#3838th of 70 in Agent frameworks and SDKs
rig
Rust library for building LLM agents, plus a Bevy-based terminal coding agent
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 8.9k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Rust
6,640 on 1 Apr 20268,932 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Rig is a Rust library that puts 20+ model providers and 10+ vector stores behind one interface, with agents that support tools, multi-turn streaming and typed hooks. The same repo ships `rig`, a terminal coding agent built as a Bevy app whose tools, commands and sessions are plugins listed in `plugins.toml`. The library is pre-1.0 and releases contain breaking changes.
Who it is for: Rust developers building LLM agents, RAG apps or a terminal coding agent
Strengths
- 20+ model providers and 10+ vector stores behind one interface
- Covers completion, embeddings, transcription, audio and image generation
- Core and agent runtime target browser WASM (wasm32-unknown-unknown)
- OpenTelemetry GenAI conventions and replay of agent effects via rig-cassette
Weaknesses
- Pre-1.0; each release contains breaking changes, so migration notes must be read
- Rust only; the coding agent needs Rust 1.97.1 or newer
- Coding agent runs on Linux and macOS; Windows is not listed
- Integrations are separate crates enabled by feature flags, adding setup steps
What it needs
- GPU optional
- Needs Rust 1.97.1+, tokio, LLM provider API key
- Models: OpenAI, AWS Bedrock, Google Vertex AI, Google Gemini gRPC, Candle (local Llama/SmolLM2/Qwen3)
Also in Agent frameworks and SDKs
See all 70| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 94 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 89 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| #4 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 89 out of 100 |
| #5 | mastraTypeScript framework for building AI agents and workflows | 89 out of 100 |