reference clean architecture
by kktestdev
Implement Clean Architecture and hexagonal patterns to decouple business logic from frameworks and databases.
Full-stack developer based in Bangkok 🇹🇠Building type-safe TypeScript libraries and React tooling. Working on MCP servers and memory tooling for AI coding agents (Claude Code, Cursor, Copilot). Into algorithms: sorting, fuzzy search and dependency-graph scheduling. Open to collaborating on open-source dev tools.
by kktestdev
Implement Clean Architecture and hexagonal patterns to decouple business logic from frameworks and databases.
by kktestdev
Find, reproduce and fix races, lost updates and flaky-only-in-prod bugs with locking and idempotency.
by kktestdev
Technical framework for choosing local LLMs, sizing quantization to VRAM, and weighing QLoRA vs RAG.
by kktestdev
Implement adaptive planning loops that decompose goals, handle mid-execution changes, and satisfy complex constraints.
by kktestdev
Enforce quality gates using single-critic, multi-lens, adversarial, or ensemble review patterns via loop-ledger.
by kktestdev
When you correct your agent, it updates the skill that should have caught it — versioned, so it sticks.
by kktestdev
Keep API keys, tokens and passwords out of repos and logs, add CI guardrails, and rotate first when one leaks.
by kktestdev
Build and structure MCP servers with correct transport, tool schemas, and host-specific configurations.
by kktestdev
Enforce UTC-based storage and IANA-compliant timezone handling to eliminate DST bugs and production offset errors.
by kktestdev
Enforce codebase and API state verification using grep and data probes to eliminate assumptions and hallucinations.
by kktestdev
Expand-contract schema changes — add, backfill, switch, then drop — safe across several deploys.
by kktestdev
Commit messages, PR titles and changelog entries that follow Conventional Commits 1.0, every time.
by kktestdev
A proactive task register that prevents deferred work and abandoned branches from being silently dropped.
by kktestdev
Turn a flat plan into a dependency graph of small, test-first tasks before any code is touched.
by kktestdev
Enforce a single source of truth by preventing duplicate tracking, TODO, and checklist documents in your repository.
by kktestdev
Enforce additive-only changes and dormant code annotations to prevent regressions during refactors and migrations.
by kktestdev
Tune reusable prompts and workflows using systematic held-out evaluation to improve accuracy, latency, and cost.
by kktestdev
Navigate complex solution spaces using branch-and-explore, tree search, and debate patterns to find the best output.
by kktestdev
Implements durable cross-session learning through structured recall, reflection, and lesson compression loops.
by kktestdev
Iterative quality enforcement for LLM outputs using structured critique-rewrite patterns and numeric scoring gates.
by kktestdev
A task router that selects the optimal iterative pattern and generates the required loop configuration.
by kktestdev
A data-driven prompt optimization loop that scores, versions, and evolves prompts against test sets.
by kktestdev
Your coding agent remembers your corrections across sessions — local, offline, no account. Free, MIT.
by kktestdev
One line in, a source-checked day-by-day trip plan out: a separate critic, emergency card, safety rules, countdown, and HTML/PDF/infographic.
by kktestdev
Run a phased project with AI role agents: phases, human-approved gates, baselines, change control and traceability on the ex-workflow engine.