polter
Active·★ 20·MIT·Updated 2026-10-22
Polter is a tool that enables a single Claude Code session to act as a supervisor, coordinating and managing multiple other AI agent sessions. It allows the supervisor to read screen text, type commands, open new tabs, and distribute tasks, making it ideal for automating complex, multi-agent workflows.
#Agent Orchestration#Multi-Agent System#Terminal Automation#LLM Supervision#Workflow Automation#Session Management#Developer Tooling
01
Features
01Supervisor agent can read and type into worker terminals.
02Ability to open new tabs and start agents.
03Group chat and task distribution panel for agent coordination.
04Monitor agent activity by tracking terminal stillness.
02
Compatibility
macOS
Operating System
Verified via docs
Windows
Operating System
Verified via docs
Linux
Operating System
Verified via docs
Claude Code
AI Agent CLI
Verified via docs
MCP Protocol
Integration Standard
Verified via docs
03
Quick start
1
$ unzip Polter-*-macos-universal.zip
2
$ xattr -dr com.apple.quarantine Polter.app
3
$ mv Polter.app /Applications/
04
Use cases
↳Orchestrating multiple AI agent sessions for large-scale development tasks.
↳Automating long-running, multi-step coding or data processing jobs performed by AI.
↳Supervising and managing AI agents' progress and task distribution over extended periods.
05
Alternatives
unterm★ 15
The terminal AI agents can drive — and the cockpit to run them from. 99 MCP methods / 21 namespaces, agent Inbox, verified worktree fleets, diff review & rollback. macOS / Linux / Windows, local-first, $0, MIT.
multi-llm-mcp-728★ 56
一个让 Claude Code 调用 Codex 干活，并可以同时调用多个模型（GPT、Kimi、DeepSeek 等）的 MCP 工具。
archie-hq★ 16
AI employee for your team — delegate real work in Slack and a team of Claude-powered agents gets it done. Built on the Claude Agent SDK with OS-level sandboxing, MCP tools, and a plugin architecture. TypeScript/Node.
agent-manager★ 615
The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.
vibops-mcp★ 19
74 MCP tools for GPU infrastructure + Agent FinOps — deploy LLMs, track cost per agent, enforce budgets and model policies. Works with Claude, Cursor, n8n, LangChain.
vhk★ 12
VHK — AI 코딩 세션을 목표·증거·기억·규칙으로 묶는 한국어 CLI. 규칙 동기화, MCP 35 tools, verify/review/preflight 게이트.
Comments
Log in to leave a comment
No comments yet. Be the first!