paneflow
Active·★ 87·GPL-3.0·Updated 2026-10-21
Paneflow is a native GPUI workspace designed for running multiple coding agents in parallel, providing real terminal panes and live status tracking. It aims to solve the coordination problem of supervising many agent sessions by offering a visual interface, worktree diff review, and a local control plane for orchestration.
#Coding Agents#Multi-Agent#Workflow Orchestration#Developer Tools#Parallel Processing#Terminal Workspace#Rust#GPUI
01
Features
01Real terminal panes for running various coding agents with live status updates.
02Local CLI and JSON-RPC control plane for scripted orchestration and workflow execution.
03Read-only Multi-Agent Communication Protocol (MCP) bridge allowing agents to safely inspect each other's output.
04Side-by-side review surface for comparing worktree diffs generated by agents.
05Native runtime built with Rust and GPUI for high performance across Linux, macOS, and Windows.
02
Compatibility
Linux
OS
Verified via docs
macOS
OS
Verified via docs
Windows
OS
Verified via docs
Rust
Runtime
Verified via docs
GPUI
Framework
Verified via docs
03
Quick start
1
$ brew tap arthurdev44/paneflow
2
$ brew install --cask paneflow
04
Use cases
↳Supervising multiple AI coding agents working on different tasks simultaneously.
↳Orchestrating complex development workflows involving a fleet of coordinated agents.
↳Reviewing and managing code changes generated by AI agents in dedicated branches or worktrees.
↳Debugging and monitoring agent activities through visible terminal output and live status updates.
05
Alternatives
hadron★ 27
A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.
Agenvoy★ 489
Make AI actually work for you - A personal agent that writes its own tools and repairs itself.
piyaz★ 196
The agentic workspace where people and AI coding agents work together on every project.
ask-user-questions-mcp★ 147
Better 'AskUserQuestion' - A lightweight MCP server/OpenCode plugin/Agent Skills + CLI tool that allows your LLMs ask questions to you. Be the human in the human-in-the-loop!
pydantic-deepagents★ 1.1k
Python Deep Agent framework built on top of Pydantic-AI designed to help you quickly build production-grade autonomous agents with planning, filesystem operations, subagent delegation, and skills.
dos-kernel★ 20
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
squadra★ 297
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
Comments
Log in to leave a comment
No comments yet. Be the first!