Developer Tools / AI Security
Stroq is a local action firewall for AI coding agents. It scans tool output, marks risky sessions, blocks dangerous follow-up actions, and keeps a hash-chained audit log, with support for Claude Code, Cursor, Codex, Copilot CLI, Windsurf, OpenClaw, and MCP clients.
The page clearly describes an AI security product with a concrete job to do: preventing injected commands and unsafe follow-up actions in AI coding agents. It shows how it works, which agents it supports, that it is open source, and includes installation, demo, policy, and audit details strong enough for a public listing.
The page is strong on security mechanics, but it is harder to tell how easy it is to adopt in real projects, what configuration options exist beyond the demo flow, and whether there are docs or releases beyond the landing page and examples.
Last evaluated just now. Current rank #357. 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.
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.
