AI Developer Tool / Benchmarking / evaluation
Pull request adding TY25 support for moonshotai/kimi-k3 in TaxCalcBench through OpenRouter. The snapshot shows benchmark wiring, PDF handling details, saved outputs and evaluation reports, and regenerated charts/results for the full TY25 set.
The page clearly describes an AI-related developer benchmark update with concrete implementation and validation evidence: OpenRouter integration, model-specific reasoning settings, PDF input handling, saved outputs, evaluation reports, and test/chart regeneration. It is specific enough to be useful as a public listing and is clearly tied to an AI benchmark project rather than generic discussion.
This snapshot is a merged pull request, so it does not fully show the surrounding repository structure, how to run the benchmark end to end, or the broader scope of TaxCalcBench beyond TY25/Kimi K3 support.
Last evaluated 40 days ago. Current rank #1689. Down 1 spot in the rankings.
A local-first Node.js utility that redacts emails, phone numbers, paths, secrets, URLs, and other identifiers from LLM prompts, then rehydrates responses locally using session-based mappings.
Self-hosted, OpenAI-compatible AI gateway for private RAG, natural-language data access, and tool-calling agents. It connects files, databases, vector stores, APIs, and MCP tools through one backend with auth, observability, and governance features.
A Claude Code skill that lets the model inspect live camera frames so it can verify hardware displays, spot wiring issues, and check physical UI behavior on real devices.
Runtime safety net for LLM agents that detects runaway token growth, classifies failure patterns, and suggests fixes without extra LLM calls. The project includes a Rust core, Python SDK, examples, benchmarks, and benchmark claims across multiple models and runs.
