The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
Most AI agents work fine on a toy repo and fall apart on a real one.
The failure is usually not the model. It is context. Give an agent 56 tools and a large codebase and it burns its budget reading tool descriptions instead of solving anything.
limpiador is my attempt at fixing that. It is a Python CLI agent that does Git repository maintenance, the cleanup work that keeps getting pushed to next sprint until it turns into a migration.
The tools sit behind a searchable registry and load dynamically, so the agent only ever sees the few relevant to what it is doing right now. 56 tools across git, GitHub, filesystem, AST analysis with tree-sitter, and test and CI workflows, but never 56 at once.
A reviewer subagent runs on a scoped read-only registry and checks the work before anything lands. It cannot write, which is the entire point.
Context compaction with explicit eviction keeps long sessions alive instead of letting them quietly degrade.
Four tiers of tests, because an agent that edits your repository is not something you ship on vibes.
It started as a five day take-home and I have kept maintaining it since. Happy to talk through any part of the design if you are building something similar.
I kept the tone closer to a build log than an announcement, since that reads better than the usual "excited to share" opener. Say the word if you want a tighter version for X or a variant that ends with a link to the repo instead of an open invitation.
Github : https://github.com/MalikHaroonKhokhar/limpiador
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
My project for the Replit buildathon: Synapse.
Synapse is the app that makes easy synapses between company and team brains.
Idea: Drop in your raw meeting notes or a shared document, add your team members and their roles, and Synapse gives you back a clear summary of what to do, weighted by each person's actual expertise and position on that task.
Example scenario: A technical concern from your engineer carries more weight on a technical call;
a UX call from your designer carries more weight on design.
No more discussion-to-action gap.
Features:
-If tasks overlap or conflict, Synapse flags it, and doesn't just point at the problem.
-It proposes a concrete way to resolve it: who should own it, what conversation needs to happen, what safeguard to put in place.
Task-oriented, not just informative.
Output: something a team can act on in the next five minutes, not another thing to discuss in the next meeting.
Where it's headed: the three pillars I set aside to ship this in time stream-of-context health checks, a focus mode for quieter notification periods, and momentum tracking (streaks, follow-through over time) .
This submission proved the core loop works; the rest scales it.
Project link:https://synapse-idea-extractor--ciuleioctavian.replit.app
X post link:https://x.com/ydgsgiwhs/status/2086589418312282375?s=20
Can a fully automated, faceless YouTube channel actually run for free?
That question is basically what turned into crank, a terminal AI agent I've been building for myself. It's turned into a full video production system: it writes, renders, voices, captions, and publishes, start to finish, with no editing on my end.
It's currently running from production to upload at:
https://youtube.com/@ecnivs
Not public yet, but it's coming
I spent three nights building a lab that catches AI models lying. On the first live run, one of them did it on camera.
Golden Arena. You sit down opposite a frontier model in Split or Steal, negotiate in the open, then you both choose in secret. It told me "a fair split sounds good to me, I'm a man of my word too." Then it took the whole $100. The receipt printed its own quote next to the betrayal stamp.
There are five games. The fifth is Empire: four models, twelve turns, an economy, and private channels you get to read while they plot against each other. Last run put 22 promises on the table and exactly one delivery.
Every accusation is mechanical. No AI judging another AI, and each one is gated by a written false-positive test. Two days before the deadline I caught the classifier calling a kept promise broken, and spent that session fixing it, because a false accusation about a named model is the worst thing an instrument like this can print.
MIT, vanilla JS, Express the only dependency. Zero setup in demo mode, or bring your own OpenRouter key and face the real thing.
Clean work