12ziyad
Show HN: Aven-stops AI coding tools from breaking yours project's rules
Ask HN: Would you use a tool that adds a real back end to any front end?
i am building a backend connection where user can upload any ui/ux it will auto connect the backend within 1 minute or maybe 2 and also im providing many backend connectionsincluding advanced version like ai models ,datastorage,login and many other options ,all this in one click setup,what you guys really thinking about it
Re:Show HN: Claude and ChatGPT need a datacenter. This runs on my phone
on Thursday September 03, 2026 @12:31PM (#49552751)
Fair point on the wording — I've reworded it. And thanks for the list. AI Edge and MLC use the GPU, which I don't yet, so PocketPal is the closest comparison to mine. It was slower than PocketPal and that's fixed now.
Re:Show HN: Claude and ChatGPT need a datacenter. This runs on my phone
on Thursday September 03, 2026 @12:30PM (#49552739)
Thanks. An optional online lookup mode is a nice idea and I've noted it — offline stays the default though, that's the whole point of it.
Show HN: Claude and ChatGPT need a datacenter. This runs on my phone
Re:Show HN: Itsuki – open-source memory engine for AI agents (API and ...
on Saturday August 29, 2026 @04:27AM (#49488037)
Itsuki stores memory on its Cloudflare servers,not on the user's computer.instead of complete transcripts Itsuki extracts like useful facts and events,also the data and memory isn't used for training and also it have setup like user can export or delete it.
Show HN: Itsuki – open-source memory engine for AI agents (API and MCP)
Re:Show HN: Shared memory graph for Claude and ChatGPT, over MCP
on Friday July 31, 2026 @12:57PM (#49125729)
thankss
Re:Show HN: Shared memory graph for Claude and ChatGPT, over MCP
on Friday July 31, 2026 @12:46PM (#49125553)
Fair hit. I wrote the landing copy with AI and it shows. Rewriting it now in plain language. What would actually be useful to you on that page — the API call and a screenshot of the graph?
Show HN: Shared memory graph for Claude and ChatGPT, over MCP
Show HN: AgentWing – make AI agents complete tasks faster
Hi HN, I’m building AgentWing.The idea is simple: AI agents usually execute work as one long sequence:plan → act → wait → observe → act again → verify → finishThat makes agent workflows feel slow, especially when parts of the task do not actually depend on each other.AgentWing adds a director layer that turns one agent task into multiple isolated worker runs. The director decides which parts...