Omar

SE

Startup Equity Adventure Game

I put this together (with Claude) as a semi-gamified way for folks to learn about startup equity. Take a look, and share your scorecard :)

LI

Limen

I built and released Limen v0.1.0: https://github.com/thecodearcher/limen Writeup/docs: https://limenauth.dev/blog/introducing-limen It’s inspired by better-auth’s plugin-first DX, but designed for idiomatic Go. The core handles sessions/cookies/security primitives, and auth methods are composed as plugins (credential auth, OAuth providers, and 2FA today). It exposes an http.Handler, so it works with plain net/http and frameworks like Gin/Echo/Chi/Fiber without framework lock-in. This is the first public release. I’d really appreciate feedback.

AM

Agent MCP Studio

I built a browser-only studio for designing and orchestrating MCP agent systems for development and experimental purposes. The whole stack — tool authoring, multi-agent orchestration, RAG, code execution — runs from a single static HTML file via WebAssembly. No backend. The bet: WASM is a hard sandbox for free. When you generate tools with an LLM (or write them by hand), the studio AST-validates the source, registers it lazily, and JIT-compiles into Pyodide on first call. SQL tools run in DuckDB-WASM in a Web Worker. The built-in RAG uses Xenova/all-MiniLM-L6-v2 via Transformers.js for on-device embeddings. Nothing leaves the browser; close the tab and the stack is gone. The WASM boundary is what makes it safe to execute LLM-generated code locally — no Docker, no per-tenant container, no server. Above the tool layer sits an agentic system with 10 orchestration strategies: - Supervisor (router → 1 expert) - Mixture of Experts (parallel + synthesizer) - Sequential Pipeline - Plan & Execute (planner decomposes, workers execute) - Swarm (peer handoffs) - Debate (contestants + judge) - Reflection (actor + critic loop) - Hierarchical (manager delegates via ask_<persona> tools) - Round-Robin (panel + moderator) - Map-Reduce (splitter → parallel → aggregator) You build a team visually: drag tool chips onto persona nodes on a service graph, pick a strategy, and the topology reshapes to match. Each persona auto-registers as an MCP tool (ask_<name>), plus an agent_chat(query, strategy?) meta tool. A bundled Node bridge speaks stdio to Claude Desktop and WebSocket to your tab — your browser becomes an MCP server. When you're done, Export gives you a real Python MCP server: server.py, agentic.py, tools/*.py, Dockerfile, requirements.txt, .env.example. The exported agentic.py is a faithful Python port of the same orchestration logic running in the browser, so the deployable artifact behaves identically to the prototype. Also shipped: Project Packs. Export the whole project as a single .agentpack.json. Auto-detects required external services (OpenAI, GitHub, Stripe, Anthropic, Slack, Notion, Linear, etc.) by scanning tool source for os.environ.get(...) and cross-referencing against the network allowlist. Recipients get an import wizard that prompts for credentials. Manifests are reviewable, sharable, and never carry secrets. Some things I'm honestly uncertain about: - 10 strategies might be too many. My guess is most users only need Supervisor, Mixture of Experts, and Debate. Open to data on which ones actually pull weight. - Browser cold-starts (Pyodide warm-up on first load) are a real UX hit despite aggressive caching. - bridge.js is the only non-browser piece. A hosted variant is the obvious next step. Built with Pyodide, DuckDB-WASM, Transformers.js, OpenAI Chat Completions (or a local Qwen 1.5 0.5B running in-browser via Transformers for fully offline mode). ~5K lines of HTML/CSS/JS in one file. https://www.agentmcp.studio Genuinely curious whether running this much LLM-generated code in a browser tab feels reasonable to you, or quietly terrifying.

IB

I've built a nice home server OS

ohai! I've released Lightwhale 3, which is possibly the easiest way to self-host Docker containers. It's a free, immutable Linux system purpose-built to live-boot straight into a working Docker Engine, thereby shortcutting the need for installation, configuration, and maintenance. Its simple design makes it easy to learn, and its low memory footprint should make it especially attractive during these times of RAMageddon. If this has piqued your interest, do check it out, along with its easy-to-follow Getting Started guide. In any event, have a nice day! =)

AV

A visual CI/CD system

Over a year ago I started Actionforge, a managed/self-managed visual CI/CD platform. Just for fun, because I like building and experimenting with dev tools. Back then I thought the user would be a human with a keyboard and a mouse. These days I rarely write pipelines. I mostly write specs, an agent dumps 500 lines of YAML, Python and a Makefile then I get my artifacts. The amount is overwhelming and a liability, and I stop trusting what I just merged. So I pivoted my CI/CD project toward more visualization, analytics and data aggregation, so engineers can see what agents and the pipeline produced, the flow, steps, data. Where it fails. With that I have a better mental model instead of a blob of code. The goal is better observability, and pipelines that explain their own failures back to the next agent. And also with a personal focus on UX and design. My project supports Perforce P4, Git/GitHub and GitLab, so quite flexible. Would love to hear your impression. I'm also very interested in your CI/CD horror stories, and how you use them these days. Any input is much appreciated! P.S. Code is public and provides GitHub Attestations.