conductor is a good parallel runner — agent sessions in isolated worktrees, with diffs for you to review. defract is a different kind of tool: a full pipeline that carries a story from idea to shipped — guided stages, agent-reviewed merges, and memory so you never re-load context. all of it built to lower the load in your head.
they share one thing. both defract and conductor run agents in parallel, each in its own git worktree, isolated so they don't collide — and both run on claude code as the engine. that's where the overlap ends. they're two separate apps making different bets: conductor bets on being a fast runner; defract bets on the whole path a story takes between “start” and “shipped.”
conductor gives you parallel agent sessions that you drive and track yourself. defract is built around a pipeline.
scope → design → architecture → implementation → review → release. you weigh in on the decisions at each gate; agents do the work in between. the structure lives in the tool, not in your head — so you stop holding the whole process in working memory.
conductor hands you raw diffs and makes you the reviewer of record. defract does the opposite.
types, lint and tests gate every merge, plus review agents for architecture, security and ux. code only progresses once it's signed off.
the review you do is on a dedicated surface for each phase — scope, design, architecture, implementation — not an 800-line diff. you review intent and shape, fast.
conductor sessions start largely fresh. defract remembers.
defract carries memory of your codebase, your decisions and your conventions — so you pick up monday exactly where you left off friday, without having to remember anything. and it compounds: every shipped story sharpens the next. the app gets smarter as it runs, and your life gets easier.
| defract | conductor | |
|---|---|---|
| unit of work | a story shipped to production | a parallel agent session |
| structure | guided pipeline: scope → design → architecture → implementation → review → release | open agent sessions you drive and track yourself |
| code review | agents review agents (types · lint · tests · architecture · security · ux); merge gated on sign-off | you review the diffs yourself |
| what you review | purpose-built uis per phase — intent and shape | raw diffs |
| memory / context | persistent memory of codebase, decisions, conventions — compounds over time | no built-in cross-session memory |
| parallel git worktrees | ›yes parity | ›yes |
| models today | claude code (codex · gemini · opencode in v1) | claude code + codex, multi-model compare |
| platform | macos (windows · linux in v1) | macos |
| availability | open beta — download now | available now |
we'll be straight: conductor is shipping now, it's mac-native and mature, and it already runs codex and multi-model compare. if you want a slick parallel runner today and you're happy being the reviewer, it's a reasonable pick.
defract is in open beta — claude code on macos for now, with codex, gemini, opencode and windows + linux landing in v1. the bet we're asking you to make is on the workflow and the lower cognitive load, not on a feature count.
download the open beta. if you've lived in conductor, we'd especially love your eyes on it.