Project AIR is an open-source toolkit that keeps a tamper-proof record of what AI agents do. Every action an agent takes gets signed, chained to the step before it, and tied to the person who authorized it. The chain is anchored to Sigstore Rekor, a public transparency log, so anyone can check later that nothing was changed or deleted. When something goes wrong, you can show exactly what happened and who approved it, instead of just saying it happened.
It also runs 16 detectors over every record, covering all ten risks on the OWASP Top 10 for Agentic Applications, three from the OWASP list for LLM apps, and three of its own. It can stop an agent mid-action until a person signs off. It plugs into LangChain, LlamaIndex, and the OpenAI, Anthropic and Gemini SDKs with a line or two of code.
I built the Python library and command-line tool, published on PyPI as projectair (now at version 1.3.1) under the Apache 2.0 license, plus the website and dashboard in SvelteKit. We run it on our own infrastructure too: every request to vindicara.io (http://vindicara.io) is recorded and anchored to Rekor every minute.
7
3
819
AgRisk – Digital Farmer Profiling & Risk Assessment Platform
AgRisk is a platform we built to help agricultural partners, lenders, and organizations better evaluate and support smallholder farmers. Farmers complete a simple digital application, and the system captures key data such as identity details, farm information, location coordinates, land size, and activity type.
The platform then structures this data into a clear farmer profile and risk overview that partners can use for decision-making, monitoring, and eligibility assessment.
The result is a scalable digital infrastructure that makes it easier to identify legitimate farmers, assess risk, and deploy capital or resources more efficiently in agriculture.
0
126
Built a job-search workflow that turns scattered job listings into a structured review pipeline.
The system collects job descriptions, removes duplicates and irrelevant roles, evaluates opportunities against configurable preferences, and organizes promising positions for human review. It also supports role-specific resume matching and generates traceable summaries so application decisions remain consistent and explainable.
Built with Python, structured data processing, browser automation, and AI-assisted evaluation.
1
61
