rig vs adk-rust
Rust LLM building blocks compared with an agent framework
rig and adk-rust are Rust projects for building applications with language models and agents. rig centers on shared interfaces for providers, vector stores, and composable LLM workflows, while adk-rust offers broader agent orchestration and service capabilities, including memory, HTTP serving, and real-time voice.
rig: Build LLM Applications in Rust
Rig is a Rust library for building modular LLM applications, with shared interfaces for model providers, vector stores, and agent workflows. It suits Rust developers who want to integrate multiple LLM services without building each integration from scratch.
adk-rust: Build AI Agents with Rust
ADK-Rust is a modular framework for building and deploying asynchronous AI agents in Rust. It supports multiple model providers, tools, workflows, memory, and real-time voice, with composable crates for projects ranging from prototypes to production services.
| rig | adk-rust | |
|---|---|---|
| Language | Rust | Rust |
| License | MIT | NOASSERTION |
| Stars | 8.8k | 690 |
| Forks | 989 | 108 |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- rig emphasizes portable core contracts and shared interfaces across more than 20 model providers and more than 10 vector store integrations; adk-rust organizes capabilities across modular crates and tiered features.
- rig covers completion, embeddings, agent workflows, and supported audio and image capabilities; adk-rust focuses on agent orchestration, including teams, graph workflows, typed tools, and session handling.
- adk-rust lists HTTP serving, evaluation, guardrails, authentication, and OpenTelemetry; rig's listed focus is LLM components and integrations.
- rig is licensed MIT; adk-rust's repository metadata reports NOASSERTION, while its README states Apache 2.0, so its license terms should be verified.
- The supplied metadata lists rig at 8.8k stars and 989 forks, compared with adk-rust at 690 stars and 108 forks; both are marked as not archived.
Choose rig if you…
- need shared Rust interfaces for model providers and vector stores.
- want composable completion, embedding, and agent workflows without starting each integration from scratch.
- need a portable core with Browser-WASM support, within the stated runtime limitations.
Choose adk-rust if you…
- want typed, asynchronous agent infrastructure with sequential, parallel, team, or graph workflows.
- need agent capabilities such as session storage, long-term memory, HTTP serving, or observability.
- are building a real-time voice agent or want to select capabilities through separate crates and optional features.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.