Skip to content
Back to search

awesome-agentic-patterns

A curated catalogue of awesome agentic AI patterns

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/nibzard/awesome-agentic-patterns with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/nibzard/awesome-agentic-patterns'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/nibzard--awesome-agentic-patterns/badge.svg)](/listings/nibzard--awesome-agentic-patterns)

HTML

<a href="/listings/nibzard--awesome-agentic-patterns"><img src="/api/listings/nibzard--awesome-agentic-patterns/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 347 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Awesome Agentic Patterns
  2. ![Awesome Agentic Patterns](/agentic-patterns.jpeg)
  3. A curated catalogue of **agentic AI patterns** — real‑world tricks, workflows, and mini‑architectures that help autonomous or semi‑autonomous AI agents get useful work done in production.
  4. > **Why?**
  5. > Tutorials show toy demos. Real products hide the messy bits. This list surfaces the repeatable patterns that bridge the gap so we can all ship smarter, faster agents.
  6. ---
  7. ## What counts as a pattern?
  8. * **Repeatable** – more than one team is using it.
  9. * **Agent‑centric** – improves how an AI agent senses, reasons, or acts.
  10. * **Traceable** – backed by a public reference: blog post, talk, repo, or paper.
  11. If your link ticks those boxes, it belongs here.
  12. ---
  13. ## 🌐 Explore the Website
  14. **Visit:** [https://agentic-patterns.com](https://agentic-patterns.com)
  15. The website offers powerful discovery tools beyond this README:
  16. - **Pattern Explorer**: Browse, filter, and search all patterns by category, status, complexity, and more
  17. - **Compare Tool**: Side-by-side comparison of multiple patterns with shared attributes
  18. - **Decision Explorer**: Interactive guide to find the right pattern for your use case
  19. - **Graph Visualization**: Visual map of pattern relationships and connections
  20. - **Pattern Packs**: Curated collections of patterns for common agent architectures
  21. - **Developer Guides**: In-depth documentation on pattern selection and usage
  22. - **Dark Mode**: Full theme support for comfortable reading in any environment
  23. Built with [Astro](https://astro.build), deployed on [Vercel](https://vercel.com), source code in [`apps/web/`](./apps/web/).
  24. ---
  25. ## Quick Tour of Categories
  26. <!-- AUTO-GENERATED TOC START -->
  27. | Category | What you'll find |
  28. | ------------------------------------------------------ | --------------------------------------------------------- |
  29. | [**Context & Memory**](#context-memory) | Sliding-window curation, vector cache, episodic memory |
  30. | [**Feedback Loops**](#feedback-loops) | Compilers, CI, human review, self-healing retries |
  31. | [**Learning & Adaptation**](#learning-adaptation) | Agent RFT, skill libraries, variance-based RL |
  32. | [**Orchestration & Control**](#orchestration-control) | Task decomposition, sub-agent spawning, tool routing |
  33. | [**Reliability & Eval**](#reliability-eval) | Guardrails, eval harnesses, logging, reproducibility |
  34. | [**Security & Safety**](#security-safety) | Isolated VMs, PII tokenization, security scanning |
  35. | [**Tool Use & Environment**](#tool-use-environment) | Shell, browser, DB, Playwright, sandbox tricks |
  36. | [**UX & Collaboration**](#ux-collaboration) | Prompt hand-offs, staged commits, async background agents |
  37. <!-- AUTO-GENERATED TOC END -->
  38. *Categories are fluid — open a PR if you see a better slice!*
  39. The tables below are auto‑generated from the `patterns/` folder.
  40. ---
  41. <!-- …existing content above… -->
  42. <!-- AUTO-GENERATED PATTERNS START -->
  43. ### <a name="context-memory"></a>Context & Memory
  44. - [Agent-Powered Codebase Q&A / Onboarding](patterns/agent-powered-codebase-qa-onboarding.md)
  45. - [Context Budget as a Governed Resource](patterns/context-budget-as-a-governed-resource.md)
  46. - [Context Window Anxiety Management](patterns/context-window-anxiety-management.md)
  47. - [Context Window Auto-Compaction](patterns/context-window-auto-compaction.md)
  48. - [Context-Minimization Pattern](patterns/context-minimization-pattern.md)
  49. - [Cross-Agent Lesson Sharing via Git](patterns/cross-agent-lesson-sharing.md)
  50. - [Curated Code Context Window](patterns/curated-code-context-window.md)
  51. - [Dynamic Context Injection](patterns/dynamic-context-injection.md)
  52. - [Episodic Memory Retrieval & Injection](patterns/episodic-memory-retrieval-injection.md)
  53. - [Filesystem-Based Agent State](patterns/filesystem-based-agent-state.md)
  54. - [Layered Configuration Context](patterns/layered-configuration-context.md)
  55. - [Memory Synthesis from Execution Logs](patterns/memory-synthesis-from-execution-logs.md)
  56. - [Proactive Agent State Externalization](patterns/proactive-agent-state-externalization.md)
  57. - [Progressive Disclosure for Large Files](patterns/progressive-disclosure-large-files.md)
  58. - [Prompt Caching via Exact Prefix Preservation](patterns/prompt-caching-via-exact-prefix-preservation.md)
  59. - [Schema-Guided Graph Retrieval for Multi-Hop Reasoning](patterns/schema-guided-graph-retrieval.md)
  60. - [Self-Identity Accumulation](patterns/self-identity-accumulation.md)
  61. - [Semantic Context Filtering Pattern](patterns/semantic-context-filtering.md)
  62. - [Session-Scoped Context Runtime for Agent Tools](patterns/session-scoped-context-runtime-for-agent-tools.md)
  63. - [Surface-Scoped System Prompt](patterns/surface-scoped-system-prompt.md)
  64. - [Tool Search Lazy Loading](patterns/tool-search-lazy-loading.md)
  65. - [Working Memory via Task Tracking](patterns/working-memory-via-todos.md)
  66. ### <a name="feedback-loops"></a>Feedback Loops
  67. - [AI-Assisted Code Review / Verification](patterns/ai-assisted-code-review-verification.md)
  68. - [Background Agent with CI Feedback](patterns/background-agent-ci.md)
  69. - [Deterministic Grader in the Loop](patterns/deterministic-grader-in-the-loop.md)
  70. - [Dogfooding with Rapid Iteration for Agent Improvement](patterns/dogfooding-with-rapid-iteration-for-agent-improvement.md)
  71. - [Graph of Thoughts (GoT)](patterns/graph-of-thoughts.md)
  72. - [Incident-to-Eval Synthesis](patterns/incident-to-eval-synthesis.md)
  73. - [Inference-Healed Code Review Reward](patterns/inference-healed-code-review-reward.md)
  74. - [Iterative Prompt & Skill Refinement](patterns/iterative-prompt-skill-refinement.md)
  75. - [Reflection Loop](patterns/reflection.md)
  76. - [Rendered UI Finish Gate](patterns/rendered-ui-finish-gate.md)
  77. - [Rich Feedback Loops > Perfect Prompts](patterns/rich-feedback-loops.md)
  78. - [Self-Critique Evaluator Loop](patterns/self-critique-evaluator-loop.md)
  79. - [Spec-As-Test Feedback Loop](patterns/spec-as-test-feedback-loop.md)
  80. - [Tool Use Incentivization via Reward Shaping](patterns/tool-use-incentivization-via-reward-shaping.md)
  81. ### <a name="learning-adaptation"></a>Learning & Adaptation
  82. - [Agent Reinforcement Fine-Tuning (Agent RFT)](patterns/agent-reinforcement-fine-tuning.md)
  83. - [Commitment Ledger with Reality-Gated Credit](patterns/commitment-ledger-reality-gated-credit.md)
  84. - [Compounding Engineering Pattern](patterns/compounding-engineering-pattern.md)
  85. - [Frontier-Focused Development](patterns/frontier-focused-development.md)
  86. - [Memory Reinforcement Learning (MemRL)](patterns/memory-reinforcement-learning-memrl.md)
  87. - [Merged Code + Language Skill Model](patterns/merged-code-language-skill-model.md)
  88. - [Persistent Test Memory Feedback Loop](patterns/persistent-test-memory-feedback-loop.md)
  89. - [Self-Discover: LLM Self-Composed Reasoning Structures](patterns/self-discover-reasoning-structures.md)
  90. - [Shipping as Research](patterns/shipping-as-research.md)
  91. - [Skill Library Evolution](patterns/skill-library-evolution.md)
  92. - [Variance-Based RL Sample Selection](patterns/variance-based-rl-sample-selection.md)
  93. ### <a name="orchestration-control"></a>Orchestration & Control
  94. - [402-First Machine Payments (Price-Before-Work Tool Purchases)](patterns/402-first-machine-payments.md)
  95. - [Action-Selector Pattern](patterns/action-selector-pattern.md)
  96. - [Agent Modes by Model Personality](patterns/agent-modes-by-model-personality.md)
  97. - [Agent-Driven Research](patterns/agent-driven-research.md)
  98. - [Artifact-Driven Analysis Pipeline Orchestration](patterns/multi-step-analysis-pipeline-orchestration.md)
  99. - [Autonomous Workflow Agent Architecture](patterns/autonomous-workflow-agent-architecture.md)
  100. - [Board-Mediated Async Inter-Agent Coordination](patterns/board-mediated-inter-agent-coordination.md)
  101. - [Budget-Aware Model Routing with Hard Cost Caps](patterns/budget-aware-model-routing-with-hard-cost-caps.md)
  102. - [Burn the Boats](patterns/burn-the-boats.md)
  103. - [Capability-Escrow-Receipt](patterns/capability-escrow-receipt.md)
  104. - [Classify-Then-Act for Background Agents](patterns/classify-then-act-for-background-agents.md)
  105. - [Conditional Parallel Tool Execution](patterns/parallel-tool-execution.md)
  106. - [Continuous Autonomous Task Loop Pattern](patterns/continuous-autonomous-task-loop-pattern.md)
  107. - [Cross-Cycle Consensus Relay](patterns/cross-cycle-consensus-relay.md)
  108. - [Cross-Domain Agent Conflict Resolution](patterns/cross-domain-agent-conflict-resolution.md)
  109. - [Custom Sandboxed Background Agent](patterns/custom-sandboxed-background-agent.md)
  110. - [Declarative Multi-Agent Topology Definition](patterns/declarative-multi-agent-topology-definition.md)
  111. - [Design-Time File Partition as Concurrency Control](patterns/design-time-file-partition.md)
  112. - [Deterministic Zero-LLM Orchestration](patterns/deterministic-zero-llm-orchestration.md)
  113. - [Discrete Phase Separation](patterns/discrete-phase-separation.md)
  114. - [Disposable Scaffolding Over Durable Features](patterns/disposable-scaffolding-over-durable-features.md)
  115. - [Distributed Execution with Cloud Workers](patterns/distributed-execution-cloud-workers.md)
  116. - [Dual LLM Pattern](patterns/dual-llm-pattern.md)
  117. - [Dual-Rail Message Delivery](patterns/dual-rail-message-delivery.md)
  118. - [Explicit Posterior-Sampling Planner](patterns/explicit-posterior-sampling-planner.md)
  119. - [Factory over Assistant](patterns/factory-over-assistant.md)
  120. - [Fair-Share Task Queues with Heartbeat Leases](patterns/fair-share-task-queues-with-heartbeat-leases.md)
  121. - [Feature List as Immutable Contract](patterns/feature-list-as-immutable-contract.md)
  122. - [Hybrid LLM/Code Workflow Coordinator](patterns/hybrid-llm-code-workflow-coordinator.md)
  123. - [Inference-Time Scaling](patterns/inference-time-scaling.md)
  124. - [Initializer-Maintainer Dual Agent Architecture](patterns/initializer-maintainer-dual-agent.md)
  125. - [Inversion of Control](patterns/inversion-of-control.md)
  126. - [Iterative Multi-Agent Brainstorming](patterns/iterative-multi-agent-brainstorming.md)
  127. - [Judge-Gated Finding Exchange Between Parallel Sub-Agents](patterns/judge-gated-finding-exchange-between-sub-agents.md)
  128. - [Lane-Based Execution Queueing](patterns/lane-based-execution-queueing.md)
  129. - [Language Agent Tree Search (LATS)](patterns/language-agent-tree-search-lats.md)
  130. - [LLM Map-Reduce Pattern](patterns/llm-map-reduce-pattern.md)
  131. - [Markdown Polis — Multi-Vendor Agent Coordination via Filesystem Constitution](patterns/markdown-polis-coordination.md)
  132. - [Multi-Model Orchestration for Complex Edits](patterns/multi-model-orchestration-for-complex-edits.md)
  133. - [Non-Generative Judgment Routing with Typed Escalation](patterns/non-generative-judgment-routing.md)
  134. - [Opponent Processor / Multi-Agent Debate Pattern](patterns/opponent-processor-multi-agent-debate.md)
  135. - [Oracle and Worker Multi-Model Approach](patterns/oracle-and-worker-multi-model.md)
  136. - [Parallel Tool Call Learning](patterns/parallel-tool-call-learning.md)
  137. - [Plan-Then-Execute Pattern](patterns/plan-then-execute-pattern.md)
  138. - [Planner-Worker Separation for Long-Running Agents](patterns/planner-worker-separation-for-long-running-agents.md)
  139. - [Progressive Autonomy with Model Evolution](patterns/progressive-autonomy-with-model-evolution.md)
  140. - [Progressive Complexity Escalation](patterns/progressive-complexity-escalation.md)
  141. - [Recursive Best-of-N Delegation](patterns/recursive-best-of-n-delegation.md)
  142. - [Self-Rewriting Meta-Prompt Loop](patterns/self-rewriting-meta-prompt-loop.md)
  143. - [Shared Core with Native Shells](patterns/shared-core-native-shells.md)
  144. - [Signal-Driven Agent Activation](patterns/signal-driven-agent-activation.md)
  145. - [Specification-Driven Agent Development](patterns/specification-driven-agent-development.md)
  146. - [Stop Hook Auto-Continue Pattern](patterns/stop-hook-auto-continue-pattern.md)
  147. - [Sub-Agent Spawning](patterns/sub-agent-spawning.md)
  148. - [Subject Hygiene for Task Delegation](patterns/subject-hygiene.md)
  149. - [Swarm Migration Pattern](patterns/swarm-migration-pattern.md)
  150. - [Three-Stage Perception Architecture](patterns/three-stage-perception-architecture.md)
  151. - [Tool Capability Compartmentalization](patterns/tool-capability-compartmentalization.md)
  152. - [Tool Selection Guide](patterns/tool-selection-guide.md)
  153. - [Tracker-as-Desired-State Reconciliation](patterns/tracker-as-desired-state-reconciliation.md)
  154. - [Tree-of-Thought Reasoning](patterns/tree-of-thought-reasoning.md)
  155. - [Workspace-Native Multi-Agent Orchestration](patterns/workspace-native-multi-agent-orchestration.md)
  156. ### <a name="reliability-eval"></a>Reliability & Eval
  157. - [Action Caching & Replay Pattern](patterns/action-caching-replay.md)
  158. - [Adaptive Sandbox Fan-Out Controller](patterns/adaptive-sandbox-fanout-controller.md)
  159. - [Agent Circuit Breaker](patterns/agent-circuit-breaker.md)
  160. - [Anti-Reward-Hacking Grader Design](patterns/anti-reward-hacking-grader-design.md)
  161. - [Approval-Bound Transactional Write](patterns/approval-bound-transactional-write.md)
  162. - [Asynchronous Coding Agent Pipeline](patterns/asynchronous-coding-agent-pipeline.md)
  163. - [Canary Rollout and Automatic Rollback for Agent Policy Changes](patterns/canary-rollout-and-automatic-rollback-for-agent-policy-changes.md)
  164. - [CriticGPT-Style Code Review](patterns/criticgpt-style-evaluation.md)
  165. - [Dead-Man's Switch for Scheduled Agent Jobs](patterns/dead-mans-switch-for-scheduled-agent-jobs.md)
  166. - [Evidence-Layered Evaluation for Interactive Agents](patterns/evidence-layered-evaluation-for-interactive-agents.md)
  167. - [Extended Coherence Work Sessions](patterns/extended-coherence-work-sessions.md)
  168. - [Failover-Aware Model Fallback](patterns/failover-aware-model-fallback.md)
  169. - [Fleet Cost Simulation Before Dispatch](patterns/fleet-cost-simulation-before-dispatch.md)
  170. - [Intent-Level Cost Attribution](patterns/intent-level-cost-attribution.md)
  171. - [LLM Observability](patterns/llm-observability.md)
  172. - [No-Token-Limit Magic](patterns/no-token-limit-magic.md)
  173. - [Orchestration Prompt-Writing Benchmark](patterns/orchestration-prompt-writing-benchmark.md)
  174. - [Out-of-Process Provider-Boundary Replay](patterns/out-of-process-provider-boundary-replay.md)
  175. - [Output Verification Loop](patterns/output-verification-loop.md)
  176. - [Own-Check Fault Injection](patterns/own-check-fault-injection.md)
  177. - [Reasoning-Token Firewall](patterns/reasoning-token-firewall.md)
  178. - [Reliability Problem Map Checklist for RAG and Agents](patterns/wfgy-reliability-problem-map.md)
  179. - [RLAIF (Reinforcement Learning from AI Feedback)](patterns/rlaif-reinforcement-learning-from-ai-feedback.md)
  180. - [Schema Validation Retry with Cross-Step Learning](patterns/schema-validation-retry-cross-step-learning.md)
  181. - [Skill Activation as a Precision/Recall Measurement](patterns/skill-activation-as-precision-recall.md)
  182. - [Structured Output Specification](patterns/structured-output-specification.md)
  183. - [Subagent Compilation Checker](patterns/subagent-compilation-checker.md)
  184. - [Tier Auto-Apply by Mechanical Impact](patterns/tier-auto-apply-by-mechanical-impact.md)
  185. - [Versioned Constitution Governance](patterns/versioned-constitution-governance.md)
  186. - [Workflow Evals with Mocked Tools](patterns/workflow-evals-with-mocked-tools.md)
  187. ### <a name="security-safety"></a>Security & Safety
  188. - [Authenticated Authority Channel](patterns/authenticated-authority-channel.md)
  189. - [Black-Box Skill Invocation](patterns/black-box-skill-invocation.md)
  190. - [Consequence-Family Coverage Audit](patterns/consequence-family-coverage-audit.md)
  191. - [Credential-Free Outbox](patterns/credential-free-outbox.md)
  192. - [Cryptographic Governance Audit Trail](patterns/cryptographic-governance-audit-trail.md)
  193. - [Denial Tracking & Permission Escalation](patterns/denial-tracking-permission-escalation.md)
  194. - [Deterministic Security Scanning Build Loop](patterns/deterministic-security-scanning-build-loop.md)
  195. - [Deterministic Threat Rule Scanning](patterns/deterministic-threat-rule-scanning.md)
  196. - [Evidence Questions, Not Verdict Questions](patterns/evidence-questions-not-verdict-questions.md)
  197. - [Exact-Action Authorization Binding](patterns/exact-action-authorization-binding.md)
  198. - [External Credential Sync](patterns/external-credential-sync.md)
  199. - [Hook-Based Safety Guard Rails for Autonomous Code Agents](patterns/hook-based-safety-guard-rails.md)
  200. - [Isolated VM per RL Rollout](patterns/isolated-vm-per-rl-rollout.md)
  201. - [Lethal Trifecta Threat Model](patterns/lethal-trifecta-threat-model.md)
  202. - [Local-First Credential Broker](patterns/local-first-credential-broker.md)
  203. - [Non-Custodial Spending Controls](patterns/non-custodial-spending-controls.md)
  204. - [One OS User per Agent](patterns/one-os-user-per-agent.md)
  205. - [PII Tokenization](patterns/pii-tokenization.md)
  206. - [Policy-Gated Tool Proxy](patterns/policy-gated-tool-proxy.md)
  207. - [Sandboxed Tool Authorization](patterns/sandboxed-tool-authorization.md)
  208. - [Soulbound Identity Verification](patterns/soulbound-identity-verification.md)
  209. - [Transitive Vouch-Chain Trust](patterns/transitive-vouch-chain-trust.md)
  210. - [Zero-Knowledge Verified Agent Egress](patterns/zero-knowledge-verified-agent-egress.md)
  211. - [Zero-Trust Agent Mesh](patterns/zero-trust-agent-mesh.md)
  212. ### <a name="tool-use-environment"></a>Tool Use & Environment
  213. - [Agent SDK for Programmatic Control](patterns/agent-sdk-for-programmatic-control.md)
  214. - [Agent-First Tool Discovery](patterns/agent-first-tool-discovery.md)
  215. - [Agent-First Tooling and Logging](patterns/agent-first-tooling-and-logging.md)
  216. - [Agentic Search Over Vector Embeddings](patterns/agentic-search-over-vector-embeddings.md)
  217. - [AI Web Search Agent Loop](patterns/ai-web-search-agent-loop.md)
  218. - [CLI-First Skill Design](patterns/cli-first-skill-design.md)
  219. - [CLI-Native Agent Orchestration](patterns/cli-native-agent-orchestration.md)
  220. - [Code Mode MCP Tool Interface Improvement Pattern](patterns/code-first-tool-interface-pattern.md)
  221. - [Code-Over-API Pattern](patterns/code-over-api-pattern.md)
  222. - [Code-Then-Execute Pattern](patterns/code-then-execute-pattern.md)
  223. - [Cross-Protocol Agent Discovery](patterns/cross-protocol-agent-discovery.md)
  224. - [Dual-Use Tool Design](patterns/dual-use-tool-design.md)
  225. - [Egress Lockdown (No-Exfiltration Channel)](patterns/egress-lockdown-no-exfiltration-channel.md)
  226. - [Filesystem-Mediated Host Delegation](patterns/filesystem-mediated-host-delegation.md)
  227. - [Intelligent Bash Tool Execution](patterns/intelligent-bash-tool-execution.md)
  228. - [LLM-Friendly API Design](patterns/llm-friendly-api-design.md)
  229. - [MCP Pattern Injection](patterns/mcp-pattern-injection.md)
  230. - [Multi-Platform Communication Aggregation](patterns/multi-platform-communication-aggregation.md)
  231. - [Multi-Platform Webhook Triggers](patterns/multi-platform-webhook-triggers.md)
  232. - [Patch Steering via Prompted Tool Selection](patterns/patch-steering-via-prompted-tool-selection.md)
  233. - [Precomputed Code Graph Lookup](patterns/precomputed-code-graph-lookup.md)
  234. - [Progressive Tool Discovery](patterns/progressive-tool-discovery.md)
  235. - [Static Service Manifest for Agents](patterns/static-service-manifest-for-agents.md)
  236. - [Tool Use Steering via Prompting](patterns/tool-use-steering-via-prompting.md)
  237. - [Unified Tool Gateway](patterns/unified-tool-gateway.md)
  238. - [Virtual Machine Operator Agent](patterns/virtual-machine-operator-agent.md)
  239. - [Visual AI Multimodal Integration](patterns/visual-ai-multimodal-integration.md)
  240. ### <a name="ux-collaboration"></a>UX & Collaboration
  241. - [Abstracted Code Representation for Review](patterns/abstracted-code-representation-for-review.md)
  242. - [Agent-Assisted Scaffolding](patterns/agent-assisted-scaffolding.md)
  243. - [Agent-Friendly Workflow Design](patterns/agent-friendly-workflow-design.md)
  244. - [AI-Accelerated Learning and Skill Development](patterns/ai-accelerated-learning-and-skill-development.md)
  245. - [Chain-of-Thought Monitoring & Interruption](patterns/chain-of-thought-monitoring-interruption.md)
  246. - [Codebase Optimization for Agents](patterns/codebase-optimization-for-agents.md)
  247. - [Democratization of Tooling via Agents](patterns/democratization-of-tooling-via-agents.md)
  248. - [Dev Tooling Assumptions Reset](patterns/dev-tooling-assumptions-reset.md)
  249. - [Human-in-the-Loop Approval Framework](patterns/human-in-loop-approval-framework.md)
  250. - [Latent Demand Product Discovery](patterns/latent-demand-product-discovery.md)
  251. - [Milestone Escrow for Agent Resource Funding](patterns/milestone-escrow-agent-funding.md)
  252. - [Proactive Trigger Vocabulary](patterns/proactive-trigger-vocabulary.md)
  253. - [Seamless Background-to-Foreground Handoff](patterns/seamless-background-to-foreground-handoff.md)
  254. - [Shell Command Contextualization](patterns/shell-command-contextualization.md)
  255. - [Spectrum of Control / Blended Initiative](patterns/spectrum-of-control-blended-initiative.md)
  256. - [Team-Shared Agent Configuration as Code](patterns/team-shared-agent-configuration.md)
  257. - [Verbose Reasoning Transparency](patterns/verbose-reasoning-transparency.md)
  258. <!-- AUTO-GENERATED PATTERNS END -->
  259. <!-- …existing content below… -->
  260. ---
  261. ## For AI Assistants (llms.txt)
  262. This project includes [`llms.txt`](https://agentic-patterns.com/llms.txt), a machine-readable documentation file designed to help AI assistants and LLMs understand and recommend appropriate patterns.
  263. **What's included:**
  264. - Pattern categories and their purposes
  265. - Key patterns with concise descriptions
  266. - Usage guidelines for AI assistants
  267. - Pattern selection strategies based on use case requirements
  268. **For developers building AI assistants:**
  269. The `llms.txt` file can be provided to LLMs as context to improve pattern recommendations. It's optimized for:
  270. - RAG systems indexing this catalogue
  271. - AI coding assistants suggesting patterns
  272. - LLM-powered tools that recommend agentic patterns
  273. **Access:** https://agentic-patterns.com/llms.txt (also available in [`apps/web/public/llms.txt`](./apps/web/public/llms.txt))
  274. ---
  275. ## Contributing in 3 steps
  276. 1. **Fork & branch** → `git checkout -b add-my-pattern`
  277. 2. **Add a pattern file** under `patterns/` using the template above.
  278. 3. **Run** `bun run build:data` to refresh the generated README sections and site data.
  279. 4. **Open a PR** titled `Add: my-pattern-name`.
  280. 5. This repository is pattern-first: proposals that are primarily product announcements or promotions will be rejected, even if technically valid.
  281. See [`CONTRIBUTING.md`](https://github.com/nibzard/awesome-agentic-patterns/blob/main/CONTRIBUTING.md) for the fine print.
  282. ---
  283. ## Inspiration
  284. This project started after the write‑up [**"What Sourcegraph learned building AI coding agents"**](https://www.nibzard.com/ampcode) (28 May 2025) and the ongoing *Raising an Agent* video diary. Many first patterns come straight from those lessons — thanks to everyone sharing their journey in the open!
  285. ---
  286. ## License
  287. Apache‑2.0. See [`LICENSE`](https://github.com/nibzard/awesome-agentic-patterns/blob/main/LICENSE).
  288. ---
  289. ## Star History
  290. [![Star History Chart](https://star-history.dera.page/svg?repos=nibzard/awesome-agentic-patterns&type=date&legend=top-left)](https://star-history.dera.page/#nibzard/awesome-agentic-patterns&type=date&legend=top-left)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.