Repowise (@repowisedev) header
Repowise (@repowisedev) profile picture

Your coding agent knows the codebase before it touches it. Fewer wrong edits, fewer wasted tokens. Open source, runs on your machine.

Joined June 2026
Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)Photo by Repowise (@repowisedev)
My biggest fear with Claude Code and Codex on the same repo is one push quietly breaking someone else's work. with repowise my agent checks the shared index first, sees which files it touches, who depends on them and who owns them, and flags what it shouldn't change alone. This is just crazyyyy af :)
3
2
26
1,597
Repowise retweeted
I vibecoded an app in 2 days. Now one new feature takes a week. Every new AI chat starts from zero, so it rebuilds what exists and breaks what's connected. Repowise maps your codebase so every chat knows what's built. Save the tokens. Save your sanity. repowise.dev
2
1
3
53
Repowise retweeted
The biggest problem with AI coding isn’t writing code. It’s what happens when your Claude limit runs out. You switch to Codex. And suddenly your new AI has NO idea: • what you built • why you built it that way • which files depend on what • what it might break next So you spend the next session re-explaining your own codebase. Repowise fixes this. It gives Claude, Codex, Cursor, and other AI agents a shared map of your repo: → dependencies → architecture → decisions → change impact Stop making every new AI rediscover your project from zero.
23
6
4
67
47,622
YOUR AI CODING AGENT HAS BEEN GUESSING THIS WHOLE TIME. Found a repo called repowise. One pip install and it maps your entire codebase before Claude touches a single file. Every file, class and function goes into a dependency graph with PageRank. Your git history turns into hotspot scores and hidden co-change pairs, files that break together with no import link between them at all. Last night I pointed it at a repo I hadn't touched in months and asked Claude to add rate limiting. Instead of reading 30 files and guessing at the structure, it pulled the dependency graph, flagged the 47 files that depend on the one I touched, and surfaced the old decision doc explaining why auth works the way it does. 10 MCP tool calls and 5 layers. 2 minutes. Open source, runs fully offline with Ollama, code never leaves your machine. 5.5k stars, Check it here: github.com/repowise-dev/repo…
14
5
34
37,099