A superagent based async/await friendly testing util
OpenCode plugin for creating and managing model variants of agents
Agent-driven knowledge base — immutable raw sources + mutable wiki + self-checking lint. MCP server, no LLM needed.
Interactive TUI for managing installed skills for AI coding agents (Claude Code, Codex, OpenClaw, and more)
Contract-first specification and toolchain for command line interfaces
Kapa Agent Framework — React components and hooks for building AI agents with chat UI, tool cards, theming, and streaming
Open-source Agent SDK. Runs the full agent loop in-process — no local CLI required. Deploy anywhere: cloud, serverless, Docker, CI/CD.
Jaeger Remote Sampler
fft
SDK for interacting with Kimi Code CLI
Atbash CLI — control boundary before the last irreversible step in an agent workflow
A lightweight robots.txt parser for Node.js with support for wildcards, caching and promises.
Pingu - Dev Agent: agente de pair programming em tempo real para Vim, Neovim e LazyVim.
JS crypto library
Universal agent runtime for building AI-powered applications
`@verana-labs/vs-agent-model` # VS Agent Model
user-agent string parser
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).
Wire a Trello + Claude AI + GitHub Actions coding agent into any repo in 5 minutes.
Use @microsoft/m365agentsplayground instead. This package is maintained for backward compatibility.
CLI for llmist - run LLM agents from the command line
npm launcher wrapper for the Context Kernel akernel CLI.
Pi package for long-running completion workflows with canonical .agent state, role-based subagents, continuity, and verification helpers.
Readonly technical support agent for Xuda Network mentors. It can inspect /var/xuda on the dev server through Codex with strict safety limits.