Developer Tools / AI/LLM observability
Local CLI for analyzing when a coding agent starts degrading as session context fills, using transcript data already stored on disk.
The page clearly presents an AI-adjacent developer tool with a focused purpose: analyzing context degradation in coding agents from local session logs. The README gives a concrete quick start, command examples, report outputs, and a method for evaluating failure signals, which is enough for a useful public listing.
The snapshot does not show a live demo, screenshots of the report output, or how it performs across different agents beyond the Claude Code-style session logs it references. It also leaves some practical details open, such as supported platforms and how much history is typically needed before the analysis becomes reliable.
Last evaluated 12 days ago. Current rank #379. Down 3 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.
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.
Claude Code plugin that blocks dependency edits until a fresh, source-cited version check is recorded, helping prevent hallucinated or stale package versions across npm, pip, Poetry/uv, Cargo, and NuGet.
