Tmux-backed agent sessions
Every agent is a real tmux session, so quitting the manager does not stop the underlying work. This makes the UI a control surface rather than the runtime itself.
agent-manager
Freemium
Uma TUI desenvolvida em Go para gerenciar agentes de programação com IA pelo tmux. Inicie agentes, envie prompts, revise resultados e retome tarefas sem sair da lista de sessões.
O que é agent-manager?
agent-manager is a Go TUI that sits on top of tmux and treats every AI coding agent as a real tmux session. It is designed to help developers start agents quickly, respond to blocked agents in place, and review code changes without leaving the session list.
The product’s core workflow is centered on key-driven session management. You can spawn a new agent from a group row, answer an active session without attaching to the terminal, and open a dedicated review view for the selected session’s repository and diff. The documentation also shows that each session runs the user’s installed CLI as-is, preserving the user’s login, config, MCP servers, and other features from the underlying tool.
agent-manager keeps sessions organized in a tree of groups and subgroups, with support for folding, reordering, archiving, and plain terminal tabs. It also includes MCP tools so agents can declare the repo they moved into, the branch they merge into, and their session name, which helps the manager open review in the right place.
O que agent-manager pode fazer?
Spawn from the session list
Press space on a group row to start a new agent with a prompt and directory already set. The prompt is sent as a sentence, so you can create sessions quickly without forms or extra navigation.
Answer blocked agents in place
On a session row, the same key sends a reply into the agent’s pane as a user message. That lets you answer questions or permission prompts without attaching to the session.
Review diffs inside the app
ctrl+r opens a review mode for the selected session’s repo, showing changed files, diff counts, syntax-highlighted content, and review-specific key handling. The review view refreshes as the agent keeps editing.
Organize work in nested groups
Groups are paths rather than fixed folders, and sessions can live at any node. You can fold and unfold groups, reorder sessions and groups, and archive finished work while keeping the hierarchy intact.
Session lifecycle controls
The manager can kill a tmux session to free RAM while keeping the row and conversation record, then revive the same thread later through the agent’s resume command. It also supports forking a named sibling session from the same conversation.
Casos de uso
“Running several coding agents at once”
Useful when you want multiple tasks in flight across different projects or directories. The list view is built to show several agents at once and start them one after another with minimal interruption.
“Replying to an agent that is waiting on input”
When an agent is blocked on a question or permission prompt, you can respond directly from the session list instead of attaching to the terminal pane.
“Reviewing changes without switching tools”
If an agent is actively editing code, you can open review mode from the same interface, inspect the diff, and send line comments back to the agent.
“Keeping related work organized by repo or branch”
The group tree and MCP declarations help when one umbrella directory contains multiple repositories or worktrees, making it easier to open review on the correct target.
“Managing long-running or paused sessions”
If you need to reclaim resources, you can end the tmux process while keeping the conversation record, then resume or fork the work later.
Perguntas frequentes
What is agent-manager?
agent-manager is a Go TUI for coordinating AI coding agents that run as tmux sessions. It lets you spawn agents, answer them, review diffs, and manage session history from one interface.
Does quitting agent-manager stop my agents?
No. The docs say the agent sessions are real tmux sessions, so they keep running after the manager exits.
How do I start a new agent?
From the session list, you can press space on a group row, type the task, and press enter. The agent starts with its prompt and directory already set.
Can I review changes inside the app?
Yes. ctrl+r opens a review mode that shows the selected session’s repo diff, lets you inspect changes, and allows line comments that are sent back to the agent.
What platform does it support?
The site lists macOS, Linux, and WSL, and the install example uses Homebrew.
Informações rápidas
- Category
- Developer Tool
- Interface
- Go TUI
- Runtime
- tmux
- Supported platforms
- macOS, Linux, and WSL
- License
- Apache-2.0
- Primary workflow
- Spawn, answer, review, resume, and organize AI coding agents from a session list
- Installation example
- brew install yoanwai/tap/agent-manager
- Source domain
- agent-manager.dev
Análise de tráfego de agent-manager
Os dados de tráfego são apenas para referência.
- Classificação do domínio
- 8
Alternativas ao agent-manager
Superset
superset.sh
Superset é uma ferramenta para desktop que permite executar vários agentes de programação com AI em paralelo na sua própria máquina. Separe o trabalho em Git worktrees isolados, revise alterações e avance nas tarefas sem esperar por um agente de cada vez.
Kilo Code
kilo.ai
Kilo Code é um plugin de programação com IA multiagente para JetBrains IDEs. Desenvolvedores podem executar e gerenciar agentes de programação com IA, revisar alterações em worktrees isolados e escolher entre um amplo catálogo de modelos sem sair do IDE.
Cosyra
cosyra.com
Cosyra é um terminal móvel na nuvem para desenvolvedores que querem executar agentes de programação com IA pelo iPhone ou Android sem gerenciar o próprio VPS. Oferece um ambiente de trabalho Ubuntu isolado, armazenamento persistente e cobrança com a sua própria chave de API.
Diffsmith
apps.mergeable.io
Diffsmith é um app nativo para macOS que permite revisar alterações locais de git feitas por agentes de programação com IA, como Claude Code, Cursor, Codex e Copilot. Adicione comentários em linha e envie-os ao agente como prompt ou por meio de um servidor MCP local.
Argos
www.tryargos.cc
Argos é uma extensão do Chrome e uma ferramenta de automação para desktop e navegador que permite abrir abas, preencher formulários, pesquisar temas e concluir tarefas no navegador com sessão iniciada. Também inclui uma CLI que pode ser executada localmente e controlada pelo Telegram.
MiniMax
minimaxi.com
MiniMax é uma plataforma de inteligência artificial de uso geral que oferece grandes modelos multimodais, uma plataforma aberta para desenvolvedores e produtos por assinatura para indivíduos e equipes. É indicada para quem precisa de programação, tarefas com agentes, processamento multimodal e integração de aplicações nativas de AI.