Unpack
a lightweight way to steer Codex/Claude with phased docs. Turn AI research conversations into structured, buildable projects. Works with Claude Code and Codex. I've been using LLMs for long discovery and research chats (papers, repos, best practices), then distilling that into phased markdown (build plan + tests), then handing those phases to Codex/Claude to implement and test phase by phase.
Open source
Reactions (1)
Similar products
by description similarity
Skill that lets Claude Code/Codex spin up VMs and GPUs
cloudrouter.devOpen source applied AI lab building next-gen devtools
Concord
github.comlet Claude Code, Codex and Cursor talk to each other
I used Claude Code to discover connections between 100 books
trails.pieterma.esThematic links across books, automatically discovered by Claude.
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.
Reference MCP
github.comlet your AI agents search each other's past sessions