Feeds to Scour
SubscribedAll
Scoured 4894 posts in 8.4 ms
MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents  🕹️Agentic AI
arxiv.org·3d
Your Agent’s Context Window Is Not a Junk Drawer  🔧Agent Tooling
paolino.me·2d·Hacker News
Show HN: I built Memory Sync so I don't have to reteach every AI who I am  🪄Prompt Engineering
chromewebstore.google.com·17h·Hacker News
New pi coding agent plugin for local RAG  🔌Claude Plugins
github.com·11h·Hacker News
How to Add Memory to Your Hermes Agent  🔧Agent Tooling
cortexdb.ai·1d·Hacker News
See inside your agent's brain  🔧Agent Tooling
kern-ai.com·5d·Hacker News
Your AI Generates Files. Who Manages Them?  👨‍💻AI Coding
filesfirst.substack.com·1d·Substack
How to Design a Memory System for Agents  🔧Agent Tooling
okbrain.org·5d·Hacker News
How ChatShell Solves MCP Context Bloat with Progressive Disclosure  🤖Agent Protocols
chatshell.app·2d·Hacker News
Radial Priority Indexing: A Self-Correcting Vector Memory for NPCs  🪄Prompt Engineering
heydaytime.net·3d·Hacker News
Ask HN: Why does it look like everyone is abandoning GitHub Copilot?  🌐Open Source
news.ycombinator.com·2d·Hacker News
Ferricula: Thermodynamic Agent Memory  🔢BitNet Inference
ferricula.com·4d·Hacker News
Is RAG Dead? Long Context, Grep, and the End of the Mandatory Vector DB  📚RAG
akitaonrails.com·3d·Hacker News
FinanceBench: Agentic RAG beats full-context by 7.7 points using the same model  🔍Information Retrieval
meetdewey.com·3d·Hacker News
Give Your OpenClaw Agent a Real Memory  ⚡Edge AI
cortexdb.ai·1d·Hacker News
How We Designed Mnemosyne: Six Retrieval Signals, One Engine, and Why Architecture Matters  🪄Prompt Engineering
castnettechnology.com·6d·Hacker News
Gemma 4 Makes Local AI Agents Actually Practical  🤖AI
firethering.com·6d·Hacker News
Gemma 4 E4B vs. Gemma Family: Enterprise Benchmark Across 8 Task Suites  🪝eBPF
aiexplorer-blog.vercel.app·3d·Hacker News
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues  🤖LLM
arxiv.org·1d
Proxy-Pointer RAG: Achieving Vectorless Accuracy at Vector RAG Scale and Cost  📚RAG
towardsdatascience.com·4d

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