PRADEEP.md

agenthook: give your coding agent a webhook-backed inbox

Mon, 14 Sep 2026 12:00:00 +0000

It’s annoying when you’re working inside a coding agent, doing something with an external service that takes more time than a single turn. For example, a github deploy. Unless the agent is monitoring (which blocks the execution), we might not know.

mailcheck 2.0

Mon, 14 Sep 2026 00:00:00 +0000

Some libraries get old in a good way. They do one useful thing, people copy them into their product, and then nobody needs to think about them for years.

Flyiverse: a field guide to the fly brain’s strange internet life

Thu, 10 Sep 2026 00:00:00 +0000

A fly’s nervous system gets mapped by researchers. And somehow, someone looks at the wiring diagram and asks the eternal question - can it play Doom?

The One Pizza Startup

Tue, 30 Jun 2026 00:00:00 +0000

Around December 2025, seasoned engineers noticed that frontier coding models now generated consistently high-quality code at a low cost. This has changed the dynamics of starting companies.

Om

Thu, 25 Jun 2026 00:00:00 +0000

Writing about someone who wrote for the sheer joy of it is not easy, but I will try.

Running 4B+ models on Apple's Neural Engine

Mon, 30 Mar 2026 00:00:00 +0000

TL;DR:

4B and 9B models on ANE, bypassing CoreML entirely
11.66 tok/s single-stream, 28.62 tok/s with four concurrent streams — GPU and CPU idle
Same 16-core ANE on every M1 through M5, regardless of SKU
Bottleneck is dispatch overhead, not compute or bandwidth
Code: ane.cpp + field guide

My Coding Agent Watches Me Get Frustrated, Then Fixes Itself

Fri, 20 Feb 2026 00:00:00 +0000

pi-mem: surprisingly useful plain-md memory for the pi coding agent

Wed, 11 Feb 2026 00:00:00 +0000

camofox-browser: An OpenClaw Browser That Doesn't Get Blocked

Tue, 10 Feb 2026 00:00:00 +0000

safe-skill-search: Quality-Filtered Local Search for Agent Skills

Tue, 03 Feb 2026 00:00:00 +0000

In my previous post, I analyzed 4,784 AI agent skills across 5 registries. An agent needs to navigate this space quickly and safely.

Agent Skills: 59% Ship Scripts. 12% Are Empty.

Tue, 03 Feb 2026 00:00:00 +0000

TL;DR:

4,784 skills scraped from 5 registries
Average quality score ~78, 31% score 90+
28% are duplicates
~10% install packages via npm/pip
No verification, no provenance
Treat like early npm—read what you install
Browse all skills →