[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-3778":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":40,"readmeContent":41,"aiSummary":42,"trendingCount":16,"starSnapshotCount":16,"syncStatus":43,"lastSyncTime":44,"discoverSource":45},3778,"eliza","elizaOS\u002Feliza","elizaOS","Open source agentic operating system","https:\u002F\u002Felizaos.ai\u002F",null,"TypeScript",18556,5561,151,9,0,4,45,208,31,108,"MIT License",false,"develop",[26,27,28,29,30,31,32,5,33,34,35,36,37,38,39],"agent","agentic","ai","autonomous","chatbot","crypto","discord","elizaos","framework","plugins","rag","slack","swarm","telegram","2026-06-12 04:00:19","\u003Cdiv align=\"center\">\n  \u003Ch1>elizaOS\u003C\u002Fh1>\n  \u003Cp>\u003Cstrong>An open-source framework for building autonomous AI agents.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003C\u002Fdiv>\n\n## ✨ What is Eliza?\n\nelizaOS is an all-in-one, extensible platform for building and deploying AI-powered applications. Whether you're creating sophisticated chatbots, autonomous agents for business process automation, or intelligent game NPCs, Eliza provides the tools you need to get started quickly and scale effectively.\n\nIt combines a modular architecture, a powerful CLI, and a rich web interface to give you full control over your agents' development, deployment, and management lifecycle.\n\nFor complete guides and API references, visit our official **[documentation](https:\u002F\u002Fdocs.elizaos.ai\u002F)**.\n\n## 🚀 Key Features\n\n- 🔌 **Rich Connectivity**: Out-of-the-box connectors for Discord, Telegram, Farcaster, and more.\n- 🧠 **Model Agnostic**: Supports all major models, including OpenAI, Gemini, Anthropic, Llama, and Grok.\n- 🖥️ **Modern Web UI**: A professional dashboard for managing agents, groups, and conversations in real-time.\n- 🤖 **Multi-Agent Architecture**: Designed from the ground up for creating and orchestrating groups of specialized agents.\n- 📄 **Document Ingestion**: Easily ingest documents and allow agents to retrieve information and answer questions from your data (RAG).\n- 🛠️ **Highly Extensible**: Build your own functionality with a powerful plugin system.\n- 📦 **It Just Works**: A seamless setup and development experience from day one.\n\n> **Looking for plugins?** Browse the community plugin registry at **[elizaOS-plugins\u002Fregistry](https:\u002F\u002Fgithub.com\u002FelizaOS-plugins\u002Fregistry)** for a full list of available ElizaOS plugins.\n\n## Framework, Projects, And App Plugins\n\nelizaOS is a framework plus packages built on top of it. Knowing which layer\nyou're working with keeps projects, plugins, and app surfaces from getting\nmixed together.\n\n**The framework** is the runtime: `@elizaos\u002Fcore`, the agent loop, the plugin model (actions, providers, services, evaluators), the message\u002Fmemory\u002Fstate primitives, and the model-agnostic LLM layer. If you depend on `@elizaos\u002Fcore` from your own code, you are using the framework.\n\n**A project** is a deployable product workspace built on the framework. A\ngenerated project owns its branded app shell, usually under `apps\u002Fapp` inside\nthat project workspace.\n\n**An app plugin** is a runtime plugin that also contributes an app surface inside\nEliza. First-party app plugins live under [`plugins\u002Fapp-*`](plugins), keep npm\nnames like `@elizaos\u002Fapp-companion`, and are loaded by package name. They are\nplugins, not top-level repo applications.\n\nThe same split shows up in the directory tree:\n\n```\npackages\u002F        ← framework and shared packages\n  core\u002F          # @elizaos\u002Fcore — runtime, types, agent loop\n  agent\u002F         # @elizaos\u002Fagent — AgentRuntime + plugin loader\n  app-core\u002F      # API + dashboard host\n  elizaos\u002F       # the `elizaos` CLI\n  prompts\u002F       # shared prompt scaffolding\n  ui\u002F            # shared React component library\n  examples\u002F      # standalone examples (chat, discord, mcp, ...)\n  benchmarks\u002F    # evaluation suites (gaia, swe_bench, tau-bench, ...)\n\nplugins\u002F         ← runtime plugins and app plugins\n  app-companion\u002F app-browser\u002F app-knowledge\u002F app-phone\u002F\n  app-task-coordinator\u002F app-training\u002F plugin-form\u002F ...\n  plugin-discord\u002F plugin-openai\u002F plugin-sql\u002F ...\n\npackages\u002Felizaos\u002Ftemplates\u002F   ← CLI scaffolds + min-project \u002F min-plugin for APP\u002FPLUGIN create\n```\n\nA *plugin* sits between the two: framework-shaped (registers actions\u002Fproviders\u002Fservices with the runtime) but shipped and consumed like a product. Community plugins are listed at [elizaOS-plugins\u002Fregistry](https:\u002F\u002Fgithub.com\u002FelizaOS-plugins\u002Fregistry).\n\n## Pick your starting point\n\n| You want to… | Start here |\n|---|---|\n| Try an agent in 5 minutes | [CLI quick start](#cli-quick-start) |\n| Use the runtime from your own TypeScript code (no CLI, no UI) | [Standalone usage](#standalone-usage) |\n| Build a new deployable product | [Create a new project](#create-a-new-project) |\n| Build a runtime plugin (action \u002F provider \u002F service) | [Create a new plugin](#create-a-new-plugin) |\n| See how others did it | [Examples](#examples) |\n| Evaluate or benchmark an agent | [Benchmarks](#benchmarks) |\n| Read the docs | [docs.elizaos.ai](https:\u002F\u002Fdocs.elizaos.ai\u002F) |\n\n## CLI quick start\n\n**Prerequisites:** [Node.js v24+](https:\u002F\u002Fnodejs.org\u002F), [bun](https:\u002F\u002Fbun.sh\u002Fdocs\u002Finstallation). On Windows, use [WSL 2](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fwindows\u002Fwsl\u002Finstall-manual).\n\n```bash\nbun add -g elizaos\nelizaos create my-first-agent --template project\ncd my-first-agent\n# add OPENAI_API_KEY=... to .env (or your provider's key)\nbun install\nbun run dev\n```\n\nThe generated project exposes the runtime scripts you'll use day-to-day: `bun run dev`, `bun run build`, `bun run test`, `bun run typecheck`, `bun run lint`, `bun run verify`. The `elizaos` CLI itself is intentionally minimal — its job is scaffolding (`elizaos create`) and template upgrades (`elizaos upgrade`). For a list of available templates, run `elizaos info`.\n\nFull reference: `elizaos --help` or `elizaos \u003Ccommand> --help`.\n\n## Standalone usage\n\nUse `@elizaos\u002Fcore` directly — no CLI, no dashboard, just the runtime in your code.\n\n```bash\ngit clone --filter=blob:none https:\u002F\u002Fgithub.com\u002Felizaos\u002Feliza.git\ncd eliza\nbun install\n\n# Interactive REPL against a real agent\nOPENAI_API_KEY=your_key bun run packages\u002Fexamples\u002Fchat\u002Fchat.ts\n```\n\nNearly every surface has a working example in [`packages\u002Fexamples\u002F`](packages\u002Fexamples) — 30+ in total. Each one has its own README and runs independently. They are the fastest way to see the framework standing on its own. See [Examples](#examples) below for the highlights.\n\n> **About the partial clone.** `--filter=blob:none` gives you the full history but fetches file contents on demand — about 10× smaller. `git log`, branches, and `git checkout` work normally; `git blame` and `git log -p` will fetch on first use. To upgrade later: `git config --unset remote.origin.partialclonefilter && git fetch --refetch`. For one-off CI, `--depth=1 --single-branch` is even smaller.\n\n## Create a new project\n\nA project is a self-contained product workspace on top of the runtime: branded\napp shell, local eliza checkout, app plugin selection, platform config, and\ndeployment scripts. Two paths:\n\n**1. CLI scaffold (recommended).**\n\n```bash\nelizaos create my-app --template project\ncd my-app\nbun install\nbun run dev\n```\n\nThe project template lays out a full workspace with a local eliza checkout, default plugins (`plugin-sql`, `plugin-elizacloud`, `plugin-local-ai`, `plugin-ollama`), and a Vite + React UI you can edit immediately.\n\n**2. Copy a template directly.** [`packages\u002Felizaos\u002Ftemplates\u002Fmin-project\u002F`](packages\u002Felizaos\u002Ftemplates\u002Fmin-project) is the smallest possible app — Vite + React UI, a runtime `Plugin` with one action, the `elizaos.app` metadata block in `package.json`, and a vitest smoke test. Read [`packages\u002Felizaos\u002Ftemplates\u002Fmin-project\u002FSCAFFOLD.md`](packages\u002Felizaos\u002Ftemplates\u002Fmin-project\u002FSCAFFOLD.md) for the placeholders to replace and the verification contract.\n\nFor first-party app plugin references, browse [`plugins\u002Fapp-*`](plugins). A few starting points by complexity:\n\n- [`app-companion`](plugins\u002Fapp-companion) — chat-first companion with a custom React UI.\n- [`app-browser`](plugins\u002Fapp-browser) — agent-driven browser automation.\n- [`app-knowledge`](plugins\u002Fapp-knowledge) — RAG over user documents.\n- [`app-phone`](plugins\u002Fapp-phone) — voice + telephony surface.\n- [`plugin-form`](plugins\u002Fplugin-form) — form-driven data collection.\n- [`app-task-coordinator`](plugins\u002Fapp-task-coordinator) — multi-agent orchestration.\n- [`app-training`](plugins\u002Fapp-training) — trajectory capture + native prompt optimization.\n\n## Create a new plugin\n\nA *plugin* extends the runtime with actions, providers, services, or evaluators — no UI required.\n\n```bash\nelizaos create my-plugin -t plugin\ncd my-plugin\nbun install\nbun run build\n```\n\nOr copy [`packages\u002Felizaos\u002Ftemplates\u002Fmin-plugin\u002F`](packages\u002Felizaos\u002Ftemplates\u002Fmin-plugin) directly. See [`packages\u002Felizaos\u002Ftemplates\u002Fmin-plugin\u002FSCAFFOLD.md`](packages\u002Felizaos\u002Ftemplates\u002Fmin-plugin\u002FSCAFFOLD.md) for the contract.\n\nOnce typecheck, lint, and tests pass, publish to npm. Community plugins are listed in [elizaOS-plugins\u002Fregistry](https:\u002F\u002Fgithub.com\u002FelizaOS-plugins\u002Fregistry).\n\n## Examples\n\n[`packages\u002Fexamples\u002F`](packages\u002Fexamples) — 30+ runnable references covering connectors, integrations, hosting targets, and gameplay. Each subdirectory is independently buildable and has its own README.\n\n| Category | Examples |\n|---|---|\n| Conversational | [`chat`](packages\u002Fexamples\u002Fchat), [`discord`](packages\u002Fexamples\u002Fdiscord), [`telegram`](packages\u002Fexamples\u002Ftelegram), [`farcaster`](packages\u002Fexamples\u002Ffarcaster), [`farcaster-miniapp`](packages\u002Fexamples\u002Ffarcaster-miniapp), [`twitter-xai`](packages\u002Fexamples\u002Ftwitter-xai), [`bluesky`](packages\u002Fexamples\u002Fbluesky) |\n| Web frameworks | [`next`](packages\u002Fexamples\u002Fnext), [`react`](packages\u002Fexamples\u002Freact), [`html`](packages\u002Fexamples\u002Fhtml), [`browser-extension`](packages\u002Fexamples\u002Fbrowser-extension), [`rest-api`](packages\u002Fexamples\u002Frest-api) |\n| Hosting \u002F serverless | [`vercel`](packages\u002Fexamples\u002Fvercel), [`cloudflare`](packages\u002Fexamples\u002Fcloudflare), [`gcp`](packages\u002Fexamples\u002Fgcp), [`aws`](packages\u002Fexamples\u002Faws), [`supabase`](packages\u002Fexamples\u002Fsupabase), [`convex`](packages\u002Fexamples\u002Fconvex) |\n| Protocols | [`mcp`](packages\u002Fexamples\u002Fmcp), [`a2a`](packages\u002Fexamples\u002Fa2a) |\n| On-chain \u002F trading | [`polymarket`](packages\u002Fexamples\u002Fpolymarket), [`trader`](packages\u002Fexamples\u002Ftrader), [`lp-manager`](packages\u002Fexamples\u002Flp-manager) |\n| Fun \u002F games | [`tic-tac-toe`](packages\u002Fexamples\u002Ftic-tac-toe), [`text-adventure`](packages\u002Fexamples\u002Ftext-adventure), [`game-of-life`](packages\u002Fexamples\u002Fgame-of-life), [`roblox`](packages\u002Fexamples\u002Froblox), [`elizagotchi`](packages\u002Fexamples\u002Felizagotchi) |\n| Other | [`autonomous`](packages\u002Fexamples\u002Fautonomous), [`avatar`](packages\u002Fexamples\u002Favatar), [`code`](packages\u002Fexamples\u002Fcode), [`form`](packages\u002Fexamples\u002Fform), [`moltbook`](packages\u002Fexamples\u002Fmoltbook), [`_plugin`](packages\u002Fexamples\u002F_plugin) |\n\n## Benchmarks\n\n[`packages\u002Fbenchmarks\u002F`](packages\u002Fbenchmarks) — 30+ evaluation suites for measuring agent capability. Each lives in its own subdirectory with its own harness and README.\n\n| Category | Benchmarks |\n|---|---|\n| General agent | [`gaia`](packages\u002Fbenchmarks\u002Fgaia), [`agentbench`](packages\u002Fbenchmarks\u002Fagentbench), [`tau-bench`](packages\u002Fbenchmarks\u002Ftau-bench), [`gauntlet`](packages\u002Fbenchmarks\u002Fgauntlet), [`realm`](packages\u002Fbenchmarks\u002Frealm), [`trust`](packages\u002Fbenchmarks\u002Ftrust), [`experience`](packages\u002Fbenchmarks\u002Fexperience) |\n| Coding | [`swe_bench`](packages\u002Fbenchmarks\u002Fswe_bench), [`bfcl`](packages\u002Fbenchmarks\u002Fbfcl), [`mint`](packages\u002Fbenchmarks\u002Fmint) |\n| OS \u002F desktop | [`OSWorld`](packages\u002Fbenchmarks\u002FOSWorld), [`terminal-bench`](packages\u002Fbenchmarks\u002Fterminal-bench) |\n| Web | [`mind2web`](packages\u002Fbenchmarks\u002Fmind2web), [`webshop`](packages\u002Fbenchmarks\u002Fwebshop) |\n| On-chain \u002F trading | [`HyperliquidBench`](packages\u002Fbenchmarks\u002FHyperliquidBench), [`solana`](packages\u002Fbenchmarks\u002Fsolana), [`evm`](packages\u002Fbenchmarks\u002Fevm), [`vending-bench`](packages\u002Fbenchmarks\u002Fvending-bench) |\n| Voice \u002F multimodal | [`voicebench`](packages\u002Fbenchmarks\u002Fvoicebench) |\n| Specialized | [`adhdbench`](packages\u002Fbenchmarks\u002Fadhdbench), [`clawbench`](packages\u002Fbenchmarks\u002Fclawbench), [`openclaw-benchmark`](packages\u002Fbenchmarks\u002Fopenclaw-benchmark), [`woobench`](packages\u002Fbenchmarks\u002Fwoobench), [`rlm-bench`](packages\u002Fbenchmarks\u002Frlm-bench), [`social-alpha`](packages\u002Fbenchmarks\u002Fsocial-alpha) |\n| elizaOS-specific | [`app-eval`](packages\u002Fbenchmarks\u002Fapp-eval), [`configbench`](packages\u002Fbenchmarks\u002Fconfigbench), [`context-bench`](packages\u002Fbenchmarks\u002Fcontext-bench), [`framework`](packages\u002Fbenchmarks\u002Fframework), [`orchestrator`](packages\u002Fbenchmarks\u002Forchestrator), [`orchestrator_lifecycle`](packages\u002Fbenchmarks\u002Forchestrator_lifecycle) |\n\nThe runbook for orchestrator-driven benchmark runs is [`packages\u002Fbenchmarks\u002FORCHESTRATOR_SUBAGENT_BENCHMARK_RUNBOOK.md`](packages\u002Fbenchmarks\u002FORCHESTRATOR_SUBAGENT_BENCHMARK_RUNBOOK.md). The Eliza adapter that lets a benchmark drive an Eliza agent lives at [`packages\u002Fbenchmarks\u002Feliza-adapter`](packages\u002Fbenchmarks\u002Feliza-adapter). A combined results viewer is at [`packages\u002Fbenchmarks\u002Fviewer`](packages\u002Fbenchmarks\u002Fviewer).\n\n## Working in the monorepo\n\n```bash\nbun install            # workspace install\nbun run dev            # API + Vite UI for apps\u002Fapp\nbun run build          # turbo build across the workspace\nbun run lint           # turbo lint across the workspace\nbun run test           # full test suite (scripts\u002Frun-all-tests.mjs)\n```\n\nKey framework packages:\n\n- **[`@elizaos\u002Fcore`](packages\u002Fcore)** — runtime, types, agent loop. The package the framework starts and ends with.\n- **[`@elizaos\u002Fagent`](packages\u002Fagent)** — `AgentRuntime`, plugin loader, default plugin map.\n- **[`@elizaos\u002Fapp-core`](packages\u002Fapp-core)** — Express API + dashboard host that runs agents.\n- **[`elizaos`](packages\u002Felizaos)** — the `elizaos` CLI: `create`, `info`, `upgrade`, `version`.\n- **[`@elizaos\u002Fprompts`](packages\u002Fprompts)** — shared prompt scaffolding.\n- **[`@elizaos\u002Fui`](packages\u002Fui)** — shared React component library.\n- **[`plugins\u002F`](plugins)** — connectors and capabilities (Telegram, Discord, Farcaster, Twitter\u002FX, browser, video, TEE, …).\n\n## Contributing\n\nContributions welcome. Open an issue before sending a non-trivial PR.\n\n- [Bug Report](.github\u002FISSUE_TEMPLATE\u002Fbug_report.md)\n- [Feature Request](.github\u002FISSUE_TEMPLATE\u002Ffeature_request.md)\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\n## Contributors\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Felizaos\u002Feliza\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=elizaos\u002Feliza\" alt=\"Eliza project contributors\" \u002F>\n\u003C\u002Fa>\n","elizaOS是一个用于构建自主AI代理的开源框架。其核心功能包括丰富的连接器支持（如Discord、Telegram等）、模型无关性（兼容OpenAI、Anthropic等多种主流模型）、现代化的Web界面、多代理架构设计、文档摄入能力以及高度可扩展的插件系统，旨在提供从开发到部署的一站式解决方案。适用于需要快速搭建并管理聊天机器人、业务流程自动化代理或智能游戏角色NPC等各种场景。凭借其模块化架构和强大的CLI工具，elizaOS能够帮助企业及开发者轻松实现AI应用的创建与规模化运营。",2,"2026-06-11 02:56:12","top_language"]