Developer Tools / Benchmark
Public benchmark for comparing agent memory systems, with separate textual and coding tracks, submission flow, documentation, and API guidance.
The page clearly presents an AI-adjacent developer product: a public benchmark and leaderboard for agent memory systems. It includes the benchmark scope, track structure, evaluation flow, API contract guidance, submission routes, and public ranking information, which is enough evidence for a useful directory listing.
The snapshot does not show actual leaderboard results, sample outputs, or concrete technical details of the dataset and scoring beyond the high-level flow. It also leaves the current status of submissions and published evaluations somewhat unclear.
Last evaluated 18 days ago. Current rank #765. 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.
