News for hackers. Stuff that matters.

justagoat

Thanks for checking out ArguSeek! We’d love your feedback.especially on any obscure sources you think we should crawl, and bugs or edge cases you hit. Please feel free to fire away any questions or suggestions.

Show HN: ArguSeek – Agent‑first deep‑search API for hard‑to‑find dev answers

https://agruseek.com/

Hi HN,Even the smartest AI coding agents stall when the fix isn’t in their training data. AgruSeek runs an agentic search loop across ~30 M developer sources to dig up solutions normal web search misses.REAL‑WORLD USES• Found an undocumented `--runtime‑bypass` flag (buried in a 2017 gist)• Pulled actual Claude Code pricing from forum anecdotes - no “contact us” paywalls• Traced a race condition...

( Read More... | 4 comments | 4 points | on HN )
Re: on Sunday June 22, 2025 @02:51PM (#44349340)
Hi HN,

I came across this project and thought it was worth sharing. It’s called ChunkHound, a local-first, offline code search engine that lets AI assistants (and humans) explore and search large codebases — semantic search, regex, MCP protocol, etc.

After speaking with the developer, I learned something pretty wild.

The entire project — specs, architecture, implementation, even the name — was generated by an AI coding agent. No human coding, just high-level prompting with a factory-style system feeding the agent tasks and specs. The agent handled the full build end-to-end.

In a way, it even indexed itself once it was done.

* Local-first semantic + regex search (Tree-Sitter + DuckDB)

* MCP server to serve AI agents (Claude, Cursor, VSCode, etc.)

* MIT licensed

Repo: https://github.com/ofriw/chunkhound

Re: on Thursday March 20, 2025 @12:06PM (#43425101)
Large Language Models (LLMs) dominate AI, but Small Language Models (SLMs) are emerging as a serious alternative. They are faster, more cost-effective, and privacy-focused, making them ideal for on-device AI in sensitive industries like healthcare, finance, and defence.

Why SLMs?

* No Cloud Costs – Runs locally, eliminating expensive API calls

* Privacy First – Data stays on-device with no third-party servers

* Low Latency – Real-time AI without cloud dependency Offline AI – Works in planes, submarines, and remote areas Customizable & Efficient – Tailored AI without large-scale infrastructure

The Challenge

Running AI Locally Deploying SLMs on resource-constrained devices is difficult. Even a small 7B model requires optimization techniques like quantization and pruning to run efficiently. Local data storage is another issue—traditional AI systems rely on the cloud, but for true Edge AI, we need a local-first approach.

The Experiment

Running AI Fully Locally We built a ChatGPT-style AI assistant that runs entirely in the browser with no network connection required.

Stack

SLM (Stories15M) running fully in-browser with wllama GoatDB for local chat history storage Zero cloud dependencies This is just the beginning. SLMs and Edge AI could enable medical AI chat applications that are HIPAA-compliant, offline assistants for embedded systems, and much more.

Read more at: https://dev.to/nadav_benitzhak_7703f5b2/the-case-for-edge-ai...

Show HN: SQLite vs. GoatDB: Surprising Benchmark Results for a New Realtime NoDB

https://goatdb.dev/benchmarks/

We introduced GoatDB just three weeks ago and have been blown away by the community’s response. Your feedback and excitement genuinely exceeded our expectations—so first and foremost, thank you from all of us!For anyone just hearing about it: GoatDB is a real-time, version-controlled NoDB for Deno and React that’s edge-native, meaning it requires only minimal backend infrastructure without...

( Read More... | 2 comments | 4 points | on HN )

Show HN: Order Stamps – A String-Based Trick for Effortless List Ordering

https://github.com/goatplatform/orderstamp-js

Hey HN,our small team recently stumbled onto a neat approach for handling ordered lists in DBs without all the reindexing headaches. We’ve been calling it Order Stamps, and we originally built it for our own distributed database project, GoatDB. The concept is simple—treat the “position” of each list item as an infinitely splittable string rather than an integer index.Why bother? Ever inserted...

( Read More... | no comments | 2 points | on HN )

Show HN: GoatDB – A Lightweight, Offline-First, Realtime NoDB for Deno and React

https://github.com/goatplatform/goatdb

Hey HN,We've been experimenting with a real-time, version-controlled NoDB for Deno & React called GoatDB. The idea is to remove backend complexity while keeping apps fast, offline-resilient, and easy to self-host.Runs on the client – No backend required, incremental queries keep things efficient. Self-hosted & lightweight – Deploy a single executable, no server stack needed. ...

( Read More... | 46 comments | 4 points | on HN )