Developer Tools / Security
A local proxy that inspects LLM requests and attachments for secrets before they reach the model, with redaction, rejection modes, and local attachment decoding/OCR.
The page clearly describes a useful AI developer tool: a local proxy for scanning LLM requests and attachments before inference. The README shows how it works, what it protects against, supported OpenAI-compatible endpoints, and quick-start commands, which is enough for a solid public listing.
The crawl does not show test coverage, release status, or how mature the project is beyond the repo contents. It also does not show supported model providers beyond OpenAI-compatible routing or a live demo.
Last evaluated 26 days ago. Current rank #445. Down 4 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.
Lumae is a free native macOS screen recorder and screenshot tool for polished demos, with automatic zooms, cursor smoothing, motion blur, captions, voiceover, and annotated screenshots. It also exposes editing commands over MCP so agents like Claude Code or Claude Desktop can edit projects directly.
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.
