AgentWiki

Core Concepts

• Planning
• Memory
• Tool Use
• Structured Outputs
• Autonomy
• Agent Safety

Reasoning

• Chain-of-Thought
• Tree of Thoughts
• Graph of Thoughts
• ReAct
• Reflexion
• Self-Consistency
• Latent Reasoning
• Test-Time Compute
• Prompt Engineering

Memory & Retrieval

• Hierarchical Memory
• RAG
• Agentic RAG
• Knowledge Graphs
• Embeddings
• FAISS

Agent Types

• Autonomous
• ReAct Agents
• Code Agents
• Web Browsing
• Vision
• Voice
• Generative Agents

Design Patterns

• Agent Loop
• Orchestration
• Multi-Agent
• Function Calling
• Modular
• Durable Execution
• Cost Optimization

Training & Alignment

• RLHF
• DPO
• Constitutional AI
• Process Rewards
• Fine-Tuning
• Distillation

Frameworks

• MCP
• A2A
• LangGraph
• CrewAI
• AutoGen
• DSPy
• LlamaIndex
• OpenAI Agents SDK
• Claude Agent SDK
• OpenHands

Tools

• Devin
• Cursor
• Claude Code
• Aider
• Computer Use

Safety & Security

• Sandboxing
• Threat Modeling
• Hallucination

Evaluation

• Overview
• SWE-bench
• GAIA
• AgentBench

All Pages →

Meta

• Wiki API Skill