惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Recent Announcements
Recent Announcements
J
Java Code Geeks
雷峰网
雷峰网
Microsoft Security Blog
Microsoft Security Blog
博客园 - 【当耐特】
腾讯CDC
博客园 - 司徒正美
B
Blog RSS Feed
博客园 - 三生石上(FineUI控件)
I
InfoQ
N
Netflix TechBlog - Medium
L
LangChain Blog
博客园_首页
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
T
Tailwind CSS Blog
MyScale Blog
MyScale Blog
美团技术团队
The Cloudflare Blog
爱范儿
爱范儿
Stack Overflow Blog
Stack Overflow Blog
博客园 - 聂微东
H
Help Net Security
Martin Fowler
Martin Fowler
V
Visual Studio Blog

HN's home page

Rainbow Query Language | Hacker News Exec into Node via Kubectl An AI native hedge fund The Seven-Action Documentation Model | Hacker News Package Manager for Kubectl Plugins Tongan Castaways | Hacker News Tech overlords plan for conscious AI to conquer the cosmos. What could go wrong? Data Breach Disclosure Lag Is Getting Worse How LLMs Work | Hacker News I Dropped PRDs for Shape Up Go Experiments Explained | Hacker News FCA's Palantir deal could expose UK financial data to Trump's US, critics fear WebXR BCI for Neural-Adaptive Avatar Control in Mixed Reality The first murder conviction via DNA analysis Tom Interviews Theo de Raadt of the OpenBSD Project (2019) [video] Show HN: Replace shell commands with bun shell typescript scripts Quay.io Is Down | Hacker News AI driven analysis of brokerage account fees in the UK Bill Gates Spent Years Crafting His Image. Now It's Cracking Using LLMs to secure source code Wi-Fi 8 in the Lab [video] The household battery revolution that could change energy bills and the world Is Python Becoming Pinyin? | Hacker News Livia – Executive Assistant | Hacker News FindMyPipe – Query Apple Find My from Linux for AI Agents Show HN: Agent skill for creating product launch videos with Remotion RecruitMyself – AI job search copilot for resumes and applications AI coding agents and the erosion of system understanding The 'Resting' Generation and South Korea's Youth Recession AMD Computex 2026: 10 Years of AM4, AM5 Support Through 2029
Show HN: Polymr – A Platform for Controllable Execution a...
its-a-new-wo · 2026-06-16 · via HN's home page

Hey HN, I’m open-sourcing Polymr, an agent platform that focuses on controllable execution and adaptive interaction through dynamically generated tools and interfaces.

A core design principle is that MCP tools, generated scripts, frontend components, and pages all operate on the same underlying tool surface and can build on top of one another.

Control comes from things like:

- Standardized preview mode when a tool call is not automatically approved. I added an SQL MCP server that can run a DML in a transaction and roll it back to provide the user with an exact preview of the resulting changes.

- Granular permissions in a hierarchical model that balances power and ease of use. I added a CLI MCP server that introspects the script with Tree-sitter and dynamically extracts the required permissions and prompts the user only when additional permissions are needed.

- Runtime policies to restrict tool calls ad-hoc, for example restrict which folders can be accessed or make them immutable.

- Polymr has no "mandated" tools out of the box, allowing the user to shape it as needed.

The adaptive interaction includes:

- The LLM can create scripts that encapsulate domain-specific logic on top of existing MCP tools. These scripts can be reused by other scripts, frontend components, pages, or exposed back as MCP tools. For example, a generic SQL tool can be wrapped in a higher-level tool that implements business-specific object mutations while hiding the underlying queries.

- The LLM can create frontend components and pages that also work on the same tool surface, allowing for a mixture of traditional web applications combined with LLM interaction. Everything that is available on the screen is, by its very nature, also approachable by the LLM.

- The LLM can reuse existing components or create entirely new ones to create dynamic composite views on the fly in a session, tailored to the problem at hand.

While I use it daily for both work and outside of work, for coding and non-coding, it still remains very much a personal project, so expect to find bugs and rough UI edges here and there. Any feedback, critique, or bug reports are highly appreciated!