[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-5581":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":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":37,"readmeContent":38,"aiSummary":39,"trendingCount":16,"starSnapshotCount":16,"syncStatus":40,"lastSyncTime":41,"discoverSource":42},5581,"rig","0xPlaygrounds\u002Frig","0xPlaygrounds","⚙️🦀 Build modular and scalable LLM Applications in Rust","https:\u002F\u002Frig.rs",null,"Rust",7590,841,55,62,0,14,64,348,58,39.78,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35,36],"agent","ai","artificial-intelligence","automation","generative-ai","large-language-model","llm","llmops","rust","scalable-ai","2026-06-12 02:01:12","\u003Cp align=\"center\">\n\u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"img\u002Frig-rebranded-logo-white.svg\">\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"img\u002Frig-rebranded-logo-black.svg\">\n    \u003Cimg src=\"img\u002Frig-rebranded-logo-white.svg\" style=\"width: 40%; height: 40%;\" alt=\"Rig logo\">\n\u003C\u002Fpicture>\n\u003Cbr>\n\u003Cbr>\n\u003Ca href=\"https:\u002F\u002Fdocs.rig.rs\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F📖 docs-rig.rs-dca282.svg\" \u002F>\u003C\u002Fa>  \n\u003Ca href=\"https:\u002F\u002Fdocs.rs\u002Frig\u002Flatest\u002Frig\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-API Reference-dca282.svg\" \u002F>\u003C\u002Fa>  \n\u003Ca href=\"https:\u002F\u002Fcrates.io\u002Fcrates\u002Frig-core\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fcrates\u002Fv\u002Frig-core.svg?color=dca282\" \u002F>\u003C\u002Fa>\n \n\u003Ca href=\"https:\u002F\u002Fcrates.io\u002Fcrates\u002Frig-core\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fcrates\u002Fd\u002Frig-core.svg?color=dca282\" \u002F>\u003C\u002Fa>\n\u003C\u002Fbr>\n\u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002Fplaygrounds\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F511303648119226382?color=%236d82cc&label=Discord&logo=discord&logoColor=white\" \u002F>\u003C\u002Fa>\n \n\u003Ca href=\"\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fbuilt_with-Rust-dca282.svg?logo=rust\" \u002F>\u003C\u002Fa>\n \n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002F0xPlaygrounds\u002Frig?style=social\" alt=\"stars - rig\" \u002F>\u003C\u002Fa>\n\u003Cbr>\n\n\u003Cbr>\n\u003C\u002Fp>\n \n\n\n\u003Cdiv align=\"center\">\n\n[📑 Docs](https:\u002F\u002Fdocs.rig.rs)\n\u003Cspan>  •  \u003C\u002Fspan>\n[🌐 Website](https:\u002F\u002Frig.rs)\n\u003Cspan>  •  \u003C\u002Fspan>\n[🤝 Contribute](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Fissues\u002Fnew)\n\u003Cspan>  •  \u003C\u002Fspan>\n[✍🏽 Blogs](https:\u002F\u002Fdocs.rig.rs\u002Fguides)\n\n\u003C\u002Fdiv>\n\n✨ If you would like to help spread the word about Rig, please consider starring the repo!\n\n> [!WARNING]\n> Here be dragons! As we plan to ship a torrent of features in the following months, future updates **will** contain **breaking changes**. With Rig evolving, we'll annotate changes and highlight migration paths as we encounter them.\n\n## Table of contents\n\n- [Table of contents](#table-of-contents)\n- [What is Rig?](#what-is-rig)\n- [High-level features](#high-level-features)\n- [Who's using Rig?](#who-is-using-rig)\n- [Get Started](#get-started)\n  - [Simple example](#simple-example)\n- [Integrations](#supported-integrations)\n\n## What is Rig?\nRig is a Rust library for building scalable, modular, and ergonomic **LLM-powered** applications.\n\nMore information about this crate can be found in the [official](https:\u002F\u002Fdocs.rig.rs) and [crate](https:\u002F\u002Fdocs.rs\u002Frig\u002Flatest\u002Frig\u002F) API reference documentation.\n\n## Features\n- Agentic workflows that can handle multi-turn streaming and prompting\n- Full [GenAI Semantic Convention](https:\u002F\u002Fopentelemetry.io\u002Fdocs\u002Fspecs\u002Fsemconv\u002Fgen-ai\u002F) compatibility\n- 20+ model providers, all under one singular unified interface\n- 10+ vector store integrations, all under one singular unified interface\n- Full support for LLM completion and embedding workflows\n- Support for transcription, audio generation and image generation model capabilities\n- Integrate LLMs in your app with minimal boilerplate\n- Full WASM compatibility (core library only)\n\n## Who is using Rig?\nBelow is a non-exhaustive list of companies and people who are using Rig:\n- [St Jude](https:\u002F\u002Fwww.stjude.org\u002F) - Using Rig for a chatbot utility as part of [`proteinpaint`](https:\u002F\u002Fgithub.com\u002Fstjude\u002Fproteinpaint), a genomics visualisation tool.\n- [Coral Protocol](https:\u002F\u002Fwww.coralprotocol.org\u002F) - Using Rig extensively, both internally as well as part of the [Coral Rust SDK.](https:\u002F\u002Fgithub.com\u002FCoral-Protocol\u002Fcoral-rs)\n- [VT Code](https:\u002F\u002Fgithub.com\u002Fvinhnx\u002Fvtcode) - VT Code is a Rust-based terminal coding agent with semantic code intelligence via Tree-sitter and ast-grep. VT Code uses `rig` for simplifying LLM calls and implement model picker.\n- [Con](https:\u002F\u002Fgithub.com\u002Fnowledge-co\u002Fcon) - Con is a GPU-accelerated terminal emulator with a built-in AI agent harness. It uses Rig as the provider abstraction layer for its integrated coding agents.\n- [Dria](https:\u002F\u002Fdria.co\u002F) - a decentralised AI network. Currently using Rig as part of their [compute node.](https:\u002F\u002Fgithub.com\u002Ffirstbatchxyz\u002Fdkn-compute-node)\n- [Nethermind](https:\u002F\u002Fwww.nethermind.io\u002F) - Using Rig as part of their [Neural Interconnected Nodes Engine](https:\u002F\u002Fgithub.com\u002FNethermindEth\u002Fnine) framework.\n- [Neon](https:\u002F\u002Fneon.com) - Using Rig for their [app.build](https:\u002F\u002Fgithub.com\u002Fneondatabase\u002Fappdotbuild-agent) V2 reboot in Rust.\n- [Listen](https:\u002F\u002Fgithub.com\u002Fpiotrostr\u002Flisten) - A framework aiming to become the go-to framework for AI portfolio management agents. Powers [the Listen app.](https:\u002F\u002Fapp.listen-rs.com\u002F)\n- [Cairnify](https:\u002F\u002Fcairnify.com\u002F) - helps users find documents, links, and information instantly through an intelligent search bar. Rig provides the agentic foundation behind Cairnify’s AI search experience, enabling tool-calling, reasoning, and retrieval workflows.\n- [Ryzome](https:\u002F\u002Fryzome.ai) - Ryzome is a visual AI workspace that lets you build interconnected canvases of thoughts, research, and AI agents to orchestrate complex knowledge work.\n- [deepwiki-rs](https:\u002F\u002Fgithub.com\u002Fsopaco\u002Fdeepwiki-rs) - Turn code into clarity. Generate accurate technical docs and AI-ready context in minutes—perfectly structured for human teams and intelligent agents.\n- [Cortex Memory](https:\u002F\u002Fgithub.com\u002Fsopaco\u002Fcortex-mem) - The production-ready memory system for intelligent agents. A complete solution for memory management, from extraction and vector search to automated optimization, with a REST API, MCP, CLI, and insights dashboard out-of-the-box.\n- [Ironclaw](https:\u002F\u002Fgithub.com\u002Fnearai\u002Fironclaw) - A secure personal AI assistant\n- [ilert](https:\u002F\u002Fwww.ilert.com\u002F) - Incident management & alerting platform. Uses Rig as the multi-provider abstraction in its agentic LLM proxy powering ilert AI.\n\nFor a full list, check out our [ECOSYSTEM.md file.](https:\u002F\u002Fwww.github.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002FECOSYSTEM.md)\n\nAre you also using Rig? [Open an issue](https:\u002F\u002Fwww.github.com\u002F0xPlaygrounds\u002Frig\u002Fissues) to have your name added!\n\n## Get Started\nUse the root `rig` facade when you want feature-gated access to companion crates,\nor use `rig-core` directly when you only need the core provider abstractions.\n\n```bash\ncargo add rig\n# or: cargo add rig-core\n```\n\n### Simple example\n```rust\nuse rig::client::{CompletionClient, ProviderClient};\nuse rig::completion::Prompt;\nuse rig::providers::openai;\n\n#[tokio::main]\nasync fn main() -> Result\u003C(), anyhow::Error> {\n    \u002F\u002F Create OpenAI client\n    let client = openai::Client::from_env();\n\n    \u002F\u002F Create agent with a single context prompt\n    let comedian_agent = client\n        .agent(openai::GPT_5_2)\n        .preamble(\"You are a comedian here to entertain the user using humour and jokes.\")\n        .build();\n\n    \u002F\u002F Prompt the agent and print the response\n    let response = comedian_agent.prompt(\"Entertain me!\").await?;\n\n    println!(\"{response}\");\n\n    Ok(())\n}\n```\nNote using `#[tokio::main]` requires you enable tokio's `macros` and `rt-multi-thread` features\nor just `full` to enable all features (`cargo add tokio --features macros,rt-multi-thread`).\n\nYou can find more examples in each crate's `examples` directory (for example, [`examples`](.\u002Fexamples)). Many provider-specific examples now also live as ignored live integration tests under [`tests\u002Fproviders`](.\u002Ftests\u002Fproviders), organized by provider. When running those provider-backed tests, prefer provider-specific targets such as `cargo test -p rig --test openai -- --ignored --test-threads=1` to avoid rate-limiting. More detailed use case walkthroughs are regularly published on our [Dev.to Blog](https:\u002F\u002Fdev.to\u002F0thtachi) and added to Rig's official documentation at [docs.rig.rs](https:\u002F\u002Fdocs.rig.rs).\n\n## Supported Integrations\n\nVector stores are available as separate companion-crates:\n- MongoDB: [`rig-mongodb`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-mongodb)\n- LanceDB: [`rig-lancedb`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-lancedb)\n- Neo4j: [`rig-neo4j`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-neo4j)\n- Qdrant: [`rig-qdrant`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-qdrant)\n- SQLite: [`rig-sqlite`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-sqlite)\n- SurrealDB: [`rig-surrealdb`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-surrealdb)\n- Milvus: [`rig-milvus`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-milvus)\n- ScyllaDB: [`rig-scylladb`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-scylladb)\n- AWS S3Vectors: [`rig-s3vectors`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-s3vectors)\n- HelixDB: [`rig-helixdb`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-helixdb)\n- Cloudflare Vectorize: [`rig-vectorize`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-vectorize)\n\nThe following providers are available as separate companion-crates:\n- AWS Bedrock: [`rig-bedrock`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-bedrock)\n- Fastembed: [`rig-fastembed`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-fastembed)\n- Google Gemini gRPC: [`rig-gemini-grpc`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-gemini-grpc)\n- Google Vertex: [`rig-vertexai`](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig\u002Ftree\u002Fmain\u002Fcrates\u002Frig-vertexai)\n\nThe root `rig` facade also exposes these companion crates behind one feature per integration:\n\n```toml\nrig = { version = \"0.36.0\", features = [\"lancedb\", \"fastembed\"] }\n```\n\nAvailable facade features include `bedrock`, `fastembed`, `gemini-grpc`,\n`helixdb`, `lancedb`, `milvus`, `mongodb`, `neo4j`, `postgres`, `qdrant`,\n`s3vectors`, `scylladb`, `sqlite`, `surrealdb`, `vectorize`, and `vertexai`.\nWith those features enabled, use the ergonomic root modules such as\n`rig::lancedb`, `rig::mongodb`, `rig::bedrock`, and `rig::fastembed`.\n\nWe also have some other associated crates that have additional functionality you may find helpful when using Rig:\n- `rig-onchain-kit` - the [Rig Onchain Kit.](https:\u002F\u002Fgithub.com\u002F0xPlaygrounds\u002Frig-onchain-kit) Intended to make interactions between Solana\u002FEVM and Rig much easier to implement.\n\n\n\u003Cp align=\"center\">\n\u003Cbr>\n\u003Cbr>\n\u003Cimg src=\"img\u002Fbuilt-by-playgrounds.svg\" alt=\"Build by Playgrounds\" width=\"30%\">\n\u003C\u002Fp>\n","Rig 是一个用于构建模块化和可扩展的大规模语言模型（LLM）应用程序的 Rust 库。其核心功能包括支持多轮对话流、与 20 多个模型提供商及 10 多种向量存储集成，并提供统一接口，简化了 LLM 在应用程序中的集成过程。此外，Rig 还完全符合 GenAI 语义规范，支持文本生成、嵌入、转录、音频和图像生成等多种模型能力。适用于需要高效处理自然语言处理任务并追求高性能与可维护性的开发场景。",2,"2026-06-11 03:04:13","top_language"]