Recently Added
3,528 documents
PkVision — Roadmap
Lists 30+ planned features and improvements for a tricking detection and scoring system, organized into six categories.
About Azure PowerShell Toolkit
Documents a 772-script Azure PowerShell toolkit, its quality status, known issues, and a three-phase remediation plan.
Prometheus Automation AI Marketplace - Project Documentation
Documents an enterprise AI marketplace built with Next.js 15, covering architecture, AI algorithms, security, and deployment.
Summary
Bridges CARLA and Autoware for scenario-based testing, supporting both dynamic scenario generation and benchmark mode.
SPEC: HackTheBench Agent Support
Specifies how AI agents compete in a CTF benchmark via SSH and an MCP server, with verified badges on the leaderboard.
Useful Data Sources
Curates a large collection of open data portals, APIs, teaching datasets, and sector-specific resources for public affairs and nonprofit analytics.
Overview
Aggregates LLM leaderboard rankings with pricing data into a daily-updated CSV and web comparison tool.
Giva - Generative Intelligent Virtual Assistant
Defines a macOS personal assistant with local LLM inference, email/calendar sync, CLI, REST API, and SwiftUI menu bar app.
TerrainGossip: Decentralized Infrastructure for AI Manipulation Detection
> A gossip-based protocol for distributed LLM evaluation, behavioral monitoring, and evidence collection—built to resist manipulation of the monitoring system itself.
Trust: A Multi-Level Exploration and Framework
Explores trust definitions from simple to scholarly, includes mathematical models, code, and resources for AI trustworthiness.
WARP.md
Guides WARP terminal AI on commands, architecture, and conventions for an ASR evaluation and media processing toolkit.
PHM-LLM Template Setup Guide
Guides you through setting up and customising a PHM-LLM template for prognostic health management projects with configuration and variant options.
CLAUDE.md
Defines a financial reasoning benchmark with 306 curated problems across seven categories and evaluation runners for multiple LLM providers.
Large Language Models — Structured Notes
Explains LLM architecture, training pipeline, and deployment concepts from tokenization through quantization.
What If You Could Run 20 AI Agents in One Terminal?
Describes a prototype that runs multiple CLI coding agents in parallel tmux panes, each with its own workspace and task queue.
How to use the AI Technology Radar
Explains the purpose, structure, and usage of a technology radar for AI agents and RAG systems, including segments and rings.
Development notes
Documents iterative model experiments for a financial returns prediction challenge, tracking what worked and what didn't across three versions.
Speed Evaluation
Presents cycle counts, memory usage, and code size for Kyber and NewHope KEM variants on an ARM Cortex-M4 target.
Benchmarks 05/07/2016
Records Go benchmark results for fingerprint database operations across three dates, comparing performance of Python and Go implementations.
Pasto Performance Benchmarks
Provides a template for benchmarking Pasto's HTTP performance across multiple machines and worker counts.
Benchmarks
Compares.NET serializer performance using an echo benchmark with a custom MessageEnvelope type, showing throughput and size trade-offs.
Benchmarks
Compares Tesseract OCR versions 3.05, 4.1, and 5.0 across three tessdata sets, showing execution times in seconds.
Benchmark: pinky
Presents cycle-accurate NES emulator and prime sieve benchmarks comparing PolkaVM against 15+ other VMs across oneshot, execution, and compilation time.
Benchmarks
Presents benchmark results comparing CacheManager handle performance (Dictionary, Runtime, MsMemory, Redis) and serializer throughput using BenchmarkDotNet.