|
@wifo/factory-context
|
Filesystem-first context store — typed shared memory for agent phases, with content-addressable records and a DAG of provenance |
MIT |
10
greenflagged
/ 10 total
|
|
@wifo/factory-core
|
Universal spec format, schema, parser, and lint CLI for software factories |
MIT |
10
greenflagged
/ 10 total
|
|
@wifo/factory-harness
|
Scenario runner for software-factory specs — runs `test:` satisfaction lines and scores `judge:` lines via LLM |
MIT |
10
greenflagged
/ 10 total
|
|
@wifo/factory-runtime
|
Phase-graph runtime that composes core/harness/twin/context into an end-to-end agent pipeline — explore, plan, implement, validate, iterate until scenarios converge |
MIT |
10
greenflagged
/ 10 total
|
|
@wifo/factory-spec-review
|
LLM-judged spec quality reviewer — runs subscription-paid `claude -p` judges against software-factory specs and emits findings in factory-spec-lint's output format |
MIT |
10
greenflagged
/ 10 total
|
|
@wifo/factory-twin
|
Digital twin contract — record/replay external dependencies so agents can iterate without burning real API quota or real money |
MIT |
10
greenflagged
/ 10 total
|