πŸ” Search
Sign in to post
Show HN: Pi-Infinite-Contexthttps://github.com/fdietze/pi-infinite-context

Hi HN! Since I created this extension and heavily refined its core design, I'm not worrying about context size anymore. It just works so well. So I wanted to share. It is stress-tested with OpenAI and Anthropic models. Since HN is sensitive to good readmes, I wanted to do it well here. I started writing it by hand, but noticed that it was not great. then I decided to go back to LLM help, but iterate on it until it was short, simple and readable. I hope you like it. In this process I had an insight about AI generated content. Slop is not only the fact that AI was used, but that the creator did…

β†—
Show HN: RSI-Anything – JEPA world models for self-improving agentshttps://github.com/Gen-Verse/RSI-Anything

Article URL: https://github.com/Gen-Verse/RSI-Anything Comments URL: https://news.ycombinator.com/item?id=50072765 Points: 1 # Comments: 0

β†—
Show HN: Bomfather, eBPF Runtime Securityhttps://github.com/bomfather/agent

Article URL: https://github.com/bomfather/agent Comments URL: https://news.ycombinator.com/item?id=50072431 Points: 4 # Comments: 0

β†—
Show HN: Give Pi background updates while it keeps codinghttps://github.com/gabry848/agent-notifications

Article URL: https://github.com/gabry848/agent-notifications Comments URL: https://news.ycombinator.com/item?id=50072030 Points: 1 # Comments: 0

β†—
Show HN: Homie – a chat-voice personality layer for coding agentshttps://github.com/prashanthgit19/homie

Article URL: https://github.com/prashanthgit19/homie Comments URL: https://news.ycombinator.com/item?id=50071939 Points: 1 # Comments: 0

β†—
Show HN: Precleared – tells your outbound agent whether a cold email is legalhttps://precleared.dev

Article URL: https://precleared.dev Comments URL: https://news.ycombinator.com/item?id=50071924 Points: 1 # Comments: 0

β†—
Show HN: Rply – ntfy for talking to your agentshttps://github.com/joshuaKnauber/rply

Article URL: https://github.com/joshuaKnauber/rply Comments URL: https://news.ycombinator.com/item?id=50071828 Points: 1 # Comments: 1

β†—
Amex introduces a framework to prevent AI agents from making unauthorized purchaseshttps://techcrunch.com/2026/10/13/amex-introduces-a-framework-to-prevent-ai-agents-from-making-unauthorized-purchases

American Express is introducing a new framework designed to ensure AI agents only make purchases their users have authorized, potentially preventing costly mistakes and disputes as AI-powered shopping grows.

β†—
Show HN: Let your agents create product demo for youhttps://www.fluxcut.dev

Fluxcut makes product demo and promo easy for creators and founders by saving lots of time of editing, VO, BGM, thumbnail so that they can focus on what matters to them i.e. product itself! Comments URL: https://news.ycombinator.com/item?id=50070400 Points: 2 # Comments: 0

Show HN: Stepbook – run long agent tasks as short steps with saved statehttps://github.com/bahdan111/stepbook

Article URL: https://github.com/bahdan111/stepbook Comments URL: https://news.ycombinator.com/item?id=50070345 Points: 3 # Comments: 0

β†—
Show HN: Run your agents across E2B, Daytona and more. steer them from anywherehttps://github.com/jaygupta17/otto

Article URL: https://github.com/jaygupta17/otto Comments URL: https://news.ycombinator.com/item?id=50070245 Points: 1 # Comments: 0

β†—
Show HN: Deep Recall – portable memory you own for Claude, ChatGPT and agentshttps://getdeeprecall.com

Article URL: https://getdeeprecall.com/ Comments URL: https://news.ycombinator.com/item?id=50070114 Points: 1 # Comments: 0

β†—
Show HN: Laya guard – a local check before your coding agent runs a commandhttps://github.com/scs0209/laya-guard

HN, this is my first Show HN post, and I'm really nervous, I'm Ayaan, a Frontend Developer. laya-guard is a local check that occurs before any coding agent tool call, deciding whether to approve, send for review, or block the call. When Jev was released, I was curious as to how I could use it, and I quickly discovered Laya which is an open-source 322M model that functions almost identically but runs on a laptop's CPU in under 100ms, as the check is local, there won't be a chance of 3rd parties seeing your commands, directories, or tokens, and there's no charge per call, I often work in Korean…

β†—
Government spent millions on Trump ads. And, federal agents raid Ilhan Omar's homehttps://www.npr.org/2026/10/13/g-s1-147822/up-first-newsletter-trump-ads-funding-campaign-rallies-ilhan-omar

The government is using millions of taxpayers' dollars on pro-Trump ads, even after the president said this would not happen. And, federal agents search Rep. Ilhan Omar's D.C. home.

β†—
Show HN: Ret – An inbox and canvas for your Codex and Claude Code agentshttps://getret.app

Over the last few weeks I've really been using Codex and Claude to solve a lot of parallel tasks, across a lot of different projects. This lead me to wishing that I could interface with my agents in the same way that I interface with my already existing windows and editors. For me, this usually means that I have like 5 to anywhere around 8 different windows that I drag around depending on where I want to focus, this could mean I am focusing on the terminal now, or I want to test stuff in a simulator or browser; but when I go to interface with agents, I have to manage many tabs, or I have to l…

β†—
Show HN: shadowclone, skills learned from your coding agent correctionshttps://github.com/theonly1me/shadowclone

shadowclone reads the coding-agent sessions already on your disk, finds where you corrected the agent and turns those corrections into skills your agents load next time. It supports Claude Code, Codex, Cursor, Pi, and Antigravity. Every capture source is off by default and has its own consent setting. Why I'm building it? I use multiple harnesses and agents, I extensively use Claud Code and Codex, but I also use Cursor and Antigravity every now and then. I didn't want to have to teach every harness or model the things I taught the other ones between my last session and the current one. I also…

β†—
Show HN: We tested how 5 LLMs handle failed write actions (duplicate prevention)https://github.com/0xguenther/agent-write-path-runs

Article URL: https://github.com/0xguenther/agent-write-path-runs Comments URL: https://news.ycombinator.com/item?id=50068634 Points: 1 # Comments: 0

β†—
Morning news briefhttps://www.npr.org/2026/10/13/nx-s1-5998694/morning-news-brief

Trump will headline a rally in Alaska Tuesday, federal agents searched Rep. Ilhan Omar's D.C. home Monday, Trump's diesel deal with Russia frustrates European leaders.

β†—
Show HN: RL agent trained only in synthetic markets got better on real 2020crashhttps://github.com/giack-hack/synthetic-markets-transfer

Article URL: https://github.com/giack-hack/synthetic-markets-transfer Comments URL: https://news.ycombinator.com/item?id=50068562 Points: 5 # Comments: 0

β†—
Show HN: Let Claude Code answer with a diagram page instead of a wall of texthttps://github.com/QingYunA/answer-me-with-html

Article URL: https://github.com/QingYunA/answer-me-with-html Comments URL: https://news.ycombinator.com/item?id=50068531 Points: 1 # Comments: 0

β†—
Show HN: Seekter – an open-source job-search agent that runs in Claude Codehttps://github.com/selfishprimate/seekter

Article URL: https://github.com/selfishprimate/seekter Comments URL: https://news.ycombinator.com/item?id=50068402 Points: 1 # Comments: 0

β†—
Scientists discover a surprising paradox in how our cells agehttps://www.sciencedaily.com/releases/2026/10/261012185009.htm

Scientists have discovered that the body's cellular recycling system behaves very differently during aging than previously believed, with higher activity sometimes linked to worse physical health. A small study suggests that even gentle exercise could help restore more youthful cellular recycling patterns in older adults.

Show HN: A 3D sky city where my Claude Code agents work and take coffee breakshttps://github.com/ishraq21/skyborne

Open source, local and no telemetry. Comments URL: https://news.ycombinator.com/item?id=50066852 Points: 1 # Comments: 0

β†—
Show HN: Search for AI agents with usefulness score built inhttps://github.com/Ayobamiu/usefulness-search

Hi HN. I partnered with Simon Kley to build this project at innovation intelligence hackathon (Berkeley). Simply, we’re building a usefulness score on top of search for ai-agents. Instead of agents reading 10 ranked relevant pages, we run a usefulness score first and give it only those that pass. We’re able to save token and cost with this and slightly better answers. During our research, we found out that the current search results already do justice when it comes to simple queries. The rankings work well. They struggle when the task requires deep research or recency matters. So, we deci…

β†—

0trust.social media

Loading your media...

Pick a GIF β€” Giphy

Loading GIFs...