Looking online, platforms like CrazyGames and Poki cater to a casual/hypercasual demographic, and I couldn't find anything out there that was for me, a core gamer that typically uses Steam and consoles. So I vibe coded my own! It features WASM ports of classic games, as well as some indie Unity titles. The goal is to host mainly WebGPU titles moving forward, and to serve as a way for smaller developers to get discovered outside of crowded channels like Steam.
Here's a few features from the platform I wanted to highlight:
• Controller support • A console-like UI/UX • Community forums (much work to do here) • Basic achievements • Store pages, modeled after Steam • Social features • Asset chunking to enable faster load times
I'd love to get feedback on the portal, to make it even better. Thanks!
Performance: Local llms are not built to do the cool things cloud models do because the model sizes are not even capable of building real apps like the 8b models, 13b, even 1b so the solution I came up with was to give these small models access to tools and features that make it actually work well in coding performance.
So what does claw-coder have access to: A knowledge graph: A knowledge graph is an interconnected network of real-world entities—such as people, places, concepts, or events—and the relationships between them. It organizes information into a readable web of meaning rather than static lists, allowing both humans and AI to understand context. So how does this help an AI, it gives the AI the ability to tell relationships between code in your codebase, a cloned unknown repo and so forth this increases performance of local llms by far in coding tasks and reasoning abilities. Rag: We have ever had of RAG at some point but there is a catch the context window of local llms can't bear large codebases and repos so RAG isn't optional by storing vectors in a vector store you enable the AI to actually know what the code means and what each piece does to the other letting you load millions of lines into the vector store without blowing up the context window.
Tools: So we have discussed the tiny but powerful ways to improve local llm performance but an agent to be an agent it needs to take action this is where exposing tools to the local llm helps so what tools have been implemented into claw-coder. 1. search_tool This enables the ai agent to actually search up to date info so that it doesnt hallucinate on info it doesn't know which is common in local llms. 2. Docker execution This agent has a special folder called workspace where it does its work without destroying your desktop but this is not enough to protect your desktop from being destroyed by cheap code so this is where docker comes in I have implemented docker containers of various languages where the agent can validate its own code this is powerful because all llms not only local ones generate code they can't even confirm works because they are just powerful predictors so enabling it to run its code can surprisingly increase the usefulness of the generated code because it now knows it works or not even for html and css the ai agent has been given a helpful vision llm to actually explain what rendered in the browser. This is the surprising power of giving an llm a docker execution tool.
We have looked at a lot of how claw-coder is different enabling local llms to actually do real work. But how do you actually try it out yourself: Claw-coder is closed source because it is going through heavy testing but that doesnt kill transparency and since we are testing it doesn't stop people from trying it on real codebase and giving feedback to get started use:
brew tap gabriel-c70/claw then brew install claw-coder
It is here:
https://calculatormusic.com
No signup is required. I would love feedback on whether the practice mode makes sense and which songs sound recognizable.I've been building Invoker, a native Mac IDE for working with agents. It plugs in your existing Codex or Claude Code CLI, using your existing plan.
I started working on it in February, with three initial design goals:
1) Run massively parallel agents in an easy, organized way
2) Provide a full IDE, so you don't need VSCode
3) Be super fast across the board: performance, shortcuts, workflow, etc.
This is not revolutionary; there are tools out there that solve each of these pieces. My goal was to build a single, integrated package that did all three out of the box.
Here are the main features:
* Linear-style task tracker for agents. In other apps, when I create too many threads, either it lags, or they end up disorganized in a tiny sidebar. With Invoker you just throw a bunch of tasks on the board. The core multiplexes them without hitting rate limits or slowing down, and the task board lets you manage them in a unified way: see what's being worked on, get notified about ready tasks, and mark done to declutter.
* Full built-in IDE. Every worktree gets a full IDE with a file tree, editor, LSPs, vim keybindings, search/replace, terminal (libghostty), and git diff viewer (inspired by GitUp).
* Unopinionated worktree support. Worktrees are useful but add overhead. Instead of every thread getting a new worktree, they're optional to create as you want. Every worktree gets its own task board and IDE workspace.
* Fully native app, GPU-rendered UI. Runs at 120 fps.
* Keyboard-first workflow. A big part of software engineering now is just incrementally herding a flock of agents to completion. I wanted a power tool like Linear or Superhuman to manage that process. The whole development loop — create tasks, open next ready task, catch up on context, respond or mark done, next, add more tasks as needed, etc — can be done from the keyboard.
Invoker has been my daily driver for a while (I built it mostly using itself), but it doesn't support every feature out there yet (e.g. `/goal` isn't implemented). If there's something you're used to that's missing, please let me know — [email protected]. Last-mile feature parity is a high priority.
The current business model is embarrassingly simple: charging for the software. There's a 3-day free trial, then it's free for the first 1 hr of combined agent use per day, then $10/mo for continued unlimited use (annual/lifetime also available). Truthfully, as I was reasoning through pricing models, I realized that it's just extremely awkward to charge for something like this without reselling tokens; any thoughts or feedback here would be welcome.
Would also love to hear any thoughts in general regarding the product, missing features, or anything else!