Failed to create session.Is the daemon running? 3 个帖子 - 2 位参与者 阅读完整话题
We all know the feeling: can’t remember the word but we know what it means. That’s why I built: WordFor - a reverse dictionary where you describe a concept and it suggests the word you’re looking for. - Runs entirely in the browser (no server calls) - No ads, tracking, or accounts - Low latency (results show up immediately as you type) Curious how well it works for other people, and happy to answer questions about the approach or tradeoffs. Technical Blog explaining the workings: https://zshn25.github.io/wordfor-reverse-dictionary/ Comments URL: https://news.ycombinator.com/item?id=47805014 Points: 3 # Comments: 2
I built a small CLI after running into UI/UX problems on my own site. It runs quick checks on a URL (layout overflow, tap targets, basic a11y via axe, console/network errors) and outputs a JSON report plus screenshots. Early stage and feedback welcome Comments URL: https://news.ycombinator.com/item?id=47803926 Points: 1 # Comments: 0
Article URL: https://shar-wasm.cjoseph.workers.dev/?skipmovie Comments URL: https://news.ycombinator.com/item?id=47783061 Points: 4 # Comments: 1
I built this using Rust to achieve 85ns latency benchmarks. Currently scaling to 824 active nodes directly from a Samsung A04e. While everyone is focused on high-end mobile AI, I'm focusing on sovereign, low-latency infrastructure that runs on anything. Feedback on the node scaling logic in my repo is appreciated Comments URL: https://news.ycombinator.com/item?id=47780284 Points: 1 # Comments: 1
I just open-sourced how https://github.com/mylovelycodes/LiteRTLM-Swift LiteRTLM-Swift lets you run LLMs locally with a clean Swift API. - On-device inference - No cloud required - Built for iOS Comments URL: https://news.ycombinator.com/item?id=47776884 Points: 1 # Comments: 0
类似于codex cli有这个功能，Prevent sleep while running。 claude code运行着就经常停下来不继续推进任务，哪怕设置了bypass permission，还需要手动和cc说设置heartbeat持续监控进度。 2 个帖子 - 2 位参与者 阅读完整话题
Built Hivecrew, a native macOS app for running parallel computer-use agents in isolated macOS VMs. You can delegate computer use tasks, watch workers live, step in by manually manipulating the VM, and review what happened afterward. It’s designed for longer-running work where safety and visibility matter. It also has a voice mode so you can launch tasks and get work done just by talking. This is basically the full business school experience; your job is just to talk now! Would love feedback on the workflow, the VM-based isolation approach, and what kinds of tasks people actually want to hand off. Comments URL: https://news.ycombinator.com/item?id=47766910 Points: 2 # Comments: 2
I built Remoroo because most coding agents fall apart once the work stops being a short edit-and-run loop. A real engineering experiment can run for hours. Along the way, the agent reads files, runs commands, checks logs, compares metrics, tries ideas that fail, and needs to remember what already happened. Once context starts slipping, it forgets the goal, loses track of the baseline, and retries bad ideas. Remoroo is my attempt to solve that problem. You point it at a repo and give it a measurable goal. It runs locally, tries changes, executes experiments, measures the result, keeps what helps, and throws away what does not. A big part of the system is memory. Long runs generate far more context than a model can hold, so I built a demand-paging memory system inspired by OS virtual memory to keep the run coherent over time. There is a technical writeup here: https://www.remoroo.com/blog/how-remoroo-works Would love feedback from people working on long-running agents, training loops, eval harnesses, or similar workflows. Comments URL: https://news.ycombinator.com/item?id=47765662 Points: 2 # Comments: 0
Error running remote compact task: unexpected status 502 Bad Gateway: Unknown error, url: http://CPA服务器url/v1/responses/compact 我继续问了下codex，他说是 compact 的模型路由和上游兼容性问题 cpa不支持远程压缩吗？ 2 个帖子 - 2 位参与者 阅读完整话题
I've created an alternative to CLI and MCP for locally running agentic tools. It uses Unix-based OS's named pipes, which means the client has quick IPC with the tool and it can have in-memory state. I created it to build components for voice agents (TTS, STT, LLM chat) but it has wide range of uses! Comes with a CLI tool, cpipe (like curl), and a Claude Code skill Comments URL: https://news.ycombinator.com/item?id=47746821 Points: 2 # Comments: 0
I kept running into “works for me, not for users” issues, where everything looked fine locally but failed somewhere along DNS / TCP / TLS / HTTP. So I built a small CLI tool that checks each layer step by step and shows where it breaks. Example: DNS (NXDOMAIN) → domain does not exist It’s meant to quickly narrow down the problem instead of guessing. You can run it directly via: npx accessyo yourdomain.com It’s free and open source. Would love feedback from people who deal with these kinds of issues. Comments URL: https://news.ycombinator.com/item?id=47741004 Points: 1 # Comments: 0
Ampere Ampere — Your OpenClaw Agent, Running in 60 Seconds Deploy your OpenClaw agent in 60 seconds. No servers, no setup, no maintenance. Always on, always yours. 教育邮箱 0.1一个自己去找，随便注册。 随便瞎点几个页面，不用绑卡也能进，要绑卡就自己解决。 进去找terminal，找openclaw配置文件，里面有openrouter渠道的baseurl和apikey，自己找，一定要走openai格式的接口。 咋？我利益相关吗？麻烦认识ampere ceo的帮我介绍介绍。 闭门关车，有这个闲工夫举报，不妨写两行代码。 有没有可能，我昨晚就发了呢，有没有可能那是首贴呢，有没有可能那已经有5k的点击了呢 openrouter原始渠道，说降智的，我都懒得说什么了 49 个帖子 - 40 位参与者 阅读完整话题