**[[start|AgentWiki]]**

**Core Concepts**
  * [[planning|Planning]]
  * [[memory|Memory]]
  * [[tool_use|Tool Use]]
  * [[structured_outputs|Structured Outputs]]
  * [[autonomy|Autonomy]]
  * [[agent_safety|Agent Safety]]

**Reasoning**
  * [[chain_of_thought|Chain-of-Thought]]
  * [[tree_of_thoughts|Tree of Thoughts]]
  * [[graph_of_thoughts|Graph of Thoughts]]
  * [[react_framework|ReAct]]
  * [[reflexion_framework|Reflexion]]
  * [[self_consistency|Self-Consistency]]
  * [[latent_reasoning|Latent Reasoning]]
  * [[test_time_compute_scaling|Test-Time Compute]]
  * [[prompt_engineering|Prompt Engineering]]

**Memory & Retrieval**
  * [[hierarchical_memory|Hierarchical Memory]]
  * [[retrieval_augmented_generation|RAG]]
  * [[agentic_rag|Agentic RAG]]
  * [[knowledge_graphs|Knowledge Graphs]]
  * [[embeddings|Embeddings]]
  * [[faiss|FAISS]]

**Agent Types**
  * [[autonomous_agents|Autonomous]]
  * [[react_agents|ReAct Agents]]
  * [[code_generation_agents|Code Agents]]
  * [[web_browsing_agents|Web Browsing]]
  * [[vision_agents|Vision]]
  * [[voice_agents|Voice]]
  * [[generative_agents|Generative Agents]]

**Design Patterns**
  * [[agent_loop|Agent Loop]]
  * [[agent_orchestration|Orchestration]]
  * [[multi_agent_systems|Multi-Agent]]
  * [[function_calling|Function Calling]]
  * [[modular_architectures|Modular]]
  * [[durable_execution_for_agents|Durable Execution]]
  * [[agent_cost_optimization|Cost Optimization]]

**Training & Alignment**
  * [[rlhf|RLHF]]
  * [[direct_preference_optimization|DPO]]
  * [[constitutional_ai|Constitutional AI]]
  * [[process_reward_models|Process Rewards]]
  * [[fine_tuning_agents|Fine-Tuning]]
  * [[agent_distillation|Distillation]]

**Frameworks**
  * [[anthropic_context_protocol|MCP]]
  * [[a2a_protocol|A2A]]
  * [[langgraph|LangGraph]]
  * [[crewai|CrewAI]]
  * [[autogen|AutoGen]]
  * [[dspy|DSPy]]
  * [[llamaindex|LlamaIndex]]
  * [[openai_agents_sdk|OpenAI Agents SDK]]
  * [[claude_agent_sdk|Claude Agent SDK]]
  * [[openhands|OpenHands]]

**Tools**
  * [[devin|Devin]]
  * [[cursor|Cursor]]
  * [[claude_code|Claude Code]]
  * [[aider|Aider]]
  * [[computer_use|Computer Use]]

**Safety & Security**
  * [[agent_sandbox_security|Sandboxing]]
  * [[agent_threat_modeling|Threat Modeling]]
  * [[llm_hallucination|Hallucination]]

**Evaluation**
  * [[agent_evaluation|Overview]]
  * [[swe_bench|SWE-bench]]
  * [[gaia_benchmark|GAIA]]
  * [[agentbench|AgentBench]]

**[[all_pages|All Pages →]]**

**Meta**
  * [[agents:wiki_skill|Wiki API Skill]]