Developer Tools / AI Infrastructure
NakshGuard is a self-hosted reverse proxy for OpenAI and Anthropic chat APIs that detects and blocks runaway AI agent loops before they waste tokens or API spend. It includes per-agent session tracking, configurable thresholds, shadow mode, and hot config reload.
The page clearly describes a real AI infrastructure tool with a specific job: protecting LLM traffic from looping agents. The README shows how it works, the supported APIs, install and run commands, configuration details, endpoints, testing commands, and deployment notes, which is enough for a useful directory listing.
The snapshot does not show release history, package distribution, or evidence of adoption beyond the repository itself. It also leaves open how accurate the loop detection is in practice, and the commercial tier features are only mentioned briefly in another file.
Last evaluated 76 days ago. Current rank #1272. Down 2 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.
