Software Factory Feature Matrix

This matrix compares the members of the Software factory category: repeatable agents-plus-code production pipelines, where deterministic code owns the loop and agents are bounded nodes inside it. Everything below was re-verified against live sources on 2026-09-13.

The deciding question for this category is who owns the loop: a factory puts phase sequencing, retries, and acceptance in code, and an agent owns only the work inside one bounded phase.

Legend: ✓ supported, ✗ not supported, ~ partial or conditional, ? not verified as of the date above. Each column links to the full research note; every cell below traces to a source cited there or in the references.

The matrix

#

Reading the matrix

#

The loop-owner row is the whole category in one glance: SSSF and Fluent move the loop into code (Python ADWs, a Rust scheduler) while HAR coordinates a fleet but leaves each agent free to edit, which is why its acceptance is verify-focused rather than loop-owned. A factory is defined by determinism, and HAR earns its place through deterministic verification rather than deterministic sequencing.

The isolation row is where the category separates from a single long agent call: Fluent and HAR isolate every candidate in its own worktree, while SSSF deliberately runs on the current branch with no sandbox or merge step, the gap its own note names first.

The self-improvement row is still a two-horse race: Fluent writes reusable Expertise after accepted changes, and Ouroboros refines specs and accumulates assets across a budgeted evolution loop, while SSSF, HAR, and Machinist stay deliberately static. The difference is what compounds: Fluent compounds lessons about the code, Ouroboros compounds the specification itself.

The hidden-grading row is Ouroboros’ claim to a distinct cell: it is the only member that structurally withholds the grading command and expected result from the worker agent, an anti-reward-hacking design none of the others attempt.

The narrow columns are candid: SSSF’s pi-only dependency versus the open agent matrix of Fluent and HAR is the single biggest reason to look past the founding member’s headline ease. Ouroboros runs the other direction with 14 runtimes, the widest agent boundary in the category, paid for in evaluation tokens and beta churn. Machinist narrows the boundary in the other direction: its named-command entrypoint is the category’s strictest agent interface, paid for with no built-in isolation and restart-from-zero failure semantics.

The rejected long tail: agentic-software-factory (1 star, inflated agent counts), ai-factory (4 stars, no license), and Takk8IS/software-factory (0 stars, no license) did not clear the citation or credibility bar and are named here so no future run re-adds them silently.

Choosing from the matrix

#

• Want the easiest code-owned loop on a single agent and will wire your own gates: Super Simple Software Factory.
• Want a self-improving factory with a real final Tester and worktree isolation, pre-1.0 accepted: Fluent.
• Want a fleet of coding agents on one repo with deterministic verification and evidence, keeping your agents: HAR.
• Want a local, auditable runner with a strict named-command boundary around any agent CLI, early-access accepted: Machinist.
• Want vague briefs turned into verified code with the grading hidden from the worker, 14 runtimes and beta churn accepted: Ouroboros.

Changes

#

• 2026-08-29 - Created as a single-column scaffold for SSSF when the Software factory category was seeded.
• 2026-08-29 - Rebuilt to three columns (SSSF, Fluent, HAR) with the who-owns-the-loop thesis.
• 2026-08-30 - Extended to four columns with Ouroboros, self-improvement and hidden-grading prose updated.
• 2026-08-30 - Re-sorted columns alphabetically with Fluent first, dropping the founding-member-first convention.
• 2026-09-05 - Extended from four to five columns with Machinist.
• 2026-09-13 - Added the Pricing row, recording HAR HQ’s first published pricing (Team $400 per month up to 50 users with $100 monthly cloud credits, Enterprise custom) alongside the free open-source core.

See also

#

• Code Factories: Factorio - the corpus metaphor this category turns into a tool taxonomy
• Hybrid Execution Feature Matrix - the deterministic-orchestrates-LLM principle at the structured-output layer
• Spec-driven Development Feature Matrix - the spec-first competitor to a full pipeline
• Harness Feature Matrix - the single coding agents these factories coordinate
• Executions Feature Matrix - scheduled and event-triggered runs versus an invoked factory

References

#

• https://github.com/disler/super-simple-software-factory - the founding column: architecture, envelopes, gates, and trace
• https://github.com/disler/super-simple-software-factory/tree/example - the stamped demo repo with real traces
• https://github.com/mrinalwadhwa/fluent - the Fluent column: scheduler, Tester, and Expertise loop
• https://github.com/os-factory/har - the HAR column: the .har contract, worktree isolation, and verify stage
• https://github.com/os-factory/har/releases - the release cadence grounding HAR’s row
• https://github.com/owainlewis/machinist - the Machinist column: named commands, executors, recording, license
• https://github.com/Q00/ouroboros - the Ouroboros column: the loop, the three-stage gate, and the hidden-grading design
• https://ouroboros.page/learn/en/evaluate/ - the gate stages and consensus triggers grounding the acceptance row