Octop TencentCloud/Octop

Self-hosted multi-user, multi-agent AI assistant with a web dashboard, desktop apps, IM channels, document RAG and Ollama or API models.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

Octop at a glance

Checked 15 Oct 2026

Octop (Tencent Cloud) is a self-hosted AI assistant in one Python process: web dashboard, CLI, desktop apps and IM channels (Telegram, Discord, WeChat and more), with per-user agent "experts", RAG knowledge bases, memory, browser automation and cron jobs. MIT licence. It ships no chat model: connect Ollama locally or an OpenAI-compatible API, so answer quality depends on the model. Releases are still beta (1.0.2b8).

Cite this pageRepoQuarry. “Octop.” Checked 15 Oct 2026. https://repoquarry.dev/projects/octop

How much of ChatGPT Plus does it replace?

2 of 3 jobs. Replaces the chat app and document Q&A for a household or small team; answer quality depends on the model you connect. No built-in web search answers documented.

Chat assistant Partial replacement

Chat with your documents Partial replacement

Web search answers Not covered

For web search answers, see other ChatGPT Plus alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, self-hosted single process (pip, installer, desktop app or Docker); data under ~/.octop Best of all, it runs entirely on your machine github.com · Octop#readme ↗ 1d ago

Code licence MIT github.com · LICENSE ↗ 1d ago

Model weights licence No bundled chat weights; licence depends on the model you connect OpenAI-compatible APIs, DashScope (Qwen), Ollama, and other presets — configure per agent in the dashboard or via `octop provider`. github.com · Octop#supported-llm-providers ↗ 1d ago

Commercial use Yes, MIT code; check the licence of whichever model you connect github.com · LICENSE ↗ 1d ago

Paid services needed? None required with Ollama; paid model APIs and Tencent Cloud hosting optional OpenAI-compatible APIs, DashScope (Qwen), Ollama, and other presets github.com · Octop#supported-llm-providers ↗ 1d ago

Hardware Multi-core CPU and a few GB RAM for Octop itself; local model needs depend on the model A modern multi-core CPU with a few GB of RAM for the process plus model/embedding caches github.com · Octop#prerequisites ↗ 1d ago

Operating systems Windows, macOS and Linux (x64 and ARM64), plus Docker and FnOS NAS packages Desktop client — native apps for Windows / macOS / Linux; FnOS packages for NAS github.com · Octop#surfaces ↗ 1d ago

Setup effort Easy; desktop installer, one-line install script or pip install octop, then octop init pip install octop github.com · Octop#1-install ↗ 1d ago