27,464 packages matching “human-approval”
lucifer-gate
v0.9.1 · 10 days ago
AI agent command firewall with Telegram-based human approval
No known vulnerabilities
@rendotdev/lgtm
v0.2.7 · 17 days ago
Human approval for agent work, with code diff and Markdown review.
No known vulnerabilities
@github-tools/sdk
v1.11.1 · 1 day ago
A typed tool layer for GitHub AI agents, with presets, human approval, and durable execution. Works with eve, the AI SDK, Vercel Workflow, and Chat SDK
No known vulnerabilities
ajnas-runtime
v0.2.2 · 21 days ago
Policy-gated agent workflow runtime with provenance receipts and human approval checkpoints.
No known vulnerabilities
ajnas-approvals
v0.1.3 · 21 days ago
Human approval workflows, deterministic review tickets, escalation, delegation, and audit receipts for Ajnas agent infrastructure.
No known vulnerabilities
confirm-mcp
v0.1.2 · 24 days ago
MCP server for Confirm.dev: gives any MCP agent a human-approval tool for risky actions.
No known vulnerabilities
inspectrum
v0.2.3 · 9 days ago
Automatic Codex plan review in Claude Code; on-demand in local MCP hosts; human approval stays yours
No known vulnerabilities
@agentfield/hax-sdk
v0.2.8 · 1 month ago
TypeScript SDK for the HAX (Human Approval eXchange) API
No known vulnerabilities
@contro1/claude-code
v0.2.1 · 22 days ago
Contro1 human-approval hook for selected Claude Code actions
No known vulnerabilities
clearance-mcp
v1.0.0 · 21 days ago
MCP server for Clearance — human approval API for AI agent commerce
No known vulnerabilities
@oked/sdk
v0.3.6 · 1 month ago
OKed SDK - human approval layer for AI agents
No known vulnerabilities
orangerail-mcp
v0.1.5 · 4 days ago
Serve an ontology registry as an MCP server: typed read tools, destructive writes staged for human approval, and an audit log of every call.
No known vulnerabilities
@adjudicate/approval-engine
v0.3.4 · 1 month ago
Reference human-approval orchestration for REQUEST_CONFIRMATION flows — pluggable channels (webhook, Slack, Teams, email) + a replay-safe resume via adapter-core confirm().
No known vulnerabilities
@paraph/sdk
v0.2.1 · 7 days ago
Paraph SDK — tamper-evident records and human-approval gates for AI agents. EU AI Act Articles 12 + 14.
No known vulnerabilities
@mekik/langchain
v0.7.1 · 9 hours ago
LangChain integration for mekik — surface agent tool calls in the UI, gate them behind human approval, and make them exactly-once across an interrupt/resume.
No known vulnerabilities
@byliner/mcp-agent
v0.2.0 · 20 days ago
MCP server letting an AI agent submit actions for multi-party human approval via Byliner. Cannot approve, reject, or delegate — by design.
No known vulnerabilities
gate-sh
v0.1.0 · 28 days ago
ntfy tells you things. gate asks you things. Human approval as a curl.
No known vulnerabilities
enkreesee-mcp
v5.0.0 · 11 days ago
MCP server that lets AI agents request human approval and block until a person decides in Enkreesee.
No known vulnerabilities
@oz-lunara/belay
v0.6.0 · 1 day ago
Belay — a local-first guardrail for AI coding agents (a Lunara product). Intercepts an agent's database/infra actions, computes the blast radius, blocks destructive ops until keychain-gated human approval, and writes a cryptographically signed audit log.
No known vulnerabilities
@runestone-labs/gatekeeper-mcp
v0.1.1 · 1 month ago
MCP server that runs agent tool calls (shell, files, HTTP, …) through Runestone Gatekeeper — policy enforcement, human approval, and audit for any MCP client
No known vulnerabilities