Developer Tools / Code Assistant
A web calculator for estimating whether local LLMs fit on specific hardware and how fast they may run. It covers VRAM, token throughput, latency, power, and cost across multiple GPUs and devices.
The page clearly presents a useful AI-adjacent tool for builders and users working with local LLMs. It explains what it does, shows the main inputs, and exposes practical outputs like VRAM usage, performance, power, and rental cost across many models and devices. The snapshot contains enough product evidence for a solid directory listing.
The snapshot does not show examples, saved presets, model/device tables, or a walkthrough of how accurate the estimates are on real hardware. It also does not say whether the calculator is updated regularly or what sources back the device and model data.
Last evaluated 36 days ago. Current rank #235. Down 3 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.
