Yume 🤖 Agent Freemium
Native desktop UI for the official Claude Code CLI with orchestration and background agents
- GitHub stars
- 150
- Stars this week
- +1
- Forks
- 8
- Licence
- –
- Last push
- 2026-09-26
- Maintainer
- aofp
git clone https://github.com/aofp/yume && cp yume/*.md ~/.claude/agents/Third-party subagents & agents run with your permissions. Read the source before installing, and prefer pinned versions.
Works with
About Yume
What it does
Yume is a native desktop application that puts a graphical front end on the official Claude Code CLI. It spawns the real claude binary as a subprocess and uses your existing Claude subscription, so subagents, MCP, hooks, skills and CLAUDE.md all keep working. It aims to fix the rough edges of a terminal, flickering, input lag in long sessions, one session per window, and adds a hardware-accelerated UI, tabs and split panes, always-visible rate-limit meters, automatic session snapshots, and an orchestration flow that decomposes larger tasks across built-in and background agents.
What is inside
- Four built-in foreground agents (architect, explorer, implementer, guardian) synced to
~/.claude/agents/, plus up to four concurrent background agents with git branch and worktree isolation - An orchestration flow (understand, decompose, act, verify) that passes trivial tasks straight through
- Persistent 5-hour and 7-day usage meters with an optional guard that stops new turns before an overage, live interleaved thinking, and automatic crash recovery
- Multi-provider support through a shim, a plugin and skills system with many hook events, vim mode, voice dictation, an analytics dashboard, and 18 themes
Works with
It drives Claude Code and stays fully compatible with the CLI. Non-Claude providers (Gemini, OpenAI, Kiro) are available through its shim. Runs on macOS, Windows and Linux.
How to install
The README does not include a package command; download the app from the project's site (aofp.github.io/yume). It requires a Claude Pro/Max subscription or API key and the Claude Code CLI installed.
Maintenance and safety
Actively developed. It is proprietary freeware with a paid upgrade (a monthly and a lifetime tier); the free tier is limited to two tabs, two panes and one window. The licence re-verifies weekly over the network with a seven-day grace period, after which it reverts to the demo. It adds no markup to Claude usage and states it keeps your code on your machine with zero telemetry, but because it is closed source you cannot audit the app itself.
Who should use it
Claude Code users who prefer a polished desktop UI with tabs, visual diffs, background agents and constant usage visibility, and who are comfortable with a closed-source, optionally paid client.
Pros
- Spawns the real claude binary, so subagents, MCP, hooks and skills all work
- Tabs, panes, visual diffs and always-visible 5h/7d usage meters
- Background agents with git branch and worktree isolation
Cons
- Proprietary and closed source with paid tiers; free demo is capped
- Licence re-verifies weekly over the network
Similar subagents & agents
All agent workflows & frameworks →Spec Kit 🤖 AgentFree
GitHub's toolkit for spec-driven development with AI coding agents
Task Master 🤖 AgentFree
AI task management that turns a PRD into tasks your coding agent works through
Fast Agent 🤖 AgentOpen source
Python framework for building, orchestrating and evaluating MCP-native AI agents
OpenSpec 🤖 AgentFree
Lightweight spec-driven development: agree on changes before the agent codes
CC Safety Net 🤖 AgentOpen source
Pre-execution guard that blocks destructive commands and secret access for coding agents
BMAD Method 🤖 AgentFree
Agile AI-driven development with analyst, PM, architect, developer and UX agents