Developer Tool / AI Evaluation / Data Format
ARF defines a JSON record format for AI evaluation runs with canonicalization and reproducible SHA-256 digests, so scores can be traced back to the underlying question, model, inputs, and judgment.
The page describes a concrete AI-adjacent developer format with visible structure: ten record types, reference links between records, offline validation, and a deterministic hashing rule. It also shows examples and explains the purpose of the format clearly enough for a public directory listing.
The page is a v0.1 spec and leaves some implementation details unresolved, including schemas and record shapes that may change. It also does not show a packaged library, API, or docs for integrating ARF into another system beyond the format description.
Last evaluated 24 days ago. Current rank #1043. Down 3 spots in the rankings.
A Rust Blu-ray disc analyzer that reimplements BDInfo for BDMV folders and ISO images, with CLI, desktop, and browser/WASM front ends.
WebLLM is a high-performance in-browser LLM inference engine that runs locally in the browser with WebGPU acceleration. It exposes an OpenAI-compatible API, supports streaming and JSON mode, and includes examples for building chat apps and browser extensions.
Molt is an open protocol for letting an AI agent make bounded purchases through disposable, single-use payment credentials. The repo includes a clear quickstart, MCP integration, a threat model, and a working test-mode demo.
Self-hosted observability and control plane for production and coding AI agents, with live timelines, fleet-wide feeds, token budgets, MCP allow/block rules, and support for Claude Code plus a Python sensor.
