Search

Report from inside your app to TellMeWhenDown — cron heartbeats and self-checks in one line.

Installable Realtime Register REST API v2 agent skill and CLI. Ships SKILL.md, 109 operation references, and the rtr validation/doc CLI. Install with `npx @cave-man/realtime-register-skills install`.

ElizaOS plugin for @arcproof/sdk -- native orchestrator + specialist builders (runtime.useModel, no LangChain needed) plus the Action/Plugin wrapper, for a bonded, independently-verified, real-payment agent.

LangChain.js adapter for @arcproof/sdk -- turn any LangChain.js tool-calling agent into a claim-gathering step for the ArcProof trust layer.

Structured tracing model for graph agent runs.

Persistent memory plugin for opencode — ports codex's two-phase memory system (extraction → consolidation → injection → citation feedback)

Subject segmentation and image classification for React Native. Vision on iOS, ML Kit on Android. Built with Nitro Modules.

Browser automation and web research tools for pi — search, visit, screenshot, interact, and inspect console output

Provides all core functionality for RapidREST based backend services.

Save AI tokens: index your codebase for LLMs and cut token usage by up to 99%. One command creates a compact project map (repo map) that Claude, ChatGPT, Gemini, Cursor and Copilot read instead of exploring your code. Local, zero dependencies, auto-update

Pi extension for checked plans, live reports, completion acceptance, and quality checks.

Ultimate reusable TypeScript fullstack/backend template scaffolder with Bun, React, Fastify, Drizzle, and security tooling

Two-phase planning workflow for pi — plan with claude-opus-4-6:medium, execute with gpt-5.5:low, with .plans/ file-based handoff

Download, run, and serve local AI models through a gateway-first CLI with OpenAI- and Ollama-compatible APIs.

Auto-model router middleware for the pi.dev coding agent

Local-first Git history investigation, portable reports, and PR impact automation.

The meirlabs loop-engineering skill — drive a big goal end-to-end as a multi-agent orchestrator. Fan out as many haiku/sonnet/opus subagents as the goal needs, pick the model tier per task, plan first and get the plan approved before any large fan-out, ad

General-purpose permission system for pi tools, handling permissions for bash and file tools with extensible matchers for custom tools.

TypeScript SDK for Axon Protocol — multi-agent coordination, shared memory, resource locking, and reasoning receipts

AI orchestration for fullstack devs — provider failover, structured output, RAG, and streaming. One library, zero markup.