Developer Tools / Code Assistant
Open-source harness for measuring how consistently hosted LLM APIs return the same output across repeated runs and over time, with raw transcripts, scoring, and a static leaderboard generator.
The page clearly describes an AI-adjacent developer tool with a specific purpose: benchmarking reproducibility of hosted LLM APIs at the byte level. The README shows quickstart instructions, scoring workflow, supported providers, methodology, and the fact that results are recomputable from raw transcripts, which is enough evidence for a useful public listing.
The snapshot cuts off before the full README ends, so it is hard to verify the complete scope of supported cases, current maintenance status, and whether there are ready-made example runs or published results beyond the reference leaderboard described here.
Last evaluated just now. Current rank #730. 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.
