Developer Tools / Code Assistant
An open-source benchmark for testing whether LLMs can follow long arithmetic derivations without using tools. It compares models on recall-proof inputs, logs digit accuracy, and reports results across multiple endpoints and model families.
The page clearly describes an AI-related developer project with a concrete purpose: benchmarking LLM reasoning and arithmetic performance without calculator access. The snapshot includes the repo title, README sections explaining the test design, enforcement, scoring method, and result tables with real model comparisons, which is enough for a useful public listing.
The snapshot does not show installation or quick-start instructions, so a visitor cannot tell how to run the benchmark locally or reproduce the results. It also does not surface licensing, release history, or broader repository structure beyond the test files and README content.
Last evaluated 19 days ago. Current rank #768. Down 6 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
