Human In The Loop Python Packages

rubrix

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

goldenmatch

Polyglot entity-resolution + data-quality toolkit. Zero-config auto-config (negative-evidence + Path Y) hits DQbench composite 91.04 (T3 53.8% → 85.5%). Holds 0.96 DBLP-ACM, 0.94 Febrl3, 0.97 NCVR. GoldenCheck → GoldenFlow → GoldenMatch → GoldenPipe. MCP per package, multi-arch containers, Airflow DAGs, browser workbench.

e2a

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

amx-cli

AI-driven CLI for documenting database schemas. DB + docs + codebase agents, 10 backends, BYO LLM, human-in-the-loop review.

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.

coglang

Graph-first intermediate language for auditable LLM-generated graph queries and updates.

jamjet

The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.

hitl-cli

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

awaithumans

The human layer for AI agents. Your agents already await promises. Now they can await humans.

humanlayer

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

execlave-sdk

Official Python SDK for the Execlave AI Governance Platform — tracing, policy enforcement, and framework auto-instrumentation for LangChain, OpenAI Agents SDK, and CrewAI

argilla-server

Open-source tool for exploring, labeling, and monitoring data for NLP projects.

goldenpipe

Polyglot entity-resolution + data-quality toolkit. Zero-config auto-config (negative-evidence + Path Y) hits DQbench composite 91.04 (T3 53.8% → 85.5%). Holds 0.96 DBLP-ACM, 0.94 Febrl3, 0.97 NCVR. GoldenCheck → GoldenFlow → GoldenMatch → GoldenPipe. MCP per package, multi-arch containers, Airflow DAGs, browser workbench.

sovigl

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

goldenflow

Polyglot entity-resolution + data-quality toolkit. Zero-config auto-config (negative-evidence + Path Y) hits DQbench composite 91.04 (T3 53.8% → 85.5%). Holds 0.96 DBLP-ACM, 0.94 Febrl3, 0.97 NCVR. GoldenCheck → GoldenFlow → GoldenMatch → GoldenPipe. MCP per package, multi-arch containers, Airflow DAGs, browser workbench.

graphrefly

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

intaris

Guardrails service for AI agents. Default-deny tool call evaluation with LLM safety analysis, priority-ordered decision matrix, and human-in-the-loop escalations. Session recording, behavioral analysis, MCP proxy, secret redaction, and real-time audit.

longparser

Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review, 3-layer memory chat, and a production FastAPI server.

browser-handoff

Pause Playwright automation, hand the browser to a human, resume when they're done.

metascreener-lars-ulaval

A plugin-based desktop application for human-in-the-loop systematic literature screening

shannot

Human-in-the-loop execution for LLM agents

pyspur

PySpur is a Graph UI for building AI Agents in Python

diplomat-gate

Runtime approval gates for AI agent tool calls. Intercept payments and emails before execution

goldenmatch-duckdb

Polyglot entity-resolution + data-quality toolkit. Zero-config auto-config (negative-evidence + Path Y) hits DQbench composite 91.04 (T3 53.8% → 85.5%). Holds 0.96 DBLP-ACM, 0.94 Febrl3, 0.97 NCVR. GoldenCheck → GoldenFlow → GoldenMatch → GoldenPipe. MCP per package, multi-arch containers, Airflow DAGs, browser workbench.