News for hackers. Stuff that matters.

ryaker

ryaker on Hacker News

Re:Show HN: Coasts – Containerized Hosts for Agents on Thursday April 02, 2026 @11:41PM (#47622959)
What is the memory footprint? If running on a mac how does it do in terms of being able to run other things concurrently?
Re:Show HN: Flight-Viz – 10K flights on a 3D globe in 3.5MB of Rust+WASM on Thursday April 02, 2026 @11:39PM (#47622945)
QWhere are you getting the flight data?

Show HN: SparrowDB, SQLite of graph DB, written in Rust, Cypher compatible

Posted by ryaker on Thursday April 02, 2026 @08:11AM
from the show-hn dept.

https://github.com/ryaker/SparrowDB

SparrowDB is an embedded Cypher graph database written in Rust. It links into your process the way SQLite does.I built it because I wanted a graph DB without running Docker or a cloud instance.SparrowDB kicks butt at point lookups, global COUNT(*), and top-10 by degree but lags on traversals (1-hop, 2-hop, and variable-length paths).It's an embedded engine with no parallel execution vs a warmed...

( Read More... | 1 comment | on HN )
Re:Show HN: FlowScript – Agent memory where contradictions are features on Thursday March 26, 2026 @11:06PM (#47538689)
I'll have to check this out. I'm very much interested in AI memory.

Show HN: Zora, AI agent with compaction-proof memory and a runtime safety layer

Posted by ryaker on Wednesday March 18, 2026 @09:16AM
from the show-hn dept.

https://github.com/ryaker/zora

In February, Summer Yue, Meta's director of AI alignment, posted about her OpenClaw agent deleting 200+ emails after she'd told it to wait for approval. She screamed "STOP OPENCLAW" at it. It kept going.The root cause: her constraint lived in the conversation. When the context compacted, it disappeared. The AI hadn't gone rogue; it had genuinely forgotten.Zora's safety architecture is designed...

( Read More... | no comments | 2 points | on HN )
Re:Zora Agent:local AI agent that can't be hijacked mid-task by contex... on Friday February 27, 2026 @04:36PM (#47185975)
Built this after watching agents go rogue because their safety instructions got compressed away mid-task. Summer Yue's inbox incident this week is exactly the failure mode I designed around. The core problem: "confirm before acting" lives in chat history. Chat history gets compacted. Instruction disappears. The agent keeps going. Zora uses HMAC-SHA256 signed intent capsules that travel separately from the conversation context. Compaction can't touch them. The original mandate stays intact no matter how long the task runs. Three commands to try it: npm i -g zora-agent zora init zora ask "summarize files in ~/Projects" Multi-model with automatic failover (Claude, Gemini, Ollama). Policy file controls exactly what it can touch. Full audit log. OWASP LLM Top 10 hardened. MIT. Happy to answer questions about the security architecture.