euk ela

I'm learning software development by building real products. My current focus is backend development, AI-powered apps, APIs, and practical engineering workflows.

Joined on Jun 22, 2026

euk ela

Aug 12

A Coding Agent's Minimal Loop: 767 Lines of TypeScript with Zero Dependencies

#ai #opensource #typescript #devtools

3 min read

Want to connect with euk ela?

Create an account to connect with euk ela. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

euk ela

Aug 11

The 116 Token Cut: A Source-Level Look at Multi-Agent CAD (MAC)

#ai #opensource #agents

3 min read

euk ela

Aug 10

A 45M-Parameter Agentic Model in a 14MB Binary: Inside Cactus Needle 2

#ai #opensource #devtools

2 min read

euk ela

Aug 9

Claude Code Can't Draw — This Plugin Borrows Your Codex CLI Login

#ai #opensource #devtools #productivity

2 min read

euk ela

Aug 8

File provenance for the AI-agent era: evidence labels, not guesses

#ai #opensource #devtools #python

2 min read

euk ela

Aug 7

Don't Read the Code Your Agent Wrote — Make It Run the Gauntlet

#ai #opensource #testing #devtools

3 min read

euk ela

Aug 6

DeepSeek V4 Flash Went Official: Checking the 'Flash Beats Pro' Claim Against the Model Card and config.json

#ai #opensource #moe #llm

3 min read

euk ela

Aug 6

How a 176 KB C Binary Runs a 2.78-Trillion-Parameter Model on One CPU with 8 GB of RAM

#ai #opensource #systems #moe

4 min read

euk ela

Aug 4

AI Technical Figures Need an Editability Test, Not Just a Similarity Score

#ai #opensource #devtools #productivity

2 min read

euk ela

Aug 2

Skill Recorder: Turning One Human Workflow into a Reviewable Agent Procedure

#ai #opensource #automation #devtools

2 min read

euk ela

Aug 1

Coding-agent rules need a feedback loop after the edit

#ai #opensource #devtools #codereview

2 min read

euk ela

Jul 31

An Agent Hook Is Not a Security Boundary: Reading numbat's Coverage Matrix

#ai #opensource #security #devtools

3 min read

euk ela

Jul 29

Coding-agent cost needs evidence, not just a token dashboard

#ai #opensource #productivity #devtools

2 min read

euk ela

Jul 28

Before Sending Logs to an LLM, Reduce the Noise Into a Question

#ai #opensource #devtools #observability

2 min read

euk ela

Jul 27

AI Learning Tools Should Preserve the Work, Not Just Generate the Answer

#ai #opensource #learning #devtools

2 min read

euk ela

Jul 26

An Agent Control Loop Is More Useful When You Can Explain Every Turn

#ai #opensource #typescript #devtools

1 min read

euk ela

Jul 25

AI Memory Is a Data-Retention System, Not a Longer Prompt

#ai #opensource #rust #dataprivacy

3 min read

euk ela

Jul 24

Generative UI Needs a Component Contract Before It Needs a Better Demo

#ai #opensource #reactnative #security

3 min read

euk ela

Jul 23

AI Agents Need Request Boundaries, Not Just Hidden API Keys

#ai #security #opensource #devtools

2 min read

euk ela

Jul 22

An AI-Built App Is Not a Requirement Met: Reading QuantumByte's Read-Only Harness

#ai #opensource #devtools #testing

3 min read

euk ela

Jul 22

An Agent Harness Is Not a Security Boundary: Reading AgentSmith as a Workflow Layer

#ai #opensource #devtools #security

2 min read

euk ela

Jul 21

Save agent context without hiding failures: a look at lowfat

#ai #opensource #devtools #productivity

1 min read

euk ela

Jul 20

Multi-agent handoffs need receipts, not just more context

#ai #opensource #devtools #productivity

1 min read

euk ela

Jul 19

LLM Serving Has Three Bills: Prefill, Decode, and KV Cache

#ai #opensource #devops #cpp

1 min read

euk ela

Jul 16

A Disposable VM Is Not a Security Conclusion for Coding Agents

#ai #opensource #devtools #security

1 min read

euk ela

Jul 15

An Agentic IDE Needs an Authorization Model, Not a Longer Safety Prompt

#ai #opensource #devtools #security

1 min read

euk ela

Jul 13

An AI Research Workbench Is Not a Sandbox

#ai #opensource #security #devtools

1 min read

euk ela

Jul 12

Do Not Add an LLM Router Until You Can Defend Each Downgrade

#ai #opensource #devtools #llm

2 min read

euk ela

Jul 11

Microsoft Flint Turns Agent-Made Charts Into a Compiler Problem

#ai #opensource #dataviz #mcp

2 min read

euk ela

Jul 9

OpenConnector: SaaS access for agents needs a runtime boundary, not more raw tokens

#ai #opensource #mcp #devtools

1 min read

euk ela

Jul 8

OpenConnector: SaaS access for agents needs a runtime boundary, not more raw tokens

1 min read

euk ela

Jun 26

Lathe turns LLM answers into traceable learning artifacts

1 min read