I like treemaps for visualizing hierarchical mass and density of resource usage. I've always particularly loved GrandPerspective's dense, colorful rendering, but haven't found a similar but generalized treemap that works in reactive web views across many data visualization contexts. So I built gp-treemap, a canvas-based web component that renders GP-style treemaps with millions of nodes:... - Source: Hacker News / 2 months ago

Easiest to have different agents or turns that set aside the top-level goal via hooks/skills/manual prompt/etc. Heuristically, a human will likely ignore a lot of warnings until they've wired up the core logic, then go back and re-evaluate, but we still have to apply steering to get that kind of higher-order cognitive pattern. Product is still fairly beta, but in Sculptor[^1] we have an MCP that provides agent &... - Source: Hacker News / 6 months ago

Hey, Kanjun from Imbue here! This is exactly why we built Sculptor (https://imbue.com/sculptor), a desktop UI for Claude Code. Each agent has its own isolated container. With Pairing Mode, you can sync the agent's code and git state directly into your local Cursor/any IDE so you can instantly validate its work. The sync is bidirectional so your local changes flow back to the agent in realtime. Happy to answer any... - Source: Hacker News / 9 months ago

A lot of recent HN stories and comments lately are on the topic if LLM agent safety (or lack thereof). Let's assume that giving a non-deterministic and easily fooled program full access to run anything it wants on your dev machine is a bad idea. Let's also assume that any "handshake promises" that the LLM won't do that, or that it will get your permission before running commands, are null and void. That is, we... - Source: Hacker News / 9 months ago

Not just visually organizing the terminals for the agents, but also keeping their environments and source trees straight, and merging them to the correct upstream branches, can quickly turn into a very complex co-ordination problem. This is exactly why we built Sculptor (https://imbue.com/sculptor). You don't need to manually juggle multiple terminal tabs because each Claude Code agent gets its own container with... - Source: Hacker News / 9 months ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 3 days ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 6 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 7 days ago

Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 16 days ago

If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 17 days ago