JSONL-backed telemetry writer for the emerge agent harness.
**Goal:** Full Stack web framework for rapid development of back office applications
Placeholder for AIRGP (Artificial Intelligence Runtime Governance Protocol) — wire-level protocol for runtime AI governance signals. JavaScript/TypeScript reference implementation forthcoming. Spec: https://airgp.space
[Deprecated] IP Fabric Snapshot Inventory Comparison
OpenTelemetry Collector Exporter allows user to send collected traces to the OpenTelemetry Collector
Zero-dependency Korean PII checksum validator — RRN (주민등록번호), BRN (사업자등록번호), Korean mobile phone, masked-RRN. Pure JS, works in Node 18+, Bun, Deno, and modern browsers.
Homebridge plugin for Otodata / Nee-Vo propane tank sensors via HomeKit Humidity Sensor and Battery services
Intelligent sub-agent spawning with automatic model selection for OpenClaw
Sprkl OpenTelemetry grpc automatic instrumentation package.
Persistent project memory for Claude Code — track architectural decisions and query them conversationally
Export your ChatGPT conversations. One command. Fully local.
BMW CarData API integration for Node-RED – OAuth2 Device Flow with PKCE, SoC and telemetry access for electric vehicles
Security scanner for AI agent tools. Local static scan of MCP IDE configs (41 rules, toxic flow heuristics, AAuth visibility, auto-fix, tool pinning). Optional proxy + in-browser dashboard: traffic, findings, AAuth Explorer, YARA, Playground. Smart Scan o
See what your AI-coding session actually cost — and what's eating your context. Local, read-only CLI for Claude Code token/cost attribution.
AgentSonar integration for Open Multi-Agent (OMA) and any Node multi-agent bus: bridges agent-to-agent events to the AgentSonar coordination engine.
Frontend shell and runtime for 1FE micro-frontend applications
Your codebase has memory. Use it.
star compass
OpenTelemetry Tracing
AI-powered icon generation CLI for mobile app developers
Sivru observe — Claude Code session reader, event normalizer, savings counter, replay harness, HTTP+WS server. Strict no-network-egress (DESIGN.md §5.5).
Compare LLM prompt versions. Word/char/line diff + word-frequency delta + token-impact across 40+ models (GPT-5.4, Claude Opus 4.7, Gemini 3.1 Pro, Llama 4 Scout, Grok 4). Multi-version evolution view. Markdown output for PR comments. Runs locally, no net
Collect Redis metrics
Raindrop observability for Claude Code CLI — automatic session, tool call, and prompt tracing via hooks