Super-fast validation decorators of NestJS
Hermes Agent adapter — connects Hermes AI agents to a DKG V10 node for verifiable shared memory
Public Preview — AgentOS GitHub Copilot Extension: Build safe AI agents with natural language and 0% policy violations
FlowDeck — structured planning and execution workflows for OpenCode
MCP server that gives Claude Desktop, Cursor, and any MCP client the ability to register, discover, message, and transact with other AI agents on the OceanBus network — no server required.
GLSL fragment shader viewer for Pi Agent — live WebGL preview, Tweakpane uniform controls, presets, probe sheets & video export
Biologically-inspired memory system for AI agents. Decay by default, strength through use.
The secure grip for your agent's secrets - A security-hardened MCP gateway with proxy token authentication
OpenAI Codex CLI integration for AgenticMail — surfaces every AgenticMail agent as a native Codex subagent and wires the dispatcher daemon to the Codex SDK
Agent-first CLI for the Signal Foundry data workspace
Chapterhouse — a team-level AI assistant for engineering teams, built on the GitHub Copilot SDK. Web UI only.
Discord-style AI team chat room
NiuBot Engine — AI Persona Runtime powering autonomous digital coworkers with memory and personality
`@microsoft/app-manifest`
A local-first multi-agent collaboration workspace — bringing humans, AI agents, computers, and tasks into the same chat room
Public bootstrap installer for WE WILL's private Sara QA agent package
AI assistant plugins for Azure Functions — one-command setup for GitHub Copilot, Claude Code, and Codex
This project provides an API to Atrius Personal Wayfinder maps within a Node environment. See the README.md for more information
Drop-in workflow scaffold for AI-assisted coding — works with Claude Code, Codex, Gemini, Antigravity, and any agent loading the open agent skills standard. Project-agnostic: web apps, backends, mobile, CLIs, libraries. Includes /workflow-init slash comma
Cross-runtime local peer-to-peer messaging for IAPeer runtime endpoints using MCP. Ships two bins: iap-mcp (MCP server, invoked from a plugin .mcp.json) and iap (CLI for operators).
Agent evaluation framework with LLM-based grading for AI agent quality assessment
n8n community node — run Cursor Agent via the Cursor SDK (local runtime) with MCP servers and skills.
Generate App Store–ready screenshots with frames, gradients, and captions
Burn-rate meter for AI coding agents. Surfaces quadratic session cost and reasoning-workspace drift; nudges curated handoffs at 50/75/90% via a bundled agent protocol so context resets at position 0 instead of /compact summarizing under pressure. Zero dep