{"id":21791420,"url":"https://github.com/mastra-ai/mastra","last_synced_at":"2025-05-14T22:05:39.414Z","repository":{"id":259087189,"uuid":"839037098","full_name":"mastra-ai/mastra","owner":"mastra-ai","description":"The TypeScript AI agent framework. ⚡ Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama.","archived":false,"fork":false,"pushed_at":"2025-05-14T21:39:52.000Z","size":179684,"stargazers_count":12934,"open_issues_count":177,"forks_count":711,"subscribers_count":53,"default_branch":"main","last_synced_at":"2025-05-14T22:05:03.303Z","etag":null,"topics":["agents","ai","chatbots","evals","javascript","llm","mcp","nextjs","nodejs","reactjs","tts","typescript","workflows"],"latest_commit_sha":null,"homepage":"https://mastra.ai","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mastra-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-08-06T20:44:31.000Z","updated_at":"2025-05-14T21:38:42.000Z","dependencies_parsed_at":"2024-12-15T21:25:37.615Z","dependency_job_id":"9377a19b-4106-4c32-8358-1b41ca476be5","html_url":"https://github.com/mastra-ai/mastra","commit_stats":null,"previous_names":["mastra-ai/mastra"],"tags_count":1069,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mastra-ai%2Fmastra","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mastra-ai%2Fmastra/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mastra-ai%2Fmastra/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mastra-ai%2Fmastra/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mastra-ai","download_url":"https://codeload.github.com/mastra-ai/mastra/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254235687,"owners_count":22036962,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","ai","chatbots","evals","javascript","llm","mcp","nextjs","nodejs","reactjs","tts","typescript","workflows"],"created_at":"2024-11-27T06:00:53.363Z","updated_at":"2025-05-14T22:05:39.344Z","avatar_url":"https://github.com/mastra-ai.png","language":"TypeScript","funding_links":[],"categories":["Agentic AI ![](https://img.shields.io/badge/_-AGENTIC-22d3ee?style=flat-square\u0026logo=openai\u0026logoColor=white)","Frameworks \u0026 SDKs","🏗️ エージェントフレームワーク","SDKs","Agent Integration \u0026 Deployment Tools","TypeScript","🤖 AI \u0026 Machine Learning","🕵️ 智能体（Agents）","Agent Frameworks","📋 Changelog","ai","Agentic Workflow","📚 Projects (1974 total)","Frameworks","Design Primitives","Chatbots","HarmonyOS","🧰 Frameworks that Facilitate RAG","A01_文本生成_文本对话","APIs and HTTP Requests","Repos","🧱 Agent Frameworks","Agent SDK / framework","Best starting points","typescript","AI \u0026 LLM","Other LLM Frameworks","Other AI Agents","Built with TypeScript","Agent Ecosystem","MCP DevTools","Building","Frameworks \u0026 Libraries","5 · Evaluation infrastructure (the eval stack: datasets, scorers, online/offline, tracing, CI)","🧠 AI Applications \u0026 Platforms","Orchestration Frameworks","Agent SDKs \u0026 Frameworks","2. Libraries \u0026 Frameworks","**1. Libraries**","Tools and Code","Multi-Agent Orchestration","MCP Servers \u0026 Protocol","Open Source Tools","AI Frameworks \u0026 SDKs","Agent Development Platforms","4. Agentic AI \u0026 Multi-Agent Systems","🌟 Core Frameworks","agents","🏆 القائمة الكاملة Top 200","Agentic Systems","Agentic Frameworks","Swarm Frameworks"],"sub_categories":["Agentic frameworks","Trading \u0026 Exchanges","その他の標準","JavaScript/TypeScript","AI Agent Gateway","主流 Agent 框架","Community","2026-07-19 — Weekly Update","MCP Servers","Task Runners \u0026 Orchestration","Windows Manager","大语言对话模型及数据","Advanced Components","General Purpose","Agents \u0026 Orchestration","Videos Playlists","Multi-Agent / Orchestration Frameworks","AI","Frameworks","Multi-Agent Orchestration","5b · TypeScript/JS-native eval runners","Tools","Orchestration Frameworks","JavaScript / TypeScript","Agent Frameworks"],"readme":"# Mastra\n\n[![npm version](https://badge.fury.io/js/@mastra%2Fcore.svg)](https://www.npmjs.com/package/@mastra/core)\n![GitHub Repo stars](https://img.shields.io/github/stars/mastra-ai/mastra)\n[![Discord](https://img.shields.io/discord/1309558646228779139?logo=discord\u0026label=Discord\u0026labelColor=white\u0026color=7289DA)](https://discord.gg/BTYqqHKUrf)\n[![Twitter Follow](https://img.shields.io/twitter/follow/mastra_ai?style=social)](https://x.com/mastra_ai)\n[![NPM Downloads](https://img.shields.io/npm/dm/%40mastra%252Fcore)](https://www.npmjs.com/package/@mastra/core)\n![Static Badge](https://img.shields.io/badge/Y%20Combinator-W25-orange)\n\nMastra is an opinionated TypeScript framework that helps you build AI applications and features quickly. It gives you the set of primitives you need: workflows, agents, RAG, integrations and evals. You can run Mastra on your local machine, or deploy to a serverless cloud.\n\nThe main Mastra features are:\n\n| Features                                               | Description                                                                                                                                                                                                                                                                                            |\n| ------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| LLM Models                                             | Mastra uses the [Vercel AI SDK](https://sdk.vercel.ai/docs/introduction) for model routing, providing a unified interface to interact with any LLM provider including OpenAI, Anthropic, and Google Gemini. You can choose the specific model and provider, and decide whether to stream the response. |\n| [Agents](https://mastra.ai/docs/agents/overview)       | Agents are systems where the language model chooses a sequence of actions. In Mastra, agents provide LLM models with tools, workflows, and synced data. Agents can call your own functions or APIs of third-party integrations and access knowledge bases you build.                                   |\n| [Tools](https://mastra.ai/docs/agents/adding-tools)    | Tools are typed functions that can be executed by agents or workflows, with built-in integration access and parameter validation. Each tool has a schema that defines its inputs, an executor function that implements its logic, and access to configured integrations.                               |\n| [Workflows](https://mastra.ai/docs/workflows/overview) | Workflows are durable graph-based state machines. They have loops, branching, wait for human input, embed other workflows, do error handling, retries, parsing and so on. They can be built in code or with a visual editor. Each step in a workflow has built-in OpenTelemetry tracing.               |\n| [RAG](https://mastra.ai/docs/rag/overview)             | Retrieval-augemented generation (RAG) lets you construct a knowledge base for agents. RAG is an ETL pipeline with specific querying techniques, including chunking, embedding, and vector search.                                                                                                      |\n| [Integrations](https://mastra.ai/docs/integrations)    | In Mastra, integrations are auto-generated, type-safe API clients for third-party services that can be used as tools for agents or steps in workflows.                                                                                                                                                 |\n| [Evals](https://mastra.ai/docs/08-running-evals)       | Evals are automated tests that evaluate LLM outputs using model-graded, rule-based, and statistical methods. Each eval returns a normalized score between 0-1 that can be logged and compared. Evals can be customized with your own prompts and scoring functions.                                    |\n\n## Quick Start\n\n### Prerequisites\n\n- Node.js (v20.0+)\n\n## Get an LLM provider API key\n\nIf you don't have an API key for an LLM provider, you can get one from the following services:\n\n- [OpenAI](https://platform.openai.com/)\n- [Anthropic](https://console.anthropic.com/settings/keys)\n- [Google Gemini](https://ai.google.dev/gemini-api/docs)\n- [Groq](https://console.groq.com/docs/overview)\n- [Cerebras](https://inference-docs.cerebras.ai/introduction)\n\nIf you don't have an account with these providers, you can sign up and get an API key. Anthropic require a credit card to get an API key. Some OpenAI models and Gemini do not and have a generous free tier for its API.\n\n## Create a new project\n\nThe easiest way to get started with Mastra is by using `create-mastra`. This CLI tool enables you to quickly start building a new Mastra application, with everything set up for you.\n\n```bash\nnpx create-mastra@latest\n```\n\n### Run the script\n\nFinally, run `mastra dev` to open the Mastra playground.\n\n```bash copy\nnpm run dev\n```\n\nIf you're using Anthropic, set the `ANTHROPIC_API_KEY`. If you're using Gemini, set the `GOOGLE_GENERATIVE_AI_API_KEY`.\n\n## Contributing\n\nLooking to contribute? All types of help are appreciated, from coding to testing and feature specification.\n\nIf you are a developer and would like to contribute with code, please open an issue to discuss before opening a Pull Request.\n\nInformation about the project setup can be found in the [development documentation](./DEVELOPMENT.md)\n\n## Support\n\nWe have an [open community Discord](https://discord.gg/BTYqqHKUrf). Come and say hello and let us know if you have any questions or need any help getting things running.\n\nIt's also super helpful if you leave the project a star here at the [top of the page](https://github.com/mastra-ai/mastra)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmastra-ai%2Fmastra","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmastra-ai%2Fmastra","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmastra-ai%2Fmastra/lists"}