Trigora is a durable execution platform designed for long-running AI agents and programs that need to suspend and resume across events, timers, external effects, and child programs without replaying past execution history. Its core idea - Transparent Continuation Checkpointing (TCC) - captures and commits the program position and the live durable state at durable boundaries so recovery resumes from a committed continuation instead of re-executing completed code. That approach targets workloads that call models, tools, APIs, wait for humans or external events, sleep for minutes to days, coordinate durable children, branch dynamically, and must survive worker or process failures. A technical report and research materials describe continuation-based recovery, matched recovery versus history replay, live-state scaling, and crash/fresh-process restore semantics.
The platform provides SDKs, clients, and a CLI for TypeScript, Python (3.10-3.14), and Rust, plus a local runtime and a managed Trigora Cloud offering durable execution, deployment/versioning, events and timers, cron/webhook triggers, secrets, observability, and managed persistence. The codebase is split into focused repos: the core CLI/runtime/public contracts, language-specific SDKs, and a portable TCC Engine (mainly Rust) that can be embedded; the engine is source-available under BSL 1.1 (converting to Apache 2.0) while SDKs and clients are MIT-licensed. Quickstart commands (trigora init, trigora dev, trigora deploy), links to docs, research, and cloud are provided for getting started.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
An AI developer has launched open-source, Adobe-like creative software suites using AI reverse engineering, aiming for full feature parity. The projects, built with Anthropic’s Claude Opus, are in early alpha but plan to reach near-complete functionality within months. (arstechnica.com)
A new open vision-language model has been developed for various medical applications, enabling improved interpretation of medical data. The model aims to enhance diagnostics and treatment through advanced AI understanding of medical images and language. (nature.com)
OpenAI released 372 mathematical results generated by an internal model, many of which are verified by formal proofs. These proofs are unfamiliar and uncanny, reflecting human knowledge but in a form humans may not fully understand. (avowed.substack.com)
Google AI Edge Foresight enables offline, private transcription of meeting content. It aims to enhance data privacy and accessibility for users. (developers.google.com)
Meta and Microsoft are reducing employee use of Anthropic’s Claude AI, shifting focus to their own AI tools. Microsoft is cutting internal AI spending, while Meta is replacing Claude with its proprietary models for internal use. (rswebsols.com)
Qwen 3.8-27B, a free local language model, replaces paid cloud AI services like ChatGPT and Claude for a user’s daily tasks. It provides similar performance at no cost, removing the need for subscriptions. (xda-developers.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.