Developer Tools / AI Infrastructure
Reference implementation for using Linux Pressure Stall Information to trim an LLM KV cache under memory pressure. The repo includes requirements, basic usage commands, a simulator, a llama.cpp runner, and benchmark scripts with example results.
The page clearly describes an AI infrastructure tool with a specific technical purpose: trimming an LLM KV cache using Linux PSI. The README shows how to check PSI, run a simulator, build the runner, and execute benchmarks, giving enough evidence for a useful directory listing.
The snapshot does not show a license, API surface, package publishing details, or whether the benchmark results are reproducible outside the included example setup. It also does not explain the internal algorithm beyond the high-level PSI-based approach.
Last evaluated 19 days ago. Current rank #812. Up 2 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.
