Back to directory

Octopus

A desktop AI agent framework with one-click installation, visual drag-and-drop workflow building, markdown-based skill extensions, a personal knowledge base, and multi-channel chat across WeChat, Slack, Discord, and Telegram.

Octopus

Octopus is a desktop AI agent framework meant to be installed with a double-click, running in an embedded Python environment or a portable USB mode with data kept local. It tracks token cost in real time with visual charts and budget alerts, and lets skills be added by writing a Markdown file that supports the MCP protocol, hot-reloads, and can be installed directly from Git.

Its visual workflow editor builds AI pipelines from 24 node types across flow, AI, tool, and logic categories, and a separate visual sub-agent creator spins up isolated AI workers with their own workspace, configuration, and memory that can be scheduled to run on a cron, interval, or one-time basis and survive restarts. It also holds a document-based knowledge base with AI-assisted summarization, reads PDF, DOCX, XLSX, and PPTX files, and reaches users over desktop, WeChat, Slack, Discord, Telegram, DingTalk, email, and webhooks.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.