosting)
  13. Rakazo docs: Bots and chats (add another bot, bot templates)
  14. Rakazo docs: Groups (several bots in one chat)
  15. Rakazo docs: Mobile app (notifications)
  16. Rakazo privacy policy (updated Sep 14, 2026)
  17. Rakazo privacy policy source on GitHub
  18. Rakazo docs: Logs and monitoring (product analytics off by default)
  19. Rakazo docs: Desktop app (run locally in Docker, updates)
  20. Rakazo docs: Docker computers
  21. Rakazo docs: Self-hosted models (Ollama, LM Studio)
  22. Rakazo Railway template setup guide

OpenClaw

  1. OpenClaw homepage and Foundation section
  2. OpenClaw integrations: channels, providers and plugins
  3. openclaw/openclaw on GitHub (MIT, v2026.11.1)
  4. OpenClaw docs: Sandboxing (off by default)
  5. Wikipedia: OpenClaw
  6. Notebookcheck: OpenClaw can burn through hundreds of dollars per day
  7. OpenClaw docs: Memory overview
  8. OpenClaw docs: Automations
  9. OpenClaw docs: Chat channels
  10. OpenClaw docs: iMessage
  11. OpenClaw docs: Heartbeat, now a default Proactive check job
  12. OpenClaw docs: Multi-agent routing
  13. OpenClaw docs: Platforms (macOS, Windows, Linux, iOS and Android apps)
  14. OpenClaw docs: Tools (exec, browser, web search)
  15. OpenClaw docs: Audio and voice notes (inbound transcription)
  16. OpenClaw docs: Image and media support (inbound media)
  17. OpenClaw docs: Install (system requirements, installer script, npm, desktop apps, Docker)
  18. OpenClaw docs: One-click deploy on Railway
  19. OpenClaw docs: Usage telemetry and update checks (on by default, feature statistics opt-in)
  20. OpenClaw docs: Ollama provider (local models)