Where operations meet the algorithm.
Sharp, open tools for the messy parts of real operations. Built in public and free to fork.
I experiment with AI and build tools to understand what problems it can solve, where the constraints are, and what stays questionable the moment you try to scale to enterprise level.
Every project here is a real operational problem turned into working code, not a demo. Everything is open: fork it, break it, send it back better.
// thoughts & insights
all heuristics →// from the lab
Global Operations Risk Monitor
Operations Risk Monitor is a multi-agent framework that watches operational risk across freight, fuel, labour, weather and geopolitics, then turns what it finds into briefings you can actually use. Seven specialist agents collect and filter the feeds into one weekly briefing.
Ship-Doc
Ship-Doc is shipment document control for physical trade: the pack checked against the shipping instruction, drafts approved by a named person, originals chased via Outlook. The model reads, fixed rules decide, a person approves.
PPWR Compliance Screener
PPWR Compliance Screener: checks supplier packaging declarations against Regulation (EU) 2025/40 for completeness and internal consistency. Deterministic verdicts. Suppliers get a signed link and a rule engine screens what comes back; no model issues a pass or a fail.
Procezio - Process Navigator
Procezio is a guided canvas for finding automation opportunities in the way you already work, with an AI agent working alongside you on the same board. Map the process, mark the friction, assess it, decide what to automate - the agent drafts in pencil and a human accepts.
OODAA
OODAA is a small, readable self-improving agent loop. Observe, Orient, Decide, Act, and the second A, Adjust: the phase that makes an agent get smarter across runs instead of only faster within one.
Sample Trail
Sample Trail is a sample management workflow for the agri-food and soft-commodities sectors - coffee, cocoa, grain, sugar, cotton. It runs the quality approval decision on a physical sample, from dispatch to verdict, on the phone the person is already holding.
FlowTwin
FlowTwin turns a recording of any operational process into editable process maps and runbooks that are adjustable, auditable, and kept current. The capture layer for tribal knowledge. Watch the process once; FlowTwin captures, segments, structures and publishes what it sees.
Orchestriq Core
Orchestriq Core is the kernel for agents that run real operations. Evals, approvals, earned autonomy and EU AI Act transparency live in the runtime, so every module inherits them. Spec, gate, park, earn - autonomy is a ladder climbed per action type on measured accuracy.
Auspex
Auspex is a prediction and forecasting harness for supply chain operations. Connect a table, pick a model, read the signs. Zero-shot tabular prediction and time-series forecasting behind one interface, with confidence intervals on every prediction, exposed as an MCP server.