Read the project README and summarize the cockpit
Read the project README and summarize the cockpit
Waiting
Do the task
Read the project README and tell me what cezar does.
· worktree ready — branch
cez/2d012907 (base main)<div align="center"> # cezar ⚡ **Parallel coding agents orchestrator** — a local cockpit for running and tracking AI coding-agent tasks in your repo. Type a task, pick a workflow and an agent — **Claude Code, Codex or OpenCode, or a mix of them per step** — and watch it work live: steps, tool calls, tokens, diffs, in a browser cockpit that runs entirely on your machine. Your CLI logins, your `gh`, your files. No accounts, no database, no cloud.
cezar is a parallel coding agents orchestrator — a local cockpit for running and tracking AI coding-agent tasks in your repo. You type a task, pick a workflow and an agent (Claude Code, Codex or OpenCode, or a mix of them per step), and it does the rest on your machine — no accounts, no database, no cloud.
- Parallel worktrees — every task runs on its own branch in an isolated git worktree (this one is on
cez/2d012907), so agents never trample each other. - Live streaming — steps, tool calls, tokens and diffs stream into the browser cockpit as they happen, so you can watch a run work in real time.
- Review gate — finished runs park at a review step where you read the diff, send notes back, or draft a PR before anything merges.
Under the hood each backend is a pluggable runner behind one interface:
ts
const runner = createRunner('claude')
const run = await runner.start({ workflow: 'quick-task', base: 'main' })
run.events.on('text', (chunk) => thread.append(chunk)) // live stream
Audit the auth flow
general-purpose
Found it: src/middleware.ts:12
4 tools
Review the store layer
code-reviewer
Ran npm test -- runs/store
2 tools
Check the migration path
general-purpose
starting…
0 tools
Read README and docs
Map the run lifecycle
Summarize cockpit features
in progress
Write the summary reply
The agent is paused, waiting for your reply