Streetlight
Free, no-account AI support for people navigating housing instability,
paperwork, benefits, and hard decisions in Seattle / King County.
Anonymous by default. No accounts, no PII retention, no ads, no upsell, no
data harvesting, no premium tier. Open source from day one.
A software engineer in SOMA uses Claude every day. He pays $20/month and
it's a rounding error in his budget. A guy sleeping in a shelter ten
blocks away has the exact same brain. Often harder problems. Zero access.
That gap is not a moral failure on his part. It's an access gap. This
project closes it, in one city, for one population, as a public utility.
Status
Pre-launch. V1 in development. Soft-launch through named frontline partners
when the build is ready.
Documents
Project structure
This is a one-person, one-year commitment with a graceful sunset path if no
institutional home is found by year-end. The about page is honest about
this. Code stays public on GitHub regardless.
Useful commands
npm run lintnpm run dev:mock — runs the app with zero-cost local mock chat repliesnpm run dev:live — runs the app against the configured live model pathnpm run buildnpm run check:audit — runs npm audit for dependency advisoriesnpm run check:localesnpm run check:locales:summary — quieter locale-gap summary for routine
verification loopsnpm run check:launch — static soft-launch readiness check for docs,
placeholders, translations, and env contractnpm run check:env — validates local/env-example boolean and numeric value
shapes without printing secretsnpm run check:forbidden-integrations — fails if forbidden analytics,
error-reporting, or log-forwarding packages are addednpm run check:no-tracked-secrets — scans tracked files for common
secret-shaped values before pushnpm run check:ops — dry-run validation for the incident and ops helper
scriptsnpm run check:response-style — runs live brief-first response-shape cases
against the configured /api/chat pathnpm run check:translation-worklist — verifies that the generated
translation worklist is currentnpm run cost:status — shows the local model pair and whether cheap local
mode is activenpm run diagnostics:local — prints the current local server mode and the
report-page metadata snapshotnpm run ops:status — prints the local health, deploy metadata, model mode,
and any launch-doc placeholders still hanging aroundnpm run build:translation-worklistnpm run incident:new -- --slug short-name --severity Sev-2 — scaffolds a
public Sev-1/Sev-2 incident write-up from incidents/TEMPLATE.mdnpm run incident:sev3 -- --what "..." --action "..." --outcome "..." —
appends a structured Sev-3 note to incidents/log.md- add
--dry-run true to either incident command if you want a preview without
writing files
npm run validate:data — validates referral/crisis schema plus source and
last-verified metadatanpm run data:status — shows the oldest referral/crisis entries and whether
any have drifted past the freshness thresholdnpm run smoke — checks key pages plus a small synthetic end-to-end chat
flow against or
npm run dev:mock is for zero-cost local UI work. npm run dev:live is the
easy way back to real model calls. Full prompt regression still expects live
model replies, so npm run regression:prompts will stop with a clear message
while mock mode is active. Use npm run regression:mock for a full no-spend
plumbing pass. The GitHub Actions Verify workflow runs the full mock suite on
PRs and pushes to main; run npm run regression:prompts with the Haiku
testing model path before model, prompt, or deploy changes where live behavior
matters. Run npm run check:response-style after prompt changes that affect
answer length or structure.
Utility routes
/healthz — simple no-store JSON health check for local smoke checks and
future monitoring/report-problem — structured no-content bug report draft builder that
stays client-side and opens a mailto: draft
License
Licensed under the Apache License, Version 2.0. See LICENSE.
Contact
Bug reports currently go to [email protected].
