# 0xPlaygrounds/rig

⚙️🦀 Build modular and scalable LLM Applications in Rust

Repository: https://github.com/0xPlaygrounds/rig
Canonical: https://ross.abutalabs.com/products/rig
Homepage: https://rig.rs
Language: Rust
License: MIT
License Family: permissive
Topics: ai, llm, agent, artificial-intelligence, automation, large-language-model, rust, scalable-ai, generative-ai, llmops
Last push: 2026-08-25T04:12:59+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 86, longevity 58
- inputs: {"age_days": 819, "days_push": 8, "days_rel": 16, "gap_med": 0.0, "n_releases_24m": 633}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8415, forks 938 (observed 2026-08-28T04:10:21.024141+00:00)

## What it is
Rig is a Rust library for building modular, scalable LLM-powered applications and agents, offering a unified API across 20+ model providers plus tools, RAG, memory, and structured output. It compiles to a single binary or WASM and integrates with vector stores via companion crates like rig-mongodb and rig-qdrant.

## Use cases
- build ai agents in rust
- call llm providers through one unified api
- build a rag pipeline with vector store retrieval
- give an llm type-safe tool calling
- extract structured output from llm responses
- run local models via ollama
- stream multi-turn chat completions
- deploy an llm app as a single rust binary

## When to choose
- your codebase is already Rust and you want AI features without switching stacks
- you need provider-agnostic LLM access with easy backend swapping
- you want compile-time type safety for tool arguments and structured outputs
- you need native performance for orchestration, retrieval, and concurrency
- you want to deploy to edge or browser via WASM

## When to avoid
- you need fine-tuning or model training capabilities
- you want automatic retries and rate-limit handling out of the box
- your team works primarily in Python and prefers LangChain-style ecosystems
- you need a fully stable API - the project warns of frequent breaking changes

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, llm-inference, rag, http-client, sdk
- domain: large-language-models, machine-learning, developer-tools
- platform: rust, cross-platform, wasm, cli
- tags: llm-orchestration, multi-provider, type-safe-tools, vector-store-integrations, structured-output, opentelemetry-genai, ai-agents, retrieval-augmented-generation

## Member repositories
- 0xPlaygrounds/rig (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:21.024141+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:27:17.584987+00:00, confidence not recorded.
  - readme: https://github.com/0xPlaygrounds/rig (fetched 2026-08-28T04:10:21.024141+00:00, sha bda96e8ae42e)
  - homepage: https://rig.rs (fetched 2026-08-29T08:27:17.702840+00:00, sha 9bb810e66f1c)
  - site_page: https://rig.rs/docs (fetched 2026-08-29T08:27:17.712330+00:00, sha 27a3133f6ea4)
  - site_page: https://rig.rs/docs/quickstart (fetched 2026-08-29T08:27:17.714561+00:00, sha ee9ca16545ab)
  - site_page: https://rig.rs/docs/integrations (fetched 2026-08-29T08:27:17.716604+00:00, sha 1df657776df4)
  - site_page: https://rig.rs/docs/concepts (fetched 2026-08-29T08:27:17.718680+00:00, sha 1a013cc1113d)
  - site_page: https://rig.rs/docs/examples (fetched 2026-08-29T08:27:17.720902+00:00, sha 3268efd68695)
  - site_page: https://rig.rs/docs/faq (fetched 2026-08-29T08:27:17.723225+00:00, sha 9604e9d94390)
  - site_page: https://rig.rs/docs/how_to_contribute (fetched 2026-08-29T08:27:17.725393+00:00, sha c8289424eb5e)
  - registry_crates: https://crates.io/api/v1/crates/rig (fetched 2026-08-29T08:27:17.727164+00:00, sha 18562234bea4)
- Data as of 2026-08-30T08:39:29.467469+00:00.