Single view of agent activity
Shows the activity of your agents in one widget so you can scan what is happening without switching between tools.
Tablo is a tiny floating desktop widget that monitors Claude Code and OpenAI Codex sessions from a corner of your screen. It shows live context usage, approval prompts, and session status so you can keep track of agent work without opening each session.
Tablo is a tiny floating desktop widget that watches coding agents such as Claude Code and OpenAI Codex from a corner of your screen. It is designed to give you a compact view of what your agents are doing while keeping approvals and context warnings close at hand.
The page emphasizes a quiet, always-visible workflow: Tablo sits in the menu bar, follows you across spaces, and surfaces per-session activity, live context meters, and permission prompts. A demo on the site shows the widget tracking multiple sessions and highlighting where input is needed.
Shows the activity of your agents in one widget so you can scan what is happening without switching between tools.
Displays live context usage per session and warns when a context window crosses a threshold.
Lets you approve or deny a tool call with a tap, giving you a quick gate for risky actions.
Sends a notification when an agent needs input or an approval, so you do not have to watch the session constantly.
Can jump directly into a session from the widget, marked as experimental on the page.
Includes a dashboard with per-session live activity preview and current state information such as waiting, working, and source.
Keep an eye on several agent sessions at once and see which one is waiting, working, or asking for input without opening each session separately.
Review context usage as sessions run so you can notice when an agent is nearing its limit and may need intervention.
Approve or deny actions that need a human decision, such as tool calls or potentially risky commands, directly from the widget.
Stay informed through desktop notifications when an agent pauses for input, which helps if you are doing other work nearby.
Use the session dashboard and jump link to move from a summary view into the underlying session when you want more detail.
Tablo is a desktop widget that sits in a corner of your screen and monitors Claude Code and OpenAI Codex activity. It shows live context usage, permission requests, and session status so you can follow agent work without opening each terminal or app window.
The source shows an install command for macOS, Linux, and Windows, with separate scripts for each platform. The product page says core monitoring works on Windows and Linux, while some features are experimental there; it is optimized for macOS.
Yes. The page presents Tablo as a desktop widget and includes a live demo built for desktops. It also says the widget sits in the menu bar and follows you across spaces.
The source does not show a public pricing page and the pricing URL returns a not found page. The homepage describes Tablo as local, free, and open-source.
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.
Ghost é um assistente de IA para terminal, para conversar, gerar código e executar tarefas no prompt. Traz modelos gratuitos, funciona no Linux, macOS e Windows e é open source.