Wenlan
Wenlan is a source-backed AI knowledge base and LLM wiki for AI work: organize documents and decisions into pages you can find, inspect, and review.
翻訳待ち
No updates detected yet. GitHub releases will appear here.
The maker's introduction consists of the line above. Read the repository README for more details. Repository README ↗
Loading the full README.
Read the full README ↗Flowgrid OS (codename "Operations Engine" until Aug 2026) — white-label, multi-tenant AI operations SaaS for UK SMBs (3–50 seats). One branded workspace per client: chat workspace, cited knowledge vault (RAG), cost-routed models via cloud APIs only: open-weight by default, Claude for tool turns and final drafts once plan item F5 lands (see ASSUMPTIONS #73).
Authoritative specification: docs/phase-1-build-spec.md.
| Path | What |
|---|---|
apps/web | Next.js frontend (tenant-themed workspace) |
apps/api | FastAPI backend — /api/v1, JWT auth, tenant RLS context |
apps/worker | arq worker — document parsing (Docling) + embedding |
infra | Docker Compose, LiteLLM config, deploy notes |
packages/shared | OpenAPI-generated TypeScript client |
docs | Product spec and plans |
# infra: Postgres (pgvector) + Redis
docker compose -f infra/docker-compose.dev.yml up -d
# api
cd apps/api
uv sync
cp .env.example .env
uv run alembic upgrade head
uv run uvicorn app.main:app --reload --port 8000
# web
cd apps/web
pnpm install
pnpm dev
Tests (includes the CI-blocking cross-tenant isolation suite):
cd apps/api && uv run pytest