human-in-the-loop

Agent workflows with full observability and time travel: watch every step live, rewind, fork, replay any run. Claude Code, Codex, Gemini, any model or harness.

Autonomous Engineering

Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.

Graph-Orchestrated Agent Loop — a production-grade framework on LangGraph. Combine workflow graphs and agent loops, transpile Dify DSL to runnable code, swap wire protocols (Dify/OpenAI).

Master the art of building and enhancing AI agents. Learn to develop flow-based applications, implement agentic search, and incorporate human-in-the-loop systems using LangGraph's powerful components.

Give your computer an AI Brain

A Sovereign Agent Governance Protocol for Deep-Water Workflows

Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.

Python-based GUI to collect Feedback of Chemist in Molecules

Autonomous AI SOC for Wazuh SIEM — 11 security-expert agents triage, correlate, investigate and plan responses 24/7, every action gated by two-tier human approval. Runs on OpenClaw, Hermes or NVIDIA NemoClaw; any LLM, self-hosted vLLM, or fully air-gapped Ollama. Evidence packs, SOC KPIs, Slack approvals.

Elixir-native LangChain, LangGraph, and DeepAgents for traceable LLM apps: OTP workflows, tools, memory, human-in-the-loop, streaming, custom clients/adapters, minimal deps, and WeaveScope tracing.

LangGraph Typescript Agents Notebooks: email, human in the loop, memory

Smart multi-agent conversational assistant with LangGraph orchestration, Human-in-the-Loop, enterprise-grade observability, and full i18n support (6 languages)

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.

An open-source, AI-driven Social Media Digital Twin powered by LLMs (Ollama, vLLM) for Computational Social Science simulations, network analysis, and human-agent interaction.

🖼️ Workshop: Build a multimodal AI agent with Haystack & GPT-4o — featuring image understanding, document retrieval, conversational memory, and human-in-the-loop safety controls

Rules you can enforce, state you can derive, context you can query: plain files in your repo, under whichever coding agent you use.

QDrant-NLP

EduMIND — Multimodal Bilingual Lecture Assistant with Anti-Forget RAG, Whisper ASR, VietMix NMT (CMI-aware), and Human-in-the-Loop Active Learning via Label Studio. Built for code-mixed Vietnamese–English academic environments.