
PolyContext — AI-native localization for developers
Translate locale files with context and tone awareness for games and software.
@polycontext · X
Context-aware localization for apps, games, and software.
The full gallery
Tech stack
61 projects

Translate locale files with context and tone awareness for games and software.
@polycontext · X
Context-aware localization for apps, games, and software.


Visualize Bitcoin, Ethereum, Solana, and BNB with technical indicators like MACD, Bollinger Bands, and Chan Theory signals.
@jielove233 · X
最近看到 @dappOS_com 一个作品挺有意思 一个主流币交易共振信号Agent,通过 dappOS Coding 快速完成 链接: 这个案例的价值,不在于又做了一个行情页面,而是在于它展示了一种新的 AI Agent 构建方式 过去开发一个交易辅助工具,需要先处理数据接口,再搭建前端交互,编写指标逻辑,最后不断测试优化。 对于很多有交易想法的人来说,真正困难的不是没有策略,而是从想法到产品之间隔着一整套开发流程 dappOS Coding 改变的,就是这个过程 通过自然语言描述需求,就可以快速生成对应功能模块 像这个交易共振信号案例,本质上就是把市场数据、技术指标和信号逻辑结合起来,形成一个面向交易场景的辅助工具 它并不是替用户直接交易,也不是承诺预测市场 更重要的价值在于 帮助交易者降低信息处理成本 在 Crypto 市场里,行情 24 小时运行,大量数据、新闻、价格变化不断涌入 普通用户很难持续人工筛选有效信息 AI Agent 可以承担其中一部分重复工作: 监控市场变化 整理关键数据 输出信号参考 辅助交易决策 这也是为什么最近 AI + Crypto 的结合越来越受到关注 OKX 推出 AI 与交易生态结合 @BNBCHAIN 也在推动更多项目加入 BNB Agent Studio,鼓励开发者围绕交易、情感陪伴等方向构建 AI Agent 整个行业正在从AI 能聊天进入AI 能完成任务的阶段 而 dappOS Coding 展现出来的方向,是降低 Agent 创建门槛 以前一个想法可能停留在笔记里,需要开发团队才能实现 现在,更多开发者、交易者甚至普通用户,都有机会快速验证自己的想法 未来 Crypto 的竞争,不只是资产和协议之间的竞争,也会是 AI Agent 生态和应用数量的竞争 谁能让更多人低成本创造工具,谁就更有机会成为下一阶段基础设施的一部分 这个交易信号案例只是一个开始 AI Agent 正在逐渐成为连接用户、数据和链上应用的新入口

Simple AI chat for OpenRouter models with no login, no tracking, self-hostable.
johnfahey · HN
As someone who doesn't use any of the more "advanced" features on sites like ChatGPT or Claude (agentic mode, memory, image generation, deep research, etc), I found the bloat of these services, both in UX and in performance, to be pretty tedious. There are a million AI chat interfaces out there, but I could never find one that just did simple messaging and history in the most minimal and lightweight way possible. So I made my own. Nully is written in Go and Vanilla HTML/CSS/JS. It literally just sends messages to OpenRouter, receives the result, and stores your messages locally. It's very simple, very clean, and very lightweight (see performance graphs on the site). It has basic chat features, basic model settings, and works with just about any OpenRouter text model. It supports attachments and basic web search via the OpenRouter API. I made Nully mostly for myself, but the cost to open-source it and host it on a cheap VPS is practically nothing, so I figured I'd release it if it c

Summarize podcast episodes with AI-generated keypoints to catch up faster.
@andreimatei · X

Translation management platform with agent-native workflows for shipping multilingual apps.
@sacsandc4 · X

Pre-commit hook that catches verbose, defensive LLM-generated code before merge.
@iampeersky · X
is blazingly fast LLM generated code slop detector & clean up cli tool that installs as git pre-commit hook to save your git history from sloppppp

Collect and manage user feedback and feature requests with an open-source AI alternative to Canny.
@kngkng182542 · X
If you're paying for Canny, give FeedLog a look. Same workflow for collecting feedback and managing feature requests, but free during launch.

Unify Gmail, WhatsApp, and business tools in one workspace to manage conversations and automate customer workflows.
@wrrkai_ · X
This week we're shipping Helping startups and growing businesses manage every customer conversation from one AI-powered workspace.

Transform AI-generated text into natural-sounding human writing.
Humanizadordeia.app — 将AI文本转化为自然人类写作。1)人性化处理,让 AI 文本更自然、更贴近人工写作与品牌口吻;2)检测服务,帮助识别潜在 AI 生成内容,提升合规与质量。支持多语种、极速处理、保留语义与风格。免注册体验 300 字,适合博主、营销团队、跨境站点、教育与企业内容运营。以先进模型(GPT、Claude、Gemini 等)驱动。

Generate social media posts, visuals, and videos across multiple platforms from a single brief.
@Meet_Archy_AI · X
Craft social media campaigns in minutes - from one brief to multi-network campaign in minutes

Scan websites for AI usage and test chatbots for bias and safety with this open-source EU AI Act compliance toolkit.
@sebuzdugan · X
building @getfrai , an open source toolkit that helps ML engineers navigate EU AI Act compliance, model cards, risk files, the boring but necessary stuff