polarzero

Just released evmstate, a TypeScript library to trace & visualize state changes on EVM chains, with human-readable labels (variable names, mapping keys, decoded values, etc).

gstack is one of the most interesting AI repos Hear me out, it points to a new kind of app: a Markdown app. - The language is markdowny agentic harness - The language is markdown - The app is the workflow. And it works! It works so well it's fair to ask "why smithers?". Clearly all workflows can just be human language skills. So what is the point of smithers? Is it not overengineering. To answer this question I migrated gstack to smithers. The results: - 31 gstack skills went from generated Markdown procedures to typed Smithers workflows. - The old workflow surface was ~42k lines of generated `SKILL.md`. - The new workflow surface is ~5.4k lines of typed `.tsx`. - Gstack skills can be composed as react components - Smithers resumability, inspectability, replayability, forking features, and UI all plug right in But most importantly, I didn't migrate the workflow. An agent did. The point of Smithers is agents love structure. And if you give your agent smithers it's ability to orchestrate itself for reusable long living workflows explodes. And since the programming model of smithers is so similar to React, agents are already great at intuitively know how to build complex workflows with smithers from their pretraining on React. So smithers isn't an alternative to Markdown app programming. It's a more powerful way of doing it. It allows your agent to communicate both in human language and real control flow in a structured way agents love Check out smithers docs: smithers.sh And check out gsmithers: github.com/smithersai/gsm…

@samuellhuber I'm super strict about this and always find that it did it again. This and writing SQL migration paths. And syncing prd/specs as we discuss as if it was a changelog of our decisions.

One weird thing with agents is they stop and do workarounds for "backwards compatiblity". bruh this is not a library this is an app. just wire it in properly and update affected code, then it's clean and not spaghetti.

My most valuable insights in term of development with AI (and dev in general) come from @FUCORY (or from working with him). There is a good chance you wanna use smithers, and if you do you’re blessed, cause you’ll be able to shape it with your feedback, or customize it yourself.

I feel like the one I like best is Replit; I can't decide for sure vs Figma. They are all decent tho. I lied about the one-shot prompt I told Replit agent something like "you forgot this implement it as specified before".

Replit (Economy, idk model either) Perfect and well-thought-out layout; clean and readable. More bloated than Linear, but in a sensible way. Interestingly, it was the most “modern,” in the sense that it showed agentic stuff more intuitively than existing tools. Less thorough than Lovable in implementing everything I asked for, but after a second short prompt it fixed it. Most faithful in following Linear’s design. Very personal style, but I liked the color choices better; they were lighter than the rest, and the overall palette was very smooth on the eyes. Same for the fonts.

I sent a prompt detailing a product to Figma, Lovable, v0 and Replit to see which one I like best. All on free plan. So might as well share my thoughts. All of these screenshots are after a one-shot prompt.

@gajesh @FactoryAI smithers.sh makes that super easy to code as a workflow. @0xrandomlabs slate has this natively in their TUI.

how has no one built a hybrid model coding agent? - GPT 5.4 instructs & checks the work - MiniMax / Sonnet - some fast model executes it .@FactoryAI mission mode is probably the nearest i've seen to this structure

@EnoReyes @liufei5678 @FactoryAI Not in the same chat, you can’t follow up and it prompts to buy a plan

@liufei5678 @FactoryAI But you should still be able to send messages right? Lmk if it doesn't work

Today we're releasing the Factory desktop app. A native interface for autonomous AI agents that work across every part of your software business.

@apoorveth @walletchan_ Yes you have to provide a source code or ast. But you can provide a standard ERC20 contract; you’re forced to assume token is a standard contract but that’s the same assumption with `balanceOf`

@0xpolarzero @walletchan_ cool, is the `fromSource` mandatory?

After my last thread on @walletchan_, a lot of people asked: "Why not just use eth_simulateV1?" Here's the tradeoff between parsing logs (simulateV1) vs diffing balances (what we do) and why neither is strictly better 🧵

@heckerhut Nice! How can we know more and get involved?

today we launched the European Ethereum Institute 😎

Best uses of smithers so far - Burns — Workspace-first local control plane for authoring, running, and supervising Smithers workflows (web/desktop/CLI) github.com/l3wi/burns - Ralphinho — Multi-agent dev workflows that turn RFCs into landed code and automate code review github.com/enitrat/ralphi… - Cairo Coder — AI-powered Cairo smart contract generator using a RAG pipeline with Smithers orchestration github.com/KasarLabs/cair… - Agentix — Opinionated RFC-to-production workflow orchestrator with DDD/BDD/TDD and merge queues github.com/AbdelStark/age… - Era — Generic reusable multi-phase dev workflow engine (research → plan → implement → test → review) github.com/ClementWalter/… - Local Isolated Ralph — Kubernetes-native runner for Smithers workflows as isolated K8s Jobs/CronJobs github.com/SamuelLHuber/l…

It sounds so gimmicky AI Orchestration framework via React But hear me out, Smithers is secretly the best-in-class agentic orchestration framework In this 🧵 I answer two questions 1. Why you even need an orchestration framework? 2. Why that orchestration framework should be smithers 🧵 1/18

Proudly introducing JJHub A new code platform for agentic engineering teams 🧵 1/n

If you like using graphite you’ll probably like using jj and jjhub

@FUCORY is looking for feedback on jjhub.tech.