Open Nshipyard cleans Canada's messy civic data, exposing $15.1B phantom spend, with MCP tools for agents
RichardsonDx · x · 2026-10-16
Open Nshipyard, an open-source project inspired by Build Canada, turns unusable government open data into open infrastructure: explorer interfaces for humans plus documented APIs and MCP tools for AI agents.
Starting with Toronto/Canadian civic data, it documents 722,000 hand-entered street-name variants, 57.8% non-numeric building-permit cost fields, and $15.1B of phantom spend inside published vendor totals. Sub-projects include a drug-shortage ranking (3 companies hold 29 of 59 critical shortages; 1,742 open ones have run 647 days) and a facility-identity table matching pollutant records to carbon emitters. One showcase finding: a new detached house pays $137,846 in Toronto development charges, while 2–6 homes on the same lot pay $0.
More from coding & agent
- Handwired compiles plain JavaScript into an exact, fully differentiable neural net — ctjlewis · 2026-10-16
- Temporal Serverless Workers on Cloud Run: queue-driven autoscaling, scale to zero — rseroter · 2026-10-16
- Meta's Superintelligence Lab Runs 200+ Direct Reports—A Lesson for Flat Multi-Agent Systems — peterjliu · 2026-10-16
- LangChain CEO: the most interesting agent harness work lives at the harness-infra boundary — hwchase17 · 2026-10-16
- GitSwarm paper: agents share branchable Git memory, solving all 30 IMOProofBench problems in one run — anirudhg9119 · 2026-10-16
- Hands-on with Gemini 4 Argon: faster than Opus 5.5 but hallucinates more and costs more — prasenx · 2026-10-16