Desktop-inspired terminal diff viewer for understanding agent-authored changesets.
Docker container sandbox provider for Mastra workspaces
Message Handler plugin for Veramo
Local AI coding agent observability dashboard for Claude Code, Codex, OpenCode, OpenClaw, and Qoder. Track token usage, estimated cost, tool calls, subagent trees, and replay full sessions from local JSONL/SQLite files — no cloud, no telemetry.
Node.js native bindings for the Open Wallet Standard
Persistent memory for Pi agents — one local-or-cloud brain shared across sessions, compactions, and MCP agents
[](https://github.com/WillBooster/agent-runtime-kit/actions/workflows/test.yml) [ integration for PEAC
A lightweight agentic workflow system for testing AI agent flows with local LLMs and tool integrations
fetch wrapper with support for automatic HTTP proxy, timeout and accessible agent options
[internal] Common utilities and constants for NAISYS
Diagnose and fix React codebases for security, performance, correctness, accessibility, bundle-size, and architecture issues (fork of millionco/react-doctor with --hide-branding HTML report for CI).
Routes messages from phone channels to project-specific Claude Code agents
MCP Gateway for exposing VAT agents through Model Context Protocol
Octoryn LLM official command-line interface
SuPi Insights extension — generate usage reports analyzing your PI sessions
Cursor Agent CLI — installs the official Cursor Agent binary via npm
Agent Library
Scaffold agent-ready academic research repositories with SOTA, source ledgers, wiki memory, MCP setup, and project-local skills.
This document describes how `@rudderhq/agent-runtime-openclaw-gateway` invokes OpenClaw over the Gateway protocol.
Experimental package to simplify integrating AI into Fluid-based applications
<p> <img src="banner.png" alt="pi-intercom" width="1100"> </p>