11 packages matching “pushary”
@pushary/agent-hooks
v0.78.0 · 5 hours ago
Permission hooks for AI coding agents: route tool approvals through Pushary push notifications
No known vulnerabilities
@pushary/server
v1.3.3 · 15 hours ago
Pushary Server SDK: send push notifications and add human-in-the-loop approvals to your AI agent (pause on a decision until a specific human answers).
No known vulnerabilities
@pushary/eve
v0.2.1 · 15 hours ago
Eve tools and a Pushary channel: pause your agent until a real human approves on their phone (human-in-the-loop).
No known vulnerabilities
@pushary/ai-sdk
v0.1.2 · 15 hours ago
Vercel AI SDK tools for Pushary: pause your agent until a real human approves on their phone (human-in-the-loop).
No known vulnerabilities
@pushary/eve-extension
v0.1.2 · 14 hours ago
Pushary extension for Eve: ask a real human on their phone and block on a fail-closed answer.
No known vulnerabilities
@pushary/sdk
v1.0.10 · 15 hours ago
Pushary Web Push Notification SDK - Add push notifications to your website in minutes
No known vulnerabilities
n8n-nodes-pushary
v0.1.0 · 1 month ago
n8n community node for Pushary: send push notifications and pause your workflow for human approval from your phone or Slack.
No known vulnerabilities
@pushary/durable
v0.1.1 · 15 hours ago
Durable human-in-the-loop for Inngest, Temporal, and Vercel Workflow: park your workflow until a real human approves on their phone, resume on a signed webhook.
No known vulnerabilities
@pushary/mastra
v0.1.2 · 14 hours ago
Human-in-the-loop for Mastra: a blocking createTool that asks a real human on their phone, plus a durable suspend/resume workflow step.
No known vulnerabilities
@pushary/langgraph
v0.1.2 · 14 hours ago
Human-in-the-loop for LangGraph and LangChain: a blocking ask_human tool, plus a durable interrupt()/Command resume that reaches your user on their phone.
No known vulnerabilities
@pushary/openai-agents
v0.1.1 · 15 hours ago
Human-in-the-loop for the OpenAI Agents SDK: a function tool that asks a real human on their phone and blocks on a fail-closed answer.
No known vulnerabilities