An AI-assisted security testing workspace for authorized engagements. - hackingpal/hackingpal Read more ›
Nub is a TypeScript-first toolkit for Node.js: run TypeScript files on stock Node, a faster npm run, a pnpm-compatible package manager, and a built-in Node version manager. No lock-in. Read more ›
A single hijacked maintainer account pushed multiple trojanized packages across the entire @mastra scope in 27 minutes, each carrying a typosquat dependency that runs a remote payload on install. Combined reach is over 28 million downloads a month. Read more ›
KonxiOS is your personal AI-powered operating system that automates tasks, manages workflows, and enhances productivity with intelligent assistance built direct Read more ›
Early Stage Project TOPF has just been released and is in an early stage of development\. While it is actively used at PostFinance, APIs, configuration formats, and CLI flags may change between releases\. Feedback and contributions are welcome — please open an issue if you run into problems or have suggestions\. Get Started ## What TOPF does TOPF is a single binary that handles the full lifecycle of a Talos cluster: - **Apply configurations** with pre-flight health checks, dry-run diffs... Read more ›
ik_llama.cpp fork with experimental NUMA per-node mirroring of model weights and KV cache. This is an attempt to maximize CPU inference performance on multi-socket systems. - mikechambers84/ik_llam... Read more ›
An old Android phone + a prepaid SIM = a dedicated SMS number your AI agent can send and receive from. Open source. Connect any MCP client. Read more ›
One example caused a stir across the industry: an AI consultant told the news outlet Axios that one of their clients burned through roughly half a billion dollars in a single month because no usage limits had been set on the employees’ AI licenses. The case sounds extreme, and at that scale it is the exception. The underlying pattern is not. On a smaller scale, many organizations are experiencing it right now: a bill jumps from a few hundred to several thousand euros a month, without any alar... Read more ›
You'd think that given the same bytes of input you'd get the same bytes of output. lol. lmao. No, you don't. It's complicated. Read more ›
Hello there, I'm a human with way too many interests. Read more ›
具備 Beam Search 候選排序、受管行動閘道、程序技能學習與後台技能策展守護程序的自律型 AI 代理人系統。 Read more ›
I’ve been running a mixed Proxmox cluster for years – four nodes of wildly different capability, from an Atom x5-Z8350 with 2 GB of RAM (a z... Read more ›
Multi-agent SRE systems fail in three main ways: agents with conflicting goals acting on the same infrastructure, stale state causing agents to act on outdated facts, and deadlocks where agents freeze waiting on each other. The fix isn't smarter agents, it's better architecture. Build a shared state layer, codify a priority hierarchy (security beats SLA beats cost), add an orchestration layer with real authority to block conflicting actions, classify actions by risk tier, and define explicit ... Read more ›
--- ## TLDR In this work, we explore how to make language models better at generating high performance **HIP kernels** for **AMD GPUs**\. We present the following: 1. A **synthetic dataset** of 500 new PyTorch reference tasks using **mutation**, **composition**, and **constraint-based generation** to cover a broader range of workloads\. 1. A **multi-agent optimization pipeline** for HIP kernel generation\. Instead of relying on single-shot prompting, we used specialized agents for tas... Read more ›
LLM inference in C/C++. Contribute to ggml-org/llama.cpp development by creating an account on GitHub. Read more ›
Why deployment status is not a UI label, but a consistency problem across databases, queues, workers, locks, reconcilers, Kubernetes, and user trust. Read more ›
How good are local LLMs at translation, and do you actually need the cloud? A reproducible benchmark of 24 on-device, self-hosted, and cloud models translating into English, with the low-resource case (Afrikaans) front and centre. The headline: on Afrikaans→English a local 18 GB model lands in a statistical tie with frontier cloud. Same blinded Tatoeba sentences, same prompt, greedy decoding, scored multi-reference with COMET (meaning) and chrF++ (surface). Built to pick a translation model f... Read more ›
Add a streaming AI chat to any website, in minutes. Themeable, pluggable, zero framework dependencies. Read more ›
Local emulator for Google BigQuery. DuckDB-backed, SQLGlot-powered. Drop-in replacement for the real service in dev, CI, and offline replicas. - jjviscomi/bqemulator Read more ›
Enterprises that onboard AI assets (MCP servers, agents, skills, and multi-step workflows) need to govern these assets and make them discoverable without blocking innovation. Central IT maintains a list of approved MCP servers and skills for the organization. Each line of business also publishes its own assets to its team, and often to the wider […] Read more ›