Tag
The author is building a 'LeetCode for Agentic AI' — a practice platform with challenges for agentic frameworks like LangGraph, CrewAI, and various SDKs, so developers can learn and prepare for interviews, and is asking the community for ideas.
A practitioner shares why they stopped starting agent projects with frameworks like LangGraph or CrewAI, arguing that plain loops plus rigorous multi-run evaluation caught failures that abstractions hid, especially around side-effecting tool calls.
The post explains the difference between AI agent frameworks (libraries like ADK, LangGraph, CrewAI) and agent harnesses (pre-built agents like Claude Code, Codex, Deep Agents), and offers guidance on when to choose each as the boundaries between them blur.
A developer built a tool to compare different AI agent frameworks side-by-side, aiming to evaluate architectural differences and seeking feedback from experienced practitioners.
The article describes testing whether an AI agent using CrewAI and RAG respects user instructions when a retrieved document contains conflicting commands, as part of efforts to develop security test cases.
A discussion seeking feedback from developers on production-level issues with AI agent frameworks like LangChain and CrewAI, and predictions for future improvements.
A developer built a multi-agent Go-To-Market research assistant using Seltz, CrewAI, and Streamlit to automate cold outreach by finding trigger events and contact backgrounds before writing messages.
This is an intelligent A-share analysis system built on AKShare and CrewAI, offering professional investment analysis capabilities through multi-Agent collaboration.
The author built a governance tool for CrewAI to address coordination failures in multi-agent systems, featuring exit reports, overlap detection, and knowledge inheritance.
This paper proposes a multi-agent framework built on CrewAI for automated conversational business intelligence, using five specialized AI agents to process queries, retrieve data, and generate insights, with evaluation showing significant accuracy and quality improvements over baselines.
CrewAI has released official skills for Claude Code, Cursor, Codex, and Windsurf, automatically loading patterns for tasks like scaffolding projects and configuring agents to prevent syntax errors and outdated patterns.
TokenShield, an open-source FastAPI gateway proxy, now uses per-turn sliding window hashes to prevent agent retry loops in CrewAI, reducing token waste and cost.
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.
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.
A reproducible demo showing how adding long-term memory to CrewAI with Mem0 reduces token usage and latency via a fast/deep routing heuristic, with real measurements and a live dashboard.
Nir Diamant's genai_agents repository on GitHub, which has surpassed 22k stars, offers over 50 tutorials covering AI agent patterns from beginner to advanced, including conversational, multi-agent, RAG, and business agents built with frameworks like LangGraph, LangChain, AutoGen, CrewAI, and OpenAI Swarm.
Fact0 is a tool for tamper-evident audit trails and execution replay for AI agents, integrating with LangChain, CrewAI, and LlamaIndex. It provides cryptographic verification, execution DAG visualization, and searchable logs.
A tool for visualizing AI agent workflows is introduced, supporting multiple agent frameworks including Langgraph, CrewAI, AutoGen, Google ADK, and OpenAI Agents SDK. The creator seeks community feedback and corrections.
A community discussion asking practitioners which AI agent orchestration framework—LangGraph, CrewAI, AutoGen, or OpenAI Agents—is most production-ready and scales well in real deployments.
AgentLantern is an open-source devtool for AI agent projects that helps document, analyze, validate, and visualize agent workflows, with initial support for CrewAI and plans to extend to other frameworks.