43 stories tagged with #loca, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Loca"
Teaching an AI to know itself: Building a local LLM agent in D
The official blog for the D Programming Language.…
I made my own Perplexity locally, and the only thing I lost was the monthly bill
The experience is almost as good.…
I gave local AI eyes
Point your phone at something and let a local AI agent see it — zero-dependency, LAN or end-to-end-encrypted remote - zyads/eyes…
I tested 7 local LLMs on my NAS for smart home automation, and only one didn't fall apart
And it made my automations a lot better.…
Show HN: Free AI Prompt Gen – A local-first, open-source prompt engineering tool
The best free AI prompt generator. Craft optimal text, image & code prompts for ChatGPT, Gemini, Claude & Midjourney using proven RTF and CO-STAR frameworks.…
I paired a local LLM with Obsidian on my phone, and it's the productivity boost I didn't expect
A mobile AI stack that works even when the signal doesn't…
Local media needs support if devolution push is to succeed, publishers say
Shift from Westminster risks weakening scrutiny as regional titles battle hostility, big tech and ‘news deserts’…
Should Glasgow have its own mayor?
The BBC's David Wallace Lockhart asks if Scotland's largest city should have its own elected mayor.…
Local News Is Dying. This 25-Year-Old Bought His Hometown Paper Anyway.
Two weeks ago, Evan Newton purchased a local paper in Georgia. He has three employees and a dream, writes Frannie Block.…
Show HN: Brainstorm – a local-first, AI-native OS for knowledge work
Brainstorm is a local-first, AI-native operating system for knowledge management. Your apps, your data, and your AI all run on your machine, with optional end-to-end encrypted sync…
Building an Infinite Memory Local AI Stack on Fedora
Notes on how to build a Personalized Long-Term Memory RAG using Mem0 and Qdrant…
Show HN: Prompt-scrub – local-first PII redaction for LLM prompts and responses
Built by the [Nano Collective](https://nanocollective.org), a community collective building AI tooling not for profit, but for the community. This is the first public release of `…
Extending older smartphone lifespans with local-first AI and zero cloud uploads
Contribute to mike5gao/setting-for-me development by creating an account on GitHub.…
Fluency Is Not Authority: Building Local AI Characters for Signal Drift
Building local AI characters for Signal Drift without letting fluent output rewrite the fiction.…
Fluency Is Not Authority: Building Local AI Characters for Signal Drift
Building local AI characters for Signal Drift without letting fluent output rewrite the fiction.…
Android rolls out local ‘Documents’ backup that syncs to Google Drive
Google now lets Android users upload files and other downloads from their phone or tablet to Google Drive thanks to a new “Documents” backup.…
Show HN: Collie – a local AI harness that runs the browser, desktop and code
A local-first coding agent that proves its own work — one cross-platform Python codebase, one-click Windows installer. - colliehq/collie…
Exploring Apple Silicon’s local AI performance with the Mac Studio and M4 Max — M4 Max beats GB10 and Strix Halo in decode throughput, but memory bandwidth isn't everything
Does higher memory bandwidth make for the best local AI platform?…
Show HN: A minimalist proxy for your local LLM cluster (~1100 lines)
Lightweight API key proxy for llama.cpp servers with per-user token usage tracking. - robolamp/smol-llm-proxy…
MING and Royal Selangor Tap Local Pewter Craft for the All-New 37.06 Watch
Summary MING and Royal Selangor debut the 88-piece 37.06 Titanium Watch.It features a hand-hammered pewter dial made in Kuala Lumpur.Retailing for CHF 5,000, it marks MING's first …
Firm that uses AI to locate ancient lost shipwrecks is hiring a literal pirate to salvage sunken treasure, paying up to $500,000 a year — AI mines 500 years of Spanish colonial records spanning 80 million pages to find undiscovered wrecks and lost cargo
You'll have to provide your own bottles of rum, though.…
Cisco 'retires' its Azure Local offering rather than catch up to Microsoft’s changed hardware requirements
Redmond now allows only locked-down rigs with joint software and hardware support for its on-prem hyperconverged cloud and Switchzilla won't go there…
'The Maw' skulls and terminal locations in Halo Campaign Evolved
A guide on where to find the three skulls and one terminal location during "The Maw" level in Halo: Campaign Evolved.…
Connecticut Governor Allocates Millions in Taxpayer Cash for TPS Aliens
Almost right after an illegal alien killed an officer and his girlfriend in Connecticut, the governor there proposed allocating millions of dollars for individuals who are now also…
Show HN: A local merge queue for parallel Claude Code agents
I have been pushing up to 90 commits a day on a MacBook Air via 4-5 parallel agents. As you can imagine when all the agents try to build, test and run dev servers on an 8GB machine…
OpenLore: Deterministic, local-first memory and guardrails for AI coding agents
Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path. - clay-good/OpenLore…
I ditched Claude Code after giving my local LLM filesystem access
One MCP, and I don't have to let cloud-based tools handle my files anymore…
Show HN: Hunch – A local MCP that lets your LLM use your Mac in the background
Drive your Mac focus-free over MCP: OS APIs, AppleScript, CDP, and Accessibility - PrithviSeran/hunch-mcp…
“Clapping Is a First Amendment Right:” An Interview With the Person Arrested for Clapping at a Data Center Meeting
"I have a right to speak. I'm here to speak. I have a right to clap, and if you want me out, you're going to have to drag me out."…
You can stream local TV channels for free — here's how
Through the use of antennas, streaming from apps like YouTube TV and Hulu, and free platforms like Tubi and PlutoTV, you can get local sports and news for free.…
Show HN: Qwen Scribe – local transcription and dictation for Apple Silicon
Private, local transcription and system-wide dictation for Apple Silicon. - VladUZH/qwen-scribe…
ACR, a local-first AI orchestration runtime (memory, skills, agents
Local-first AI orchestration runtime: persistent memory, skills, and task/agent orchestration, all on SQLite. No cloud account or API key required. - hbkdad/arc…
Bird flu is spreading locally and Australia faces more wildlife deaths. How bad could it get?
Authorities say local transmission of H5 bird flu virus among South Australian birds signals ‘shift in the situation’…
'The Library' skulls and terminal locations in Halo Campaign Evolved
A guide on where to find all skull and terminal locations during "The Library" in Halo: Campaign Evolved.…
‘Farage’s got to come clean or clear off’: what voters on Clacton beach think about their MP – and the country
Nigel Farage’s constituency takes in genteel resorts and one of England’s poorest villages. With a snap byelection approaching, what do the residents want from the Reform UK leader…
New sw dev tool for safe local AI usage
Contribute to alexs60/safe-sde development by creating an account on GitHub.…
My phone runs local LLMs faster than my gaming PC, and it's the setup I actually reach for every day
The PC wins on paper, but the phone wins in practice…
I ran a local LLM on integrated graphics instead of buying a GPU, and the results surprised me
Most people assume local AI requires expensive hardware, but my real-world test on integrated graphics tells a different story.…
Show HN: Writekin – fine-tune a local LLM on your own writing, on your Mac
Writing that's kin to yours. Contribute to scouttyg/writekin development by creating an account on GitHub.…
iOS 27 includes smarter Find My location sharing for Apple Watch users
The Find My app is used by millions of people to find their misplaced devices in a pinch, and millions...…
How Much Does a Local LLM Actually Cost to Run? I Measured Every Watt on Apple Silicon
Five models, sustained generation, real wall-socket energy at $0.31/kWh — and the surprise the RTX-3090 numbers predicted, only bigger.…
Show HN: Higgs, a local AI CLI for Proton Mail (no cloud, no telemetry)
Agent-first CLI for Proton Mail. Local AI inbox classification, search, and Q&A via Proton Mail Bridge and Ollama. Nothing leaves your machine. - higgscli/higgs…
I ditched Claude Code for a local model and a cloud supervisor, and it's twice as fast
The cloud plans, Qwen does chores.…