Free, open-source shadcn-style registry of production-ready AI agent recipes for developers who want full code ownership with zero config.
What it does
agentcn is a free, open-source registry of production-ready AI agent recipes built on the shadcn copy-paste model. Each recipe ships the full agent source (instructions, tools, skills, workflows) so you own every line and can customize without fighting a library.
Most agent tooling forces a choice: move fast with an opaque package you cannot inspect, or build from scratch with raw framework primitives. agentcn takes a third path borrowed from shadcn/ui: copy the full agent source into your project, own every file, and ship on day one.
agentcn is a registry of complete AI agent recipes, not a UI component library. Each recipe distributes backend files: an agent definition, a Markdown instructions file, typed tools, and workflow logic. Per the docs, you copy them straight into your project with the shadcn CLI, so there is no runtime dependency to fight when requirements change.
You run one command, for example npx shadcn@latest add @agentcn/eve/company-knowledge, and the recipe lands in your repo as plain source files. From there, swap the model in agent.ts, extend the tools directory, or replace the vector store with pgvector or Pinecone. Every recipe ships in both Eve (a filesystem-first framework for durable agents on Vercel Functions) and Flue (an agent runtime with first-class subagents and bounded workflows), so you adopt the pattern in whichever framework you already use.
The Company Knowledge agent shows the pattern in full. It indexes internal documents into a libSQL vector store, searches the corpus first on each query, and redacts personal data (emails, phone numbers, SSNs, card numbers, API keys) from responses before returning an answer. The four files that make up the recipe are each short enough to read in minutes, and the docs list explicit swap points: feed index_document from Linear or Notion, replace the vector store, or tune the redaction patterns in lib/pii.ts.
The sharpest tradeoff: when you copy source into your project, you own upgrades too. An agentcn update will not flow to your codebase automatically the way a library patch would. You trade the convenience of npm update for full code ownership and zero framework lock-in. Teams that ship frequently and customize heavily will come out ahead; teams that want a managed, auto-updating dependency may not.
agentcn is the shadcn playbook applied to backend AI agents: browse the registry, run one CLI command, and get a working, fully inspectable agent you can reshape without working around a black box. Evaluating it takes minutes at agentcn.run. When you are ready to ship, run npx shadcn@latest add with any recipe slug and the files land directly in your project.
Features
Field notes
Reviewed Jun 26, 2026
Best for
Builder outcomes
Watch out
Tested with
agentcn is a free, open-source registry of production-ready AI agent recipes modeled after shadcn/ui but for backend agents. Each recipe ships the full agent source, including an agent definition file, a Markdown instructions file, typed tools, and workflow logic. You copy the files into your own project with the shadcn CLI and own every line from day one. The registry is hosted at agentcn.run and the source is on GitHub under the MIT license.
Run `npx shadcn@latest add @agentcn/<framework>/<recipe-name>` in your project root, replacing the placeholders with the framework (eve or flue) and the recipe slug you want. The CLI copies the agent files directly into your project. For recipes with additional dependencies, the docs list an `npm install` command for packages like `eve`, `@libsql/client`, `@ai-sdk/openai`, and `ai`.
Yes, agentcn is free and released under the MIT license, per the GitHub repository. There is no paid tier for the registry itself. Running the agents may incur costs from third-party services you configure: Vercel Functions for Eve-based recipes, your chosen vector store (libSQL, Pinecone, pgvector), and any model provider like OpenAI.
agentcn is best for developer teams who want to ship a working AI agent quickly without giving up the ability to read, customize, and extend every part of it. The docs call out internal tooling as a primary use case: document Q&A assistants, knowledge bases, and workflow automation. It pairs especially well with teams already using the shadcn CLI and deploying on Vercel with Eve.
agentcn copies full agent source directly into your project; LangChain and similar libraries ship as opaque packages you import and depend on at runtime. The practical difference: with agentcn you can read, modify, and extend every line without working around the library's abstractions, but you also own the upgrade path manually. Per the docs, agentcn explicitly takes the opposite approach to 'black box' agent packages, trading automatic patch delivery for zero lock-in and direct access to framework primitives.
The copy-paste model means that when the agentcn registry publishes an improved version of a recipe, that update does not flow automatically to your project the way an `npm update` would. You need to manually re-copy or diff changes. Additionally, recipes are built on Eve or Flue, so projects on other agent runtimes will need to add one of those frameworks. The current size of the recipe catalog is not published on the site, so browsing agentcn.run is the best way to check current coverage before committing to the tool.
78+ animated shadcn/ui components plus 100+ AI agent patterns, distributed as copy-paste source, free, open-source, and zero npm lock-in.
Best for React and Tailwind teams already using shadcn/ui who want animated, accessible components without npm package overheadshadcn/ui, open-source, copy-owned UI components for developers building their own design system with full code control.
Best for Teams building a custom design system who need full ownership of component source codeOpen-source memory and context engine for stateful AI agents, works with any model, framework, or architecture.
Best for Builders who need agents to model how users and other agents change over time, not just retrieve past messagesOpen-source React component kit for agentic AI apps: streaming chat, tool calls, reasoning, citations, and more, SDK-agnostic and fully owned by your codebase.
Best for React teams building agentic or chat interfaces who want streaming-ready components without writing them from scratchZero-dependency, SQLite-backed AI memory layer for agents, MCP-ready, local-first, and benchmarked against BEAM and LongMemEval.
Best for Builders who want persistent agent memory with zero infrastructure, no Postgres, Docker, or SaaS requiredOpen Design is the open-source, local-first Claude Design alternative for builders who want agent-native design, prototypes, decks, and video, without a vendor lock-in.
Best for Developers who want to generate design artifacts from a brief using their existing coding agent