... Your coding agent is still working on your desktop when you leave. Termexo v0.10.0 lets you reconnect to that same workbench from a phone or another computer, across networks, through a self-hosted relay. The desktop opens an outbound tunnel, so it needs no public IP or router port forwarding. Open the relay address in a phone or another computer s browser to check terminal output, respond to your agent and keep working in the same workbench. Self-host termexo

... Termexo v0.8.6 AI-generated release illustration I maintain Termexo

... Termexo s maintainer, I am focusing on a practical problem: several agents can be working while the developer is still finding terminals, checking who needs approval and reconstructing task context. For individual developers, Termexo

... Maintainer update: Termexo v0.9.0 is out for Windows 10/11 x64. Antigravity joins Claude Code, Codex CLI and OpenCode, with local conversation resume, model and reasoning controls, /usage allowance and live activity status. This release also adds vendor Windows installer choices for supported CLIs, a direct install entry when an agent is missing, change-block diff navigation (Alt+Up/Down), and fixes long lines crossing split-diff columns. OpenCode completion and waiting states now better match the actual turn. npm supports version ...

... Existing workbench screenshot (v0.8.0), shown for context. I'm the maintainer of Termexo, an MIT-licensed Windows workspace for Claude Code, Codex and OpenCode. v0.8.7 focuses on a frustrating reliability problem: an agent could keep running while its terminal went blank and appeared stopped. Resizing around a wide character could trigger a parser panic, poison the screen mutex and leave subsequent screen reads failing. Switching between clients could reproduce that combination. The screen model now uses avt, the terminal model ...

... Maker update: Termexo v0.8.5 is out. I maintain this MIT-licensed Windows workbench for Claude Code, Codex CLI, OpenCode and real terminals. More consistent terminal behavior The EXE, MSI and npm packages now bundle Microsoft's MIT-licensed ConPTY components. Older Windows ConPTY builds can lose Shift+Tab or mouse reports, affecting Claude Code shortcuts and OpenCode scrolling. Using a bundled version reduces these OS-version differences and adds about 600 KB to the installer. The frontend also detects ... ... live session. Remote access is off by default and intended for trusted LAN/VPN connections, with self-signed HTTPS and an access token that must be kept private. Release notes and installers Website Source You can also launch with npx termexo

... Maker update: Termexo v0.8.2 is out today. This release focuses on typing responsiveness while multiple agents produce output. Output now uses one application-wide subscription with routing by terminal ID, reducing duplicate callbacks and UI work. History replay restores the terminal display without reprocessing old output through task, handoff, and startup readers. Draft persistence is batched, and terminal size ownership is handled on focus/click instead of every keystroke. Also new: Claude 1M context configuration, separate Claude/Codex effort settings, per-terminal ... ... launch overrides, and direct agent buttons in empty workspaces. Actual context and effort support depends on the CLI, model, account, and provider. Termexo

... Maker update: Termexo v0.8.3 is out. I maintain this MIT-licensed Windows workbench for Claude Code, Codex CLI, OpenCode and real terminals. If typing has felt delayed while agents are working, this is an update worth installing. Give keystrokes room to run Git queries and event synchronization previously queued on the same IPC thread as terminal input. The release moves background commands to a thread pool. The official release reports key-input latency p99 falling from ...

... Port22 and AgentMicro yesterday. Termexo and TreeWork today. Four launches inside 48 hours whose core job is telling you what your coding agents are doing and which one is stuck. When four teams independently build the same wrapper in two days, that isn't a market forming. It's a primitive the agent runtimes should have shipped and didn't. Every one of them is solving the same thing. An agent can be working, blocked, done or failed, and there ...