https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It’s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
Probably working on too many projects at the moment - but really enjoying building again.
Working hard to figure out how to market, interested in trying to push things out a bit more.
Working on a benchmarking tool with https://flopper.io for GPUs too - written in Rust - which should allow me to try to get people to submit their general flop values for consumer hardware to run local llms/models.
https://spendboard.app - local-first budgeting mobile app, can be used on any number of devices offline, synced when online. Been building it for almost 3 years now (the most difficult part was the conflict resolution strategy)and happy to finally release it. :)
https://outcron.com - hosted tool to schedule health checks, webhook calls, & container executions
As an SRE, DevOps Engineer, and Platform Engineer, I've always wanted an external place to run scheduled executions of miscellaneous utilities -- checking in on a URL, running an SSL check, verification of DNS from outside, etc. REST API-centric with CLI tool and web UI control near-parity.
Backend and CLI are Golang. Frontend is React. Simple architecture--a bunch of aarch64+amd64 hosts run `outcrond` and use a shared PostgreSQL and Valkey/Redis.
I'm building a robust sandboxing environment for AI agents.
It supports multiple sandboxing backends such as docker, podman, kata, firecracker, and for Mac seatbelt and tart.
Any agent is in theory supported, but it has specific support for Claude, Gemini, codex, aider, and opencode.
Your workdir is never touched by the AI, nor is your system. It doesn't have access to your secrets (beyond what you've explicitly given), and you can restrict network access.
You move changes back to your workdir using diff and apply, so you choose which changes to keep.
I use it for all my agentic work, and couldn't go back to using Claude without it.
I am working on a P2P VPN app that lets you route your traffic through a friend's Internet connection easily. It has a few distinct uses, but right now I am testing whether emigrants from authoritarian countries will be interested in providing censorship-free connectivity to their family/friends at home.
Building Sensonym (https://sensonym.com), a vocabulary learning app that uses phone sensors (gyroscope, camera, mic, accelerometer) to create physical interactions tied to word meanings. Based on embodied cognition research. I've just launched it on iOS and Android in Germany with support for 10 languages.
AI chat for DollarDeploy (platform to automate DevOps, kind of like Vercel for your own servers). Adding more tools to deploy your apps and soon sandboxes.
I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!
Works on both plans as well as code itself. It’s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)
GitHub: https://github.com/tomasz-tomczyk/crit