Semantic Search

Feeds to Scour
SubscribedAll
Scoured 63 posts in 8.0 ms

Training-Free Lexical-Dense Fusion for Conversational-Memory Retrieval

 🎯Reranking  Content type: Academic
arxiv.org·

How to Build an Agentic RAG with RubyLLM and Rails

 🗃️databases  Content type: Blog
panasiti.me··Hacker News

DeytaHQ/khora: Library for creating knowledge repositories from multi-source data and expose a single query substrate

 🎯Reranking  Content type: Code
github.com··Hacker News

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

 📍embeddings
vectorlens.dev··Hacker News

Agentic search - retrieval, harness, or model?

 🤖agents  Content type: Blog

Playing with Vision Embeddings

 🔍AI Interpretability

If Claude Fable stops helping you, you'll never know

 🎯Reranking  Content type: Blog
jonready.com··Lobsters, Hacker News

An ode to self-optimizing query plans

 🗃️databases

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

 📍embeddings

Meta's smart glasses companion app ships a complete, dormant face-recognition pipeline on a stock account.

 🎛️interfaces
buchodi.com··Hacker News

Show HN: Lore – LLM proxy for coding agent context and memory management

 🗃️databases
withlore.ai··Hacker News

Dynamic ReACT Loop with Conductor

 🤖agents

Agentic Search Models with OpenSearch and Elasticsearch

 🗃️databases  Content type: Blog
bonsai.io··Hacker News

miniReranker: Efficient Multimodal Reranking through Visual Cache Reuse and Interaction Sparsity

 🎯Reranking  Content type: Academic
arxiv.org·

The AI Curse (Vis the Lisp Curse)

 📍embeddings  Content type: Blog
blog.djhaskin.com··Hacker News

CS Degrees Aren’t Dead. The Entry Level Pipeline Is.

 🤝Multi-Agent Systems  Content type: News

Show HN: Ext-Infer

 Context engineering

hashwnath/KMCP: Open-source MCP server for your docs. Zero LLM at query time. docker compose up and go.

 🎯Reranking  Content type: Code
github.com··Hacker News

Designing Memory for a Minimal Rust Coding Agent, Without a Vector Store

 Context engineering

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

 🗃️databases

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