StackMap
Subscribe

fabro vs zeroshot

Rust 'software factory' for coding agents: define the SDLC as a graph, agents execute it through verification gates, you intervene only at the stages that matter. Server, runs board, sandboxes. — versus — Executor–verifier orchestration for code changes: a conductor classifies the task, an executor works in an isolated worktree, and a separate verifier must reproduce the evidence — looped to approval.

The curated verdict

Same conviction — agent output must pass gates — different locus of control. In Fabro you define the SDLC graph and the gates; Zeroshot ships an opinionated conductor that sizes each task and picks the workflow for you.

fabrozeroshot
Stars1.5k1.8k
Forks168165
LanguageRustJavaScript
LicenseMITMIT
Last activityyesterdaytoday
Topicscoding, orchestrationcoding, orchestration
Curated connections46

fabro — the curator's take

For the team past the babysit-or-rubber-stamp dilemma: encode your process as a version-controlled workflow graph — implement with one model, cross-critique with another, gate on verification — and let the API server run it 24/7, locally or in isolated cloud sandboxes. CSS-like stylesheets for model routing is a genuinely clever cost lever. NOT a quick add-on: this is infrastructure with a server, a web wizard and a process philosophy — solo devs wanting lighter structure should look at terminal-first orchestrators first. Young project; the 'dark factory' ambition is ahead of the ecosystem's verification reality, so keep the gates strict.

zeroshot — the curator's take

Built on one good sentence: the agent that wrote the code shouldn't be the one that says it works. A conductor scores every task on complexity (TRIVIAL→CRITICAL) and type (INQUIRY/TASK/DEBUG) with a junior model, escalating to a senior model when it answers UNCERTAIN, and that score picks the workflow — from single-worker with no validator up to debug pipelines with investigator/fixer/tester/completion-detector. Validators never share the executor's session or reasoning, and must reproduce reported failures. Runs default in a git worktree, keeps a crash-safe SQLite ledger, brings your own provider CLI and stores no keys. Reach for it when unattended runs need to be trustworthy, not fast. Skip it for interactive pair-programming: multi-agent verification loops cost several times a single agent's tokens and can run 90 minutes for one change. Linux and macOS only; the bundled Rust product is a separate, newer track.