# fabro-sh/fabro

⚒️ The open source dark software factory for expert engineers.

Repository: https://github.com/fabro-sh/fabro
Canonical: https://ross.abutalabs.com/products/fabro
Homepage: https://fabro.sh
Language: Rust
License: MIT
License Family: permissive
Last push: 2026-08-26T19:20:26+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 87, longevity 12
- inputs: {"age_days": 173, "days_push": 7, "days_rel": 90, "gap_med": 1.0, "n_releases_24m": 11}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1538, forks 168 (observed 2026-08-28T04:04:59.923295+00:00)

## What it is
Fabro is an open-source workflow orchestration engine that runs AI coding agents as version-controlled workflow graphs defined in Graphviz DOT, with human approval gates, multi-model routing, and deterministic verification steps. It ships as a single Rust binary with an API server, web UI, and isolated cloud sandboxes for long-running, unattended agent execution.

## Use cases
- orchestrate ai coding agents in repeatable workflows
- run ai agents unattended with verification gates
- route tasks across multiple llm providers to cut token costs
- run coding agents in isolated cloud sandboxes
- add human approval gates to agent pipelines
- run agent workflows 24/7 on a server
- encode team software processes as reviewable workflow code
- automatically fix code until tests and linters pass

## When to choose
- you want long-horizon agent runs without babysitting a REPL
- you need multi-model ensembles with per-node model routing
- you want deterministic verification and fix loops around agent work
- you need isolated cloud execution with git checkpointing and audit trails

## When to avoid
- you only need a simple single-agent chat or code completion
- you require native Windows support
- you want a lightweight editor plugin rather than a server-based orchestrator
- your workflows are short one-off prompts that don't need graph orchestration

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, workflow-automation, llm-inference, api-framework, http-server, secrets-management, deployment, cli, developer-tools
- domain: large-language-models, developer-tools, self-hosted
- platform: cli, self-hosted, rust
- tags: ai-agent-orchestration, workflow-graphs, multi-model-routing, human-in-the-loop, cloud-sandboxes, workflow-as-code, git-checkpointing, llm-as-judge, single-binary, agent-security, ai-agents, automation, devops, linux, macos, docker, web-server

## Member repositories
- fabro-sh/fabro (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:59.923295+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:57.257477+00:00, confidence not recorded.
  - readme: https://github.com/fabro-sh/fabro (fetched 2026-08-28T04:04:59.923295+00:00, sha 84852fb67162)
  - homepage: https://fabro.sh (fetched 2026-08-29T11:32:36.347879+00:00, sha 6f9d98a827c3)
  - site_page: https://docs.fabro.sh (fetched 2026-08-29T11:32:36.357091+00:00, sha 013a2ac58e06)
  - site_page: https://docs.fabro.sh/changelog (fetched 2026-08-29T11:32:36.359108+00:00, sha 52ee411680ef)
  - site_page: https://docs.fabro.sh/getting-started/quick-start (fetched 2026-08-29T11:32:36.361597+00:00, sha 54c099b80e83)
- Data as of 2026-08-30T08:39:29.467469+00:00.