Treg is an agent-focused registry that exposes a curated catalog of thousands of third‑party endpoints and tools behind a single base URL and token so agents can request tasks rather than specific vendors. It covers SEO, backlinks, social, people/company enrichment, ads, scraping, image/video generation and more, with per‑call pricing from fractions of a cent and no provider signup required. Teams can register their own API keys, CLIs, or composite “skills” so calls run with team credentials injected server‑side; those own‑key calls bypass metering, while unregistered calls fall back to verified public routes or Treg’s pooled key billed to a prepaid team balance. The proxy relays requests (it never models upstream traffic), preserves caller headers, enforces input schemas (strict_query), and implements a credential ladder that decides which key is used.
Integration and workflow support include a CLI quickstart (install, login, search catalog, call tools, check balance), a Claude Code plugin and MCP connector with curated read/write surfaces and safety signals, and ready workflow skills (lead-signals, make-ugc, memory mods). Catalog lookup is task‑centric so agents find tools by what they do, not by vendor name. Hosted at treg.to and fully self‑hostable, Treg enables teams to share and meter access to many paid APIs from a single agent-friendly interface while keeping secrets on the server.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
NanoMuse is an open-source AI agent designed to work across multiple devices, including phones, tablets, and computers. It remembers user preferences, stays active when apps are closed, and interacts through a personalized interface. (github.com)
OpenWAM is an open framework that combines video prediction and robot control using a shared causal video backbone. It supports various interaction models and improves robot task success rates through causal adaptation and counterfactual supervision. (openwam.stanford.edu)
OpenAI's Decisions API can evaluate GitHub pull requests by analyzing diffs against specific review questions, such as compatibility or migration needs. This helps organize review processes by providing clear answers to targeted concerns. (vercel.com)
Strands Decider 2B is an open-source decision model designed for building AI agents. It supports various tools, integrations, and deployment options for creating and managing intelligent systems. (strandsagents.com)
UniEvo-VL is a framework that enables multimodal models to improve themselves by using their own feedback during testing. It enhances image generation performance without external supervision, showing significant gains on benchmark tests. (arxiv.org)
OpenAI has produced mathematical manuscripts and supporting proof artifacts available on GitHub. These resources aim to advance research and understanding in mathematical AI applications. (github.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.