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 75 days ago. Current rank #1506. 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.
Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.
A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.
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.
