Developer Tools / AI Agent Safety
A lightweight shell-based guard that blocks destructive commands before an AI coding agent can run them. It targets risky actions like git reset --hard, rm -rf, force-pushes, and destructive cloud/database commands, with local regex rules and a test script.
The page clearly describes an AI-adjacent developer tool with a specific job: preventing coding agents from executing destructive commands. The README shows how it works, what it blocks, how to install and test it, and the intended integration with agent CLIs and Claude Code hooks. It is focused, useful, and concrete enough for a public listing.
The snapshot does not show a demo beyond the example text, and it’s unclear how broad the hook compatibility is outside Claude Code and shell-based agent CLIs. There is also no visible release history or adoption signal, so visitors cannot tell how mature or widely tested it is.
Last evaluated 16 days ago. Current rank #1035. 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.
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.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
A lightweight React Markdown renderer with built-in LaTeX, syntax highlighting, streaming-safe rendering, and security-focused defaults.
