One durable scope
A repository or folder, its connections, tasks, sessions, and launch configuration—kept together without hiding the filesystem.
project → tasks + sessionstermloop · native control room for coding agents
TermLoop puts tasks, worktrees, real terminals, diffs, and agent coordination in one native workspace—without replacing Claude Code or Codex.
Ask To
Ask one agent to consult another agent. TermLoop creates a visible helper Session, preserves the relationship, and returns the answer to the requester.
tree project
Projects hold the durable scope, Tasks describe work, and Sessions are the live agents and terminals operating inside that Project.
A repository or folder, its connections, tasks, sessions, and launch configuration—kept together without hiding the filesystem.
project → tasks + sessionsA Task can stay lightweight or get one managed Git worktree when the work needs its own branch and checkout.
task → 0..1 worktreeClaude, Codex, terminals, and dev runs stay Project-scoped. Select them, refresh them, fork context, or coordinate them directly.
session → agent | terminal | run6 essential workflows
A second opinion, a handoff, a fresh direction, and the tools to finish the change. Recorded in a working Launchpad demo Project.
Send a visible, composed handoff from one running Project Session to another. The target receives the brief in its own real terminal and continues from there.
Fork a Session from the sidebar, see the parent-child relationship, and continue in a new Ghostty terminal. The branch in thinking is explicit instead of becoming another anonymous tab.
Keep a clear brief, acceptance criteria and a small checklist attached to each Task.
Create a branch and managed worktree directly from a Task. Keep parallel changes in separate checkouts.
Read the diff, compare versions side by side and keep track of the files you have checked.
product principles
TermLoop launches the Claude and Codex CLIs you already trust and pay for. It never proxies or imitates them.
Branches, worktrees, processes, and files remain ordinary local resources you can inspect outside the app.
TermLoop-authored prompts are visible assets. Secret values stay out of durable state and public evidence.
Agent-to-agent requests, handoffs, terminals, diffs, and lifecycle changes are real product actions.
straight answers
The first-class agent launch paths are Claude Code and OpenAI Codex, alongside ordinary terminal and dev-run Sessions. TermLoop uses your existing provider sign-ins rather than proxying model traffic.
No. A Task can have zero or one worktree. Create the Task to track work; provision a managed checkout only when branch isolation is useful.
Yes. TermLoop does not impose a product-level write lease or artificial launch gate. You choose whether agents share a checkout or work in isolated Task worktrees.
Your code remains on your filesystem. Agents connect directly to their providers. TermLoop keeps secrets out of durable product state, logs, URLs, and generated evidence.
The current public desktop download is for macOS. TermLoop Next treats macOS, Linux, and Windows as release gates; broader availability follows verified native builds rather than an untested compatibility claim.
Yes. The companion pairs with a running desktop instance for Project visibility and terminal input. The public demo intentionally masks the one-time QR payload.
Yes. The public source and releases are available on GitHub, including the terminal and agent-workflow layers.
ready when you are
Download TermLoop and keep the whole engineering loop visible.