Hacker News: ryaker

New comment by ryaker in "Show HN: Coasts – Containerized Hosts for Agents"

ryaker — Fri, 03 Apr 2026 03:41:43 +0000

What is the memory footprint? If running on a mac how does it do in terms of being able to run other things concurrently?

New comment by ryaker in "Show HN: Flight-Viz – 10K flights on a 3D globe in 3.5MB of Rust+WASM"

ryaker — Fri, 03 Apr 2026 03:39:57 +0000

QWhere are you getting the flight data?

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

ryaker — Thu, 02 Apr 2026 12:11:25 +0000

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 JVM server with a mature query planner. The traversal workload is not the target. Agents, CLIs, serverless functions that need a knowledge graph without provisioning one, that's the target.

Cold start is ~27ms. If you're in a serverless context where Neo4j's startup time is disqualifying, that matters.

Bindings for Python, JavaScript/Typescript, and Ruby. All open the same on-disk format. Built-in MCP server for Claude Desktop. A Bolt protocol server was just added, so gdotv and other Bolt clients can connect. At-rest encryption with XChaCha20-Poly1305. MIT.

https://sparrowdb.dev Demo: https://www.loom.com/share/0dffc9274f5f4338878fe0ffa61f0f4e

Comments URL: https://news.ycombinator.com/item?id=47613359

Points: 2

# Comments: 1

New comment by ryaker in "Show HN: FlowScript – Agent memory where contradictions are features"

ryaker — Fri, 27 Mar 2026 03:06:06 +0000

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

ryaker — Wed, 18 Mar 2026 13:16:34 +0000

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 so that it can't happen. A few things that are different:

Compaction-proof rules. Policy lives in ~/.zora/policy.toml, loaded before every action, not in context. The LLM and the PolicyEngine don't share a channel.

Prompt injection defense. Every incoming message (Signal/Telegram) passes through a CaMeL dual-LLM quarantine, an isolated model with no tool access that extracts structured intent from raw text. The main agent never sees the original message.

Runtime safety layer. Every tool call is scored 0–100 for irreversibility before it executes. High-risk actions pause and route to your phone for approval via Signal or Telegram. A session risk forecaster tracks drift, salami slicing, and commitment creep across the whole session.

Locked by default. A misconfigured Zora does nothing. A misconfigured OpenClaw has full system access.

npm i -g zora-agent && zora-agent init

https://github.com/ryaker/zora

Comments URL: https://news.ycombinator.com/item?id=47425436

Points: 2

# Comments: 0

New comment by ryaker in "Zora Agent:local AI agent that can't be hijacked mid-task by context compaction"

ryaker — Fri, 27 Feb 2026 21:36:47 +0000

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.

Zora Agent:local AI agent that can't be hijacked mid-task by context compaction

ryaker — Fri, 27 Feb 2026 21:36:47 +0000

Article URL: https://github.com/ryaker/zora

Comments URL: https://news.ycombinator.com/item?id=47185974

Points: 1

# Comments: 2