Agentic Patterns

Source: https://github.com/nibzard/awesome-agentic-patterns at 87538fdeccf6
License: Apache-2.0
Read the English original

This edition is an AI-assisted translation.

Awesome Agentic Patterns

精选的智能体 AI 模式目录，收录帮助自主或半自主 AI 智能体在生产环境中完成工作的真实技巧、工作流和小型架构。

为什么？ 教程展示的是玩具示例，真实产品则隐藏着复杂细节。本列表汇集可重复使用的模式，弥合两者之间的差距，帮助大家交付更智能、更快速的智能体。

---

什么算作一种模式？

• 可重复——不止一个团队正在使用。
• 以智能体为中心——改善 AI 智能体的感知、推理或行动方式。
• 可追溯——有公开资料作为依据：博客文章、演讲、代码库或论文。

如果你的链接符合这些条件，就适合收录在这里。

---

🌐 探索网站

访问： https://agentic-patterns.com

该网站还提供 README 之外的强大探索工具：

• Pattern Explorer：按类别、状态、复杂度等浏览、筛选和搜索所有模式
• Compare Tool：并排比较多个模式的共同属性
• Decision Explorer：交互式指南，帮助你为用例找到合适的模式
• Graph Visualization：以图形方式展示模式之间的关系和连接
• Pattern Packs：为常见智能体架构精选的模式集合
• Developer Guides：深入介绍模式选择与使用的文档
• Dark Mode：完整主题支持，在任何环境下都能舒适阅读

使用 Astro 构建，部署在 Vercel，源代码位于 apps/web/。

---

类别速览

类别	内容
上下文与记忆	滑动窗口筛选、向量缓存、情景记忆
反馈循环	编译器、CI、人工审查、自愈重试
学习与适应	Agent RFT、技能库、基于方差的 RL
编排与控制	任务分解、生成子智能体、工具路由
可靠性与评估	护栏、评估框架、日志记录、可复现性
安全与防护	隔离虚拟机、PII 令牌化、安全扫描
工具使用与环境	Shell、浏览器、数据库、Playwright、沙箱技巧
用户体验与协作	提示移交、暂存提交、异步后台智能体

类别并非一成不变——如果你发现更合适的划分，欢迎提交 PR！ 下方表格由 patterns/ 文件夹自动生成。

---

上下文与记忆

• Agent-Powered Codebase Q&A / Onboarding
• Context Budget as a Governed Resource
• Context Window Anxiety Management
• Context Window Auto-Compaction
• Context-Minimization Pattern
• Cross-Agent Lesson Sharing via Git
• Curated Code Context Window
• Curated File Context Window
• Dynamic Context Injection
• Episodic Memory Retrieval & Injection
• Filesystem-Based Agent State
• Layered Configuration Context
• Memory Synthesis from Execution Logs
• Proactive Agent State Externalization
• Progressive Disclosure for Large Files
• Prompt Caching via Exact Prefix Preservation
• Schema-Guided Graph Retrieval for Multi-Hop Reasoning
• Self-Identity Accumulation
• Semantic Context Filtering Pattern
• Session-Scoped Context Runtime for Agent Tools
• Tool Search Lazy Loading
• Working Memory via TodoWrite

反馈循环

• AI-Assisted Code Review / Verification
• Background Agent with CI Feedback
• Coding Agent CI Feedback Loop
• Deterministic Grader in the Loop
• Dogfooding with Rapid Iteration for Agent Improvement
• Graph of Thoughts (GoT)
• Incident-to-Eval Synthesis
• Inference-Healed Code Review Reward
• Iterative Prompt & Skill Refinement
• Reflection Loop
• Rendered UI Finish Gate
• Rich Feedback Loops > Perfect Prompts
• Self-Critique Evaluator Loop
• Self-Discover: LLM Self-Composed Reasoning Structures
• Spec-As-Test Feedback Loop
• Tool Use Incentivization via Reward Shaping

学习与适应

• Agent Reinforcement Fine-Tuning (Agent RFT)
• Commitment Ledger with Reality-Gated Credit
• Compounding Engineering Pattern
• Frontier-Focused Development
• Memory Reinforcement Learning (MemRL)
• Persistent Test Memory Feedback Loop
• Shipping as Research
• Skill Library Evolution
• Variance-Based RL Sample Selection

编排与控制

• 402-First Machine Payments (Price-Before-Work Tool Purchases)
• Action-Selector Pattern
• Agent Modes by Model Personality
• Agent-Driven Research
• Artifact-Driven Analysis Pipeline Orchestration
• Autonomous Workflow Agent Architecture
• Board-Mediated Async Inter-Agent Coordination
• Budget-Aware Model Routing with Hard Cost Caps
• Burn the Boats
• Capability-Escrow-Receipt
• Classify-Then-Act for Background Agents
• Conditional Parallel Tool Execution
• Continuous Autonomous Task Loop Pattern
• Cross-Cycle Consensus Relay
• Cross-Domain Agent Conflict Resolution
• Custom Sandboxed Background Agent
• Declarative Multi-Agent Topology Definition
• Design-Time File Partition as Concurrency Control
• Deterministic Zero-LLM Orchestration
• Discrete Phase Separation
• Disposable Scaffolding Over Durable Features
• Distributed Execution with Cloud Workers
• Dual LLM Pattern
• Dual-Rail Message Delivery
• Economic Value Signaling in Multi-Agent Networks
• Explicit Posterior-Sampling Planner
• Factory over Assistant
• Feature List as Immutable Contract
• Hybrid LLM/Code Workflow Coordinator
• Inference-Time Scaling
• Initializer-Maintainer Dual Agent Architecture
• Inversion of Control
• Iterative Multi-Agent Brainstorming
• Lane-Based Execution Queueing
• Language Agent Tree Search (LATS)
• LLM Map-Reduce Pattern
• Markdown Polis — Multi-Vendor Agent Coordination via Filesystem Constitution
• Multi-Model Orchestration for Complex Edits
• Non-Generative Judgment Routing with Typed Escalation
• Opponent Processor / Multi-Agent Debate Pattern
• Oracle and Worker Multi-Model Approach
• Parallel Tool Call Learning
• Plan-Then-Execute Pattern
• Planner-Worker Separation for Long-Running Agents
• Progressive Autonomy with Model Evolution
• Progressive Complexity Escalation
• Recursive Best-of-N Delegation
• Self-Rewriting Meta-Prompt Loop
• Signal-Driven Agent Activation
• Specification-Driven Agent Development
• Stop Hook Auto-Continue Pattern
• Sub-Agent Spawning
• Subject Hygiene for Task Delegation
• Swarm Migration Pattern
• Three-Stage Perception Architecture
• Tool Capability Compartmentalization
• Tool Selection Guide
• Tracker-as-Desired-State Reconciliation
• Tree-of-Thought Reasoning
• Workspace-Native Multi-Agent Orchestration

可靠性与评估

• Action Caching & Replay Pattern
• Adaptive Sandbox Fan-Out Controller
• Agent Circuit Breaker
• Anti-Reward-Hacking Grader Design
• Asynchronous Coding Agent Pipeline
• Canary Rollout and Automatic Rollback for Agent Policy Changes
• CriticGPT-Style Code Review
• Dead-Man’s Switch for Scheduled Agent Jobs
• Evidence-Layered Evaluation for Interactive Agents
• Extended Coherence Work Sessions
• Failover-Aware Model Fallback
• Lethal Trifecta Threat Model
• LLM Observability
• Merged Code + Language Skill Model
• No-Token-Limit Magic
• Orchestration Prompt-Writing Benchmark
• Out-of-Process Provider-Boundary Replay
• Output Verification Loop
• Own-Check Fault Injection
• Reasoning-Token Firewall
• Reliability Problem Map Checklist for RAG and Agents
• RLAIF (Reinforcement Learning from AI Feedback)
• Schema Validation Retry with Cross-Step Learning
• Skill Activation as a Precision/Recall Measurement
• Structured Output Specification
• Subagent Compilation Checker
• Tier Auto-Apply by Mechanical Impact
• Versioned Constitution Governance
• Workflow Evals with Mocked Tools

安全与防护

• Authenticated Authority Channel
• Black-Box Skill Invocation
• Consequence-Family Coverage Audit
• Cryptographic Governance Audit Trail
• Denial Tracking & Permission Escalation
• Deterministic Security Scanning Build Loop
• Deterministic Threat Rule Scanning
• Evidence Questions, Not Verdict Questions
• Exact-Action Authorization Binding
• External Credential Sync
• Hook-Based Safety Guard Rails for Autonomous Code Agents
• Isolated VM per RL Rollout
• Local-First Credential Broker
• Non-Custodial Spending Controls
• One OS User per Agent
• PII Tokenization
• Policy-Gated Tool Proxy
• Sandboxed Tool Authorization
• Soulbound Identity Verification
• Transitive Vouch-Chain Trust
• Zero-Knowledge Verified Agent Egress
• Zero-Trust Agent Mesh

工具使用与环境

• Agent SDK for Programmatic Control
• Agent-First Tool Discovery
• Agent-First Tooling and Logging
• Agentic Search Over Vector Embeddings
• AI Web Search Agent Loop
• CLI-First Skill Design
• CLI-Native Agent Orchestration
• Code Mode MCP Tool Interface Improvement Pattern
• Code-Over-API Pattern
• Code-Then-Execute Pattern
• Cross-Protocol Agent Discovery
• Dual-Use Tool Design
• Dynamic Code Injection (On-Demand File Fetch)
• Egress Lockdown (No-Exfiltration Channel)
• Filesystem-Mediated Host Delegation
• Intelligent Bash Tool Execution
• LLM-Friendly API Design
• MCP Pattern Injection
• Multi-Platform Communication Aggregation
• Multi-Platform Webhook Triggers
• Patch Steering via Prompted Tool Selection
• Precomputed Code Graph Lookup
• Progressive Tool Discovery
• Shell Command Contextualization
• Static Service Manifest for Agents
• Tool Use Steering via Prompting
• Unified Tool Gateway
• Virtual Machine Operator Agent
• Visual AI Multimodal Integration

用户体验与协作

• Abstracted Code Representation for Review
• Agent-Assisted Scaffolding
• Agent-Friendly Workflow Design
• AI-Accelerated Learning and Skill Development
• Chain-of-Thought Monitoring & Interruption
• Codebase Optimization for Agents
• Democratization of Tooling via Agents
• Dev Tooling Assumptions Reset
• Human-in-the-Loop Approval Framework
• Latent Demand Product Discovery
• Milestone Escrow for Agent Resource Funding
• Proactive Trigger Vocabulary
• Seamless Background-to-Foreground Handoff
• Spectrum of Control / Blended Initiative
• Team-Shared Agent Configuration as Code
• Verbose Reasoning Transparency

---

面向 AI 助手（llms.txt）

本项目包含 llms.txt，这是一个机器可读的文档文件，旨在帮助 AI 助手和 LLM 理解并推荐合适的模式。

包含内容：

• 模式类别及其用途
• 附有简明说明的关键模式
• 面向 AI 助手的使用指南
• 根据用例需求选择模式的策略

面向构建 AI 助手的开发者： 可将 llms.txt 文件作为上下文提供给 LLM，以改进模式推荐。该文件针对以下场景进行了优化：

• 为本目录建立索引的 RAG 系统
• 推荐模式的 AI 编程助手
• 推荐智能体模式的 LLM 工具

访问： https://agentic-patterns.com/llms.txt （也可在 apps/web/public/llms.txt 中查看）

---

三步参与贡献

1. Fork 并创建分支 → git checkout -b add-my-pattern
2. 使用上方模板在 patterns/ 下添加模式文件。
3. 运行 bun run build:data，刷新 README 自动生成的章节和站点数据。
4. 提交 PR，标题为 Add: my-pattern-name。
5. 本仓库以模式为核心：即使提案在技术上有效，如果主要是产品公告或推广，也会被拒绝。

详细要求请参阅 CONTRIBUTING.md。

---

灵感来源

本项目始于文章 “Sourcegraph 在构建 AI 编程智能体时的经验”（2025 年 5 月 28 日）以及持续更新的 Raising an Agent 视频日志。许多早期模式直接源自这些经验——感谢所有公开分享历程的人！

---

许可证

Apache‑2.0。请参阅 LICENSE。

---

Star 历史