Swarm intelligence enables many simple agents to solve complex problems through emergent collective behavior. Inspiration: Ant colonies, bird flocks, bee hives - simple rules per agent create sophisticated group behavior. Mechanisms: Local interactions only (no central control), stigmergy (indirect communication through environment), positive/negative feedback loops, self-organization. Algorithms: Ant Colony Optimization (ACO) for routing/scheduling, Particle Swarm Optimization (PSO) for continuous optimization, Artificial Bee Colony for search. AI agent applications: Multiple simple agents exploring solution space, voting/consensus from small individual contributions, robustness through redundancy, graceful degradation. Implementation patterns: Decentralized decision-making, shared environment state (blackboard), pheromone-like signals for coordination, population-based exploration. Advantages: Scalability, fault tolerance, adaptability, no single point of failure. Challenges: Emergent behavior hard to predict/debug, convergence guarantees difficult, communication overhead. Modern use: Drone swarms, distributed computing, collaborative filtering, autonomous vehicle coordination. Combines simplicity at individual level with complexity at system level.