Developer Tools / AI Safety
Open-source runtime guardrails for AI agents that intercept unsafe tool calls before they execute, aiming to block prompt-injection-driven exfiltration and other policy violations.
The snapshot shows a real AI developer tool with a focused purpose: runtime guardrails for agent tool calls. The README explains the problem, the execution-layer approach, quickstart usage, when to use it, and demo scripts that show the block in action. That is enough evidence for a useful public listing.
The crawl does not show package details, supported frameworks, installation/version info beyond a pip hint, or the full set of built-in policies and configuration options.
Last evaluated 27 days ago. Current rank #785. Down 6 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.
