Developer Tools / AI/ML Frameworks
HyperSAE is a Python package for mechanistic interpretability that trains hyperbolic sparse autoencoders on LLM activations. The page includes installation steps, a quickstart example, benchmark tables, and a short software architecture overview.
The repository clearly presents an AI-related developer tool with a defined use case: building sparse autoencoders for LLM interpretability. The snapshot shows install instructions, a runnable quickstart snippet, named modules, and benchmark results, which is enough evidence for a useful public listing.
The page does not show a full API reference, training data/licensing details, or enough context to verify the benchmark setup and claims beyond the snippets shown.
Last evaluated 20 days ago. Current rank #1545. Up 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.
