langgraph

GraphARC is an open-source governed agent runtime that uses a deterministic checker to admit or refuse proposed agent graph actions before execution, providing audit trails and cost tracking. It demonstrates how to steer agents away from forbidden actions using structured refusals.

GraphARC is an open-source MIT tool that uses a local 8B model (qwen3:8b) to plan and execute multi-node investigation graphs for root-cause analysis, with a deterministic admission gate enforcing policy and budget checks. It provides live browser views, append-only JSONL audit trails, and supports Ollama, OpenRouter, OpenAI, or Claude via CLI.

A tutorial on building agentic workflows in Python using LangGraph, covering state, nodes, edges, tool integration, and conversation memory.

Graph engineering is a new term for coordinating multiple AI agent loops using graphs of nodes (work units) and edges (control flow). The article explains the concept, its historical context (LangGraph, AutoGen, etc.), and the real challenges of designing such graphs.

An educational article exploring LangGraph, covering agent architectures, the blackboard pattern, and common bottlenecks in building agent systems.

An open-source full-stack research agent example using Gemini, LangGraph, React, and Google Search, demonstrating an end-to-end workflow with dynamic query generation, reflection loops, and cited answers.

OxDeAI is an open-source protocol for deterministic pre-execution authorization of AI agent actions, providing signed artifacts and guards to enforce policy outside the agent loop. It supports popular agent frameworks like LangGraph, CrewAI, and AutoGen, and is seeking critical feedback.

The developer created a self-hosted visual builder for LangChain/LangGraph agents and is requesting feedback from the community.

token-budget-contracts is a library for governing token spend across multi-agent systems. Version 0.3.0 adds native adapters for LangGraph and CrewAI, plus OpenTelemetry integration for monitoring budget activity.

Toyota's enterprise AI team shared the ToyotaGPT platform at the Interrupt conference. Based on LangGraph and LangSmith, it reduced AI agent delivery from 6 months to 4 days, and has over 50 agents running in production, saving millions of dollars.

A 7-week course with 7.7k stars on GitHub, building a production-grade RAG system from scratch, covering Docker, FastAPI, hybrid search, LangGraph agentic RAG, and a Telegram bot, with hands-on coding throughout.

Rippling shared how they built Rippling AI, a natural language assistant for HR and payroll, using a flat LangGraph agent, generic tools, SQL-based data retrieval, and eval-driven development.

An AI engineer released an open-source project teaching how to build a local RAG system from scratch and a production-grade agentic architecture with LangGraph, hybrid retrieval, caching, and observability.

LangChain demonstrates an agent that drafts a cited VC investment memo in ~90 seconds for $0.40 using the Perplexity Agent API and LangGraph, with four parallel research nodes and a synthesizer.

Argues that using LangGraph-style orchestration for procedural agent tasks is less effective than simply embedding the full procedure in the system prompt.

The author shares practical lessons learned from deploying multi-agent orchestration frameworks (LangGraph, CrewAI, and A2A) in production, contrasting with simple notebook experiments.

LangChain shares a customer story where PodiumHQ's Walker Ward discusses using LangGraph and LangSmith to move AI agents from prototype to production.

Discussion on which metrics to prioritize when benchmarking AI agent frameworks, specifically comparing ADK and LangGraph.

A developer reimplements Arbor, a multi-agent research system from a paper, on LangGraph, sharing lessons about graph structure enforcing invariants and backpropagating insights from failures. The reimplementation, arbor-lg, uses LangGraph's StateGraph and SQLite checkpointer for durability.

A detailed comparison of 11 LLMs on refactoring a LangGraph god node, including proposals, evaluations, and analysis of which models perform best as generators and evaluators.