AI Applications

Feeds to Scour
SubscribedAll
Scoured 107 posts in 4.8 ms

Nvidia DGX Spark GB10 – AI Models and Guide with vLLM and Autonomous Script

 🤖AI  Content type: Code
github.com··Hacker News

Inferoa AI harness claimed 90% cache savings. We ran it and measured 97.8%

 🤖AI
zozo123.github.io··Hacker News

Breaking the Ice: Analyzing Cold Start Latency in vLLM

 🤖AI  Content type: Academic
arxiv.org··Hacker News

The Missing Link Between Agents and Applications

 🌐web development  Content type: Blog
langchain.com··Hacker News

DeepSeekV4 1.6T Day 0 to Day 43 Performance Over Time - Huawei, GB300 NVL72, MI355X, B200

 🤖AI  Content type: News

How to Build an Agentic RAG with RubyLLM and Rails

 🐘PostgreSQL  Content type: Blog
panasiti.me··Hacker News

Engineers building MCPs in regulated industries: what's been the hardest part?

 🏗️software engineering
deepsense.ai··Hacker News

Show HN: RiskKernel, kill -9 an AI agent and resume it without paying twice

 🐍python
riskkernel.com··Hacker News

Prompt Injection in RAG Agentic Systems

 🏗️software engineering
ulad.net··Hacker News

memory OS for AI agents (ranks, compresses and evolves agents memory)

 🤖Coding Agents
thrindex.com··Hacker News

a desktop GUI to browse, search, & visualize your vector databases

 🌐web development
vectorlens.dev··Hacker News

Product analytics that improves your AI agents continuously

 🌐web development
intencion.io··Hacker News

Mini Shai-Hulud, Miasma, and Hades Worms Target Bioinformatics and MCP Developers via Malicious PyPI Wheels

 🐍Python  Content type: Blog
socket.dev··Hacker News

local AI agents for Cursor with pre-tuned marketplace/commu

 🛠️AI Coding Tools
locaible.com··Hacker News

Dynamic ReACT Loop with Conductor

 💻programming

Predicting the World Cup Winner: Live Coding with Hopswor...

 💻programming
hopsworks.ai··Hacker News

Researchers trained an open source AI search agent, Harness-1, that outperforms GPT-5.4 on recalling relevant information

 🤖AI

MarkSentry – zero-trust document-to-Markdown for RAG pipelines

 🧰developer tools

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

 🤖LLM

Token4Token — pay-per-token inference on Gnosis + Swarm

 🤖AI

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help