Skip to content
SPECIFICTION
Get listed

Pan-Agent

github.com

WindowsmacOSLinuxAPISelf-hosted
Visit github.com
Spec score 7.6 #14 of 24 in AI Computer Use Agents

What it is

Pan-Agent is a free, MIT-licensed, open-source AI assistant that runs on the user’s own machine. It can take screenshots, interpret screens, type, click, manage windows, run commands, and browse the web. The project lists more than 20 built-in tools, including terminal, filesystem, browser, web search, keyboard, mouse, vision, memory, and cron. It connects to OpenAI-compatible providers such as OpenAI, Anthropic, OpenRouter, Groq, Ollama, LM Studio, vLLM, and llama.cpp. Cron expressions can schedule agent runs, while separate profiles isolate API keys, model settings, persona, memory, and skills. Telegram, Discord, and Slack bots work without a public URL. A headless local HTTP API runs on localhost:8642 and has a documented set of 50 endpoints. Its 103-pattern approval system classifies commands and blocks catastrophic actions by default. Sessions use SQLite, and updates verify Ed25519 signatures. The project says it has no telemetry. Important limits include an unauthenticated API, Linux control requiring X11 or XWayland, unsigned Windows installers, and a macOS app that is not notarized.

Spec sheet

What it does
Pan-Agent is a self-hosted AI assistant that runs on the user's own machine.Read 1 Oct 2026 · github.com
Product
Pan-Agent is an open-source, self-hosted AI assistant that runs on the user’s own machine.Read 30 Sep 2026 · github.com
API
The headless HTTP API binds to localhost at port 8642 and is scriptable from any language.Read 1 Oct 2026 · github.com
Privacy
The project states that it has no telemetry and zero phone-home behavior.Read 1 Oct 2026 · github.com
License
Pan-Agent is open source under the MIT license.Read 1 Oct 2026 · github.com
API security
The HTTP API binds to 127.0.0.1 and has no authentication; the project says defending against arbitrary local code execution is out of scope.Read 30 Sep 2026 · github.com
Approval security
A 103-pattern system classifies commands as Safe, Dangerous, or Catastrophic; catastrophic commands are blocked by default.Read 1 Oct 2026 · github.com
Auto-update
The Tauri updater verifies Ed25519 signatures before installing updates.Read 1 Oct 2026 · github.com
Automation
Cron expressions can trigger scheduled agent runs such as daily briefings and periodic checks.Read 1 Oct 2026 · github.com
License and audience
Pan-Agent is MIT-licensed and describes itself as built for people who want control of their AI agent without vendor lock-in.Read 30 Sep 2026 · github.com
LLM integrations
It supports OpenAI-compatible providers including OpenAI, Anthropic, Regolo, OpenRouter, Groq, Ollama, LM Studio, vLLM, and llama.cpp.Read 1 Oct 2026 · github.com
LLM support
It supports OpenAI-compatible providers including OpenAI, Anthropic, OpenRouter, Groq, Ollama, LM Studio, vLLM, and llama.cpp.Read 30 Sep 2026 · github.com
Memory and profiles
Persistent memory and isolated profiles store separate API keys, model configuration, persona, memory, and skills.Read 1 Oct 2026 · github.com
Messaging integrations
Built-in bots connect to Telegram, Discord, and Slack.Read 1 Oct 2026 · github.com
PC control
It can take screenshots, type, click, manage windows, run commands, and browse the web.Read 1 Oct 2026 · github.com
Platform limitation
PC-control tools require X11 or XWayland on Linux; pure Wayland is unsupported.Read 1 Oct 2026 · github.com
Platform security caveats
The project says Windows installers are unsigned and the macOS app is not notarized, so first launch may require manual steps.Read 30 Sep 2026 · github.com
Safety controls
A 103-pattern approval system asks before dangerous commands and blocks catastrophic commands by default.Read 30 Sep 2026 · github.com
Security limitation
The HTTP API has no authentication and is intended for a single-user desktop app.Read 1 Oct 2026 · github.com
Storage and memory
Sessions are stored in SQLite, and persistent memory and persona files are maintained per profile.Read 30 Sep 2026 · github.com
Target users
The project is built for people who want to own their AI agent with full control and no vendor lock-in.Read 1 Oct 2026 · github.com
Tools
The project lists 20+ built-in tools, including terminal, filesystem, browser, web search, screenshot, keyboard, mouse, vision, memory, and cron.Read 30 Sep 2026 · github.com
Updates
The Tauri updater verifies Ed25519 signatures before installing updates.Read 30 Sep 2026 · github.com
Windows distribution
Windows installers are unsigned and may trigger SmartScreen or Defender warnings.Read 1 Oct 2026 · github.com

Strong points and limits

Strong points

  • Runs locally with no telemetry stated
  • Controls screens, windows, keyboard, and mouse
  • Supports many OpenAI-compatible providers
  • Scheduled runs and isolated profiles
  • Command approvals block catastrophic actions by default

Limits

  • HTTP API has no authentication
  • Linux control requires X11 or XWayland
  • Windows installers are unsigned
  • macOS app is not notarized

Who it suits

Pan-Agent suits people who want local control of an AI assistant, desktop automation, multiple model providers, and no vendor lock-in. It is also aimed at users comfortable managing self-hosted software and its platform caveats.

Verdict

Pan-Agent offers broad local automation, provider choice, messaging bots, and approval controls at no listed cost. Its unauthenticated API and operating-system setup requirements deserve attention before deployment.

Where Specifiction places it

Alternatives to Pan-AgentAll alternatives →