20x banner
peakflo peakflo

20x

Development community

Description

Self-improving Agent orchestrator for all knowledge work

Installation

This entry records only its repository, not the path inside it, so there is no exact command to give. Open the source below and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

README

20x Logo

20x

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE) [![Version](https://img.shields.io/github/package-json/v/peakflo/20x)](./package.json) [![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Windows%20%7C%20Linux-lightgrey.svg)](.) [![Discord](https://img.shields.io/badge/Discord-Join%20us-5865F2?logo=discord&logoColor=white)](https://discord.gg/fUVsqTWDxX)

**One app. All your tasks. Powered by AI agents.**

20x is a desktop app that turns your task list into an AI-powered workforce. Connect your tools — Linear, HubSpot, YouTrack, GitLab, Notion, Peakflo — assign tasks to AI agents, and watch them work in real time.

**No cloud. No subscriptions. Everything runs on your machine.**

20x product demo

Why 20x?

Most AI tools make you copy-paste context between tabs. 20x flips it: **your tasks come to the agents, not the other way around.**

  • Pull a task from Linear → AI agent picks it up, reads the context, writes the code, opens a PR
  • Got a backlog of tickets? → Queue them up, agents work through them while you review
  • Need human approval? → Agents pause and ask before doing anything risky

How It Works

20x process: Hubspot, YouTrack, Linear, Github issues, Peakflo Workflo → triage agent → Agent (Claude Code, Opencode, OpenAI Codex) → HITL review → Feedback

  1. Tasks flow in — from Linear, YouTrack, HubSpot, GitHub Issues, Notion, Peakflo Workflo, or created manually
  2. Triage agent — Assigns priority, coding agent (Claude Code, OpenCode, or Codex), relevant skills, and git repos
  3. Agent works the task — reads skills, git worktrees, and MCP servers; streams output in real time
  4. HITL review — Agents pause for human approval before risky actions
  5. Feedback loop