Core open-source frameworks for building AI agents — discover and compare LangChain, CrewAI, AutoGen, LangGraph and more. Filter by tool-calling, memory, multi-step reasoning, stars, and license to pick the right foundation for your project.
Agent harness operating system providing skills, instincts, memory optimization, continuous learning, and security scanning.
An autonomous AI agent framework from NousResearch that supports multiple LLM backends and grows with user needs.
AutoGPT is an autonomous AI agent that can complete user-defined tasks end-to-end. It plans and executes steps on its own and is considered a milestone in agent autonomy.
Langflow is a visual AI agent and workflow builder platform with drag-and-drop design, multi-LLM integration, and tool composition to simplify agent development.
Dify is an open-source LLM application development platform with a visual agent orchestration interface, supporting workflows, knowledge bases, and multiple models.
LangChain is the open-source agent engineering platform that unifies model IO, tool calling, RAG, memory and observability under one composable framework.
AI research automation agent by Andrej Karpathy that automatically runs nanochat training research experiments on a single GPU.
Pi Mono is a comprehensive AI agent toolkit including a coding agent CLI, unified LLM API, TUI and web UI libraries, Slack bot, and vLLM pod management for end-to-end agent development.
OpenHands is an open-source AI software engineering agent platform that can automatically execute development tasks, modify code, and support collaborative iteration.
worldmonitor is an AI global event monitoring dashboard aggregating news, geopolitics, energy and market data with auto-generated briefings.
paperclip is an AI agent team orchestration and scheduling platform, managing task assignment, collaboration and state across many agents.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs. Supports LoRA, QLoRA, RLHF and more for building custom agent models.
12 Lessons to Get Started Building AI Agents by Microsoft. Hands-on curriculum covering core agent concepts, tool use, and multi-agent collaboration.
The Multi-Agent Framework for building the first AI Software Company, enabling natural language programming with multi-role collaboration for automated requirement analysis, design, coding, and testing.
Open Interpreter lets LLMs execute code and control a computer locally, turning natural language into shell, Python, and browser actions on the user machine.
The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code/Codex integration.
An open-source agent harness platform providing the best agent toolkit, supporting multiple AI coding agents.
ai-hedge-fund is a multi-agent simulated hedge fund example, with researcher, trader, risk-manager agents collaborating on investment decisions.
Meta's open-source Llama 2 foundational LLM with pretrained and fine-tuned models from 7B to 70B parameters, supporting chat and text completion as a cornerstone of the open LLM ecosystem.
OpenManus is an open-source AI Agent framework from the MetaGPT team, delivering Manus-like autonomous task execution without any invite code. Supports MCP tool calls and multi-agent flow.
CrewAI is a multi-agent framework for orchestrating role-playing, autonomous AI agents that collaborate like a team to tackle complex tasks.
LlamaIndex is a data framework for building LLM applications. It provides data connectors, indexing, query engines, and agent workflow orchestration — a core tool in the RAG ecosystem.
Build agents that monitor and act on your behalf. Create automated agents for Twitter, weather monitoring, web scraping, and many other scenarios.
CLI-Anything aims to make all software agent-native by transforming applications into unified CLI interfaces, enabling AI agents to naturally interact with and operate any software through a centralized CLI Hub.
(24 / 257)
How do you know a prompt change is better, not worse? A systematic guide to canary deployment, quality gates, auto-rollback architecture, and continuous behavioral drift monitoring for agents in production.
Most teams evaluate agents by checking a few examples. Real evaluation needs layered metrics, non-rotting datasets, and judges that push back. This article provides runnable code patterns and a practical decision framework.
A systematic comparison of the three categories of agent memory -- working, long-term, and shared -- covering storage media, lifecycle, retrieval methods, typical frameworks, and design patterns, fully addressing agent personalization and multi-agent collaboration engineering.
Systematic guide to rate limiting and cost attack defense for LLM Agents in production: single-user token quotas, multi-tenant sliding windows, prompt injection amplifying cost, DDoS protection, and integration with LangChain/CrewAI/AutoGen frameworks.
Exploring how small language models are fine-tuned and deployed for agent workloads at the edge, balancing latency, cost, and accuracy for production AI agents.
A systematic guide to seven tool-call fault tolerance patterns: timeout hierarchy, exponential backoff with jitter, circuit breakers, fallback provider chains, recoverable error classification, structured validation, and idempotency keys -- keeping agents stable in unstable real-world environments.