#255 · Primary category: AI Coding Assistants
lazycodex
The one and only agent harness for complex codebases. Project memory, planning, execution, and verified completion inside Codex.
Project last updated:08/09/26
GitHub Stars
3.3K
Forks
209
Contributors
3
License
MIT
Why we included this project
On large, tangled repositories, a plain Codex session tends to lose the thread and mark tasks done before they are finished. LazyCodex wraps Codex in a structured harness: it keeps project memory across sessions, turns vague requests into concrete plans before any edits, and only calls a task complete after verification actually backs that up. Setup is a single npx command, and the harness runs inside Codex itself, so there's no separate tool to babysit. Its ultrawork mode runs parallel research across turns, holds progress durably, and keeps going until the completion claim is proven. If you want a coding agent that follows through on messy codebases rather than a glorified autocomplete, this is worth wiring in.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.