Developer Tools / AI Inference
AirLLM is an open-source inference library that aims to run very large language models on small GPUs by decomposing models layer-wise and streaming them during execution. The snapshot shows a detailed README with quickstart code, model examples, supported model notes, and recent update history.
The page clearly presents a real AI developer tool with a specific technical goal: running large language models on limited GPU memory. The crawl includes enough README evidence to understand what it does, how to install and use it, and which model families it supports. It also shows concrete examples, performance claims, and recent updates, making it useful for a public directory listing.
The snapshot does not show benchmark methodology, licensing or maintenance details beyond the repo files list, or enough context to verify the performance claims independently. It also cuts off mid-instructions, so the full setup and configuration flow is not completely visible.
Last evaluated 39 days ago. Current rank #122. Holding steady 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.
