How I built an engineering toolkit for AI coding agents I spend most of my day working...
dtoolkit adds memory and observability to AI coding agents via SQLite, solving amnesia where sessions restart from zero. Multi-provider routing (Claude, Gemini, Codex) reduces vendor lock-in—critical for CTOs optimizing LLM selection and team productivity across providers.
How I built an engineering toolkit for AI coding agents
I spend most of my day working with AI coding agents — Claude Code, Gemini CLI, Codex, OpenCode. They're incredibly powerful, but they all share the same fundamental problems:
They forget everything. Every session starts from zero. Yesterday's decisions? Gone.
They don't know your project. File paths get hallucinated. Architecture gets ignored.
You can't see what they cost. Tokens, tools, errors — all a black box.
AI Coding Agents Still Forget Everything — So I Built the Memory Layer Underneath Them AI...
The problem with AI coding agents isn't intelligence — it's memory. Every session starts cold. Mneme HQ is my answer to…
Every morning, I found myself onboarding a new AI agent. Not a new human teammate. A new Claude Code...
Most people building with AI agents hit the same wall eventually, and it has nothing to do with how...
A practical model for AI coding agents that need to remember projects, tasks, executions, and runtime sessions separately.
I lean on AI coding agents hard. Claude Code, Cursor, Codex — I drive them fast to ship fast. That's...
