Developer Tool / RAG Evaluation
A GitHub example that audits LangChain’s RAG quickstart with retrieval-quality metrics, flags off-topic and out-of-distribution queries, and surfaces ranking and calibration issues with charts and results files.
The page clearly describes an AI developer tool focused on RAG retrieval auditing. The README gives a concrete use case, explains the corpus and retriever setup, and shows the kinds of failures it detects. The snapshot also includes implementation files, result JSON, and charts, which makes it useful for a public listing.
The snapshot does not show installation or run instructions beyond the example content, and it’s hard to tell how reusable the tool is outside this specific LangChain quickstart teardown. Maintenance status, supported frameworks, and a fuller feature overview are also not visible here.
Last evaluated 27 days ago. Current rank #402. Up 4 spots in the rankings.
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.
A Windows system-tray app that shows Claude Code session and weekly rate-limit usage at a glance, with hover and click views for more detail.
Open-source, self-hostable sandbox for AI agents. It lets agents work inside isolated Linux containers through MCP tools, with CLI and host-level admin controls for creating, managing, and exposing boxes.
Open-source autonomous development pipeline for Claude Code that moves from spec and planning through implementation, validation, PR creation, Codex review, and bug triage.
