Blog
Chanakya v2: A 17-Agent Portfolio and Wealth Research Platform
Four months in, Chanakya has grown into a 17-agent research platform spanning market intelligence and personal finance: a quant-research module with dynamic correlation modeling and rigorous overfitting controls, a governance layer for tuning risk policy, and a complete financial ledger with tax-lot accounting, all reasoning across a real, dual-market portfolio every day.
Voqora: Listen to What You're Already Reading
Voqora is a native Mac app that reads selected text aloud and turns long documents into audiobooks you can follow line by line, with speech running on your Mac. It is in early release, and feedback, issues, and pull requests are welcome.
SuperSay: The Project That Led to Voqora
SuperSay was the first version of a native Mac reading-to-listening idea. The active product is now Voqora.
Chanakya: A 13-Agent Portfolio Brain, Engineered for Restraint
Inside a private, solo-built multi-agent LLM trading system — an event-driven Kafka pipeline where only 9 of 13 agents ever call an LLM, a Bull/Bear/Judge debate that's really one agent wearing three hats, and the production hardening (idempotent deduplication, tiered inference routing, on-device embeddings, circuit breakers) that keeps it running sustainably, every single day.
SuperZen: Engineering a Native macOS Wellness App That Doesn't Get in Your Way
A deep dive into SuperZen's architecture — a single 1Hz heartbeat driving the entire app, a profile-adaptive Focus Quality Score, privacy-first local-only telemetry, and the 36-hour hardening sprint that turned a two-day prototype into a licensed, accessible, publicly-releasable v1.1.10.
ytdld: Building a Live TUI on Top of a Library That Wasn't Built for One
yt-dlp is a synchronous, blocking library with no progress-separation, no cancellation API, and its own opinions about writing to your terminal. Here's how ytdld builds an 8-way-parallel, cancellable, retryable live dashboard on top of it anyway — without forking yt-dlp or fighting it.
BroSki: A Task Runner That Tells You Why It Reran
Why a Rust task runner needed transactional output promotion, content-addressed fingerprinting, and platform-aware sandboxing just to answer one question honestly: why did this rebuild?