Search Packages

rubrix

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

graphrefly

Reactive harness layer for agent workflows. Describe automations in plain language, trace every decision, enforce policies, persist checkpoints. Python. Zero dependencies.

leashd

Safety-first agentic coding framework. Three-layer safety pipeline (sandbox, YAML policies, human-in-the-loop approval) for AI coding agents. Pluggable runtimes (Claude Code, Codex), autonomous task orchestrator, full audit trail.

e2a

Authenticated email gateway for AI agents — SPF/DKIM verified inbound, HMAC-signed delivery, webhook + WebSocket fan-out, CLI + SDKs

sovigl

SOVIGL — AI agent payment governance SDK. Returns approved, pending, or blocked.

humanlayer

The best way to get AI coding agents to solve hard problems in complex codebases.

longparser

Privacy-first document intelligence engine — converts PDFs, DOCX, PPTX, XLSX, and CSV into AI-ready Markdown + structured JSON for RAG pipelines.

hitl-cli

Command-line interface for Human-in-the-Loop services

argilla-server

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

kontrol-freek-mcp

AI assumption firewall for MCP agents — intercepts risky decisions, checks past decisions, detects contradictions, and gates human approval via Telegram or Slack.

authloop

Python SDK for AuthLoop — human-in-the-loop authentication for AI agents.

jamjet

The safety layer for AI agents: policy checks, audit trails, approvals, replay, memory, cost limits, MCP + A2A.

shannot

Human-in-the-loop execution for LLM agents

diplomat-gate

Approval gates for AI agent payments and emails. CONTINUE / REVIEW / STOP before execution.

mellona-hive

CLI-first orchestration platform for autonomous agents with Git-backed task, run, and memory state

pyspur

A visual playground for agentic workflows: Iterate over your agents 10x faster

h1st

Power Tools for AI Engineers With Deadlines

gohumanloop

💯 Perfecting AI workflows with human intelligence

root-painter-trainer

RootPainter: Deep Learning Segmentation of Biological Images with Corrective Annotation

letsping

Agent trust layer: behavioral firewall, HITL, and Cryo-Sleep state for AI agents.

schema-miner

A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models

haldir

The guardian layer for AI agents — identity, secrets, audit via MCP. Gate + Vault + Watch.

polos-sdk

Polos SDK for Python - Durable Agent Execution

hitl-al-gomg

Active learning workflow to train and fine-tune molecular property predictors with chemist feedback for goal-oriented molecule generation.