169 results for routing · 2.240s

News for “routing”
16 results • 2234 ms server time
Moozonian News
tokengo.com• 2d ago• 1 min read
Show HN: Use GLM-5.3 in Cursor today via tokengo APIHi HN,Hearing a lot of buzz around GLM-5.3, which I expect to be the best open-source coding model with the weights dropping soon, I wanted to test it where I actually do my work.I just mapped GLM-5.3 to TokenGo so I could swap out the base URL and use it directly in my IDE.The backend handles the edge routing via Cloudflare to keep latency low, critical when you're waiting for inline code completions.If you want to try GLM-5.3 (or glm-5.3-flash) in your own workflow, here is the setup.For Cursor:Go to Settings > Models.Add your API key in the OpenAI API Key field.Toggle "Override OpenAI Base URL" and set it to: https://api.tokengo.com/v1Under "Model Names", add z-ai/glm-5.3.Select it in your chat panel dropdown.We're one of the first inference providers to get the GLM 5.3 family online and fully accessible for IDEs. If you'd like to try it in a high volume production workload I'd be happy to provide test keys for yall
Moozonian News
iluvatarlabs.com• 2d ago• 1 min read
Show HN: AI scientist builds an open-source Codex Micro from scratch for $40A few weeks ago, we open-sourced our design for a cost-effective but full featured alternative to OpenAI x Work Louder's sold out Codex Micro macropad. And now, we're pleased to share that we've actually built them and they work!Quick recap of the I/O: - 13 assignable keys with individual LEDs - rotary encoder - joystick - touch disc - optional edge-lit LED bandThe cool part for us was just HOW our agent was able to do it when every other agentic skills, tools, and even commercial platforms failed. We put together a more detailed writeup in the linked blog post (plus pretty pictures!), but long story short, we asked our agentic scientist, Marvin, to treat the electrical engineering as a research problem.Marvin was able to synthesize vast technical documents and best practice guidelines (e.g. scientific literature), test specific placement and routing strategies (e.g. experiments), and selectively backtrack and combine learnings (e.g. interpreting data analysis). The end result was a fu
Advertisement
Moozonian News
news.ycombinator.com• 3d ago• 1 min read
Self host sheets, docs, drive, emailSelfhost a full suite of collaboration tools powered by onion v3 routing and a isolated three dedicated service architecture.Surprisingly usable latency for realtime collaboration on sheets/docs.Host on Linux, macos, termux.https://gitlab.com/here_forawhile/tmailplus
Moozonian News
bing.com• Aug 20, 2026• 1 min read
Ramp launches its own AI model router, called RouterRamp has launched its own AI model routing service, dubbed Router, that lets users and companies use and switch between various large language models via an API.
Advertisement
Moozonian News
news.ycombinator.com• Aug 11, 2026• 1 min read
2. Ask HN: We built a solution for 100B-node P2P. Does anyone care about this?We have developed an architecture and algorithms that enable search in a peer-to-peer network of over 100 billion nodes in under one second, and under half a second in low-orbit satellite networks. The routing requires less than 80 KB of memory per device, allowing the network to run entirely on consumer devices like smartphones.We are two researchers. We spent years trying to build a mathematically protected secret voting system. In the process, we were forced to solve many networking problems that typically prevent a pure P2P network from reaching global scale:— Search: Deterministic, under 1 second, 100B+ nodes, under 80 KB routing memory per device.— Identity: Anonymous authentication without CAs. One person, many devices, no passwords. — Recovery: Session restoration without passwords or seed phrases.— Subnets: Fully autonomous, isolated networks of any scale.— Anonymization: Traffic analysis resistance built into the protocol.— Integrity: Consensus-based recovery of routing data
Moozonian News
hqbase.io• Aug 11, 2026• 1 min read
Show HN: HQBase – team email that runs in your Cloudflare accountI built HQBase, an open-source email workspace that runs in your Cloudflare account.I originally built it for myself. I wanted multiple addresses and domains - support@, sales@, personal addresses, etc. - without paying for a separate mailbox for every address or running a mail server.It uses Cloudflare Workers, Email Routing/Sending, D1 and R2.HQBase gives you one inbox for multiple domains and addresses, team invites with granular inbox access, a PWA with push notifications (including iPhone), and an MCP server.Setup takes about 2-3 minutes, and the infrastructure stays in your Cloudflare account.The project is AGPL-3.0 and fully open source.Would love feedback and any features you'd like to see.https://hqbase.io
Moozonian News
github.com• Aug 7, 2026• 1 min read
Show HN: A model router should also provide a MCP gatewaySo, I was recently exploring different options for model routing based on task complexity, and realized that it’s absolutely essential that the model router provides an unified MCP gateway as well.Because it’s as painful as connecting your separate providers to a service. For example, you are using OpenCode and Hermes, and as provider, you have got Groq, OpenRouter and Anthropic, and also a couple of MCPs. So, the hassle comes from connecting all your MCPs and LLM providers to both OpenCode and Hermes separately. Now, you can do it for two, but what if you also use OpenClaw, jcode, or Muse Code? It becomes a nightmare of executing busy chores.So, a LLM and MCP gateway like Bifrost becomes necessary, which is both free and open-source. Out of all the solutions I tried like Truefoundry or LiteLLM, Bifrost sounded the best one to me. Please share your feedbacks and opinion regarding this in the comments.
Moozonian News
trames.karazajac.io• Jul 31, 2026• 1 min read
Show HN: Offline Flock NavigationHello HN!A little side project I have been working on a fork of OsmAnd with offline ALPR/Flock camera avoidance routing.Also, took the time to at least create a paper on the project as well. https://github.com/KaraZajac/TRAMES/blob/main/research/paper...And yes, I did use AI to help me with this.All of it open sourced and available for use. Though I don't intend to build Apple version of this, or submit it to the play store.I am looking for feedback!Thank you all and have great weekend. :)