ADK-Rust

A production-ready Rust framework for building AI agents. Model-agnostic, type-safe and async, across 43 publishable crates for agent orchestration.

v2.2.0 Released! This API-compatible minor release completes the Gemini Enterprise Agent Platform consumption path: the Gen AI Evaluation Service bridge, Vertex AI RAG Engine retrieval and grounding, an Agent Retrieval vector store, Agent Registry discovery and registration, Skill Registry consumption with remote skill loading, and remote ReasoningEngine agents you can call as sub-agents — every one opt-in and composable with any preset, and all appended to gemini-agent-platform. Graph workflows gain native tool confirmation pauses. Tracing is fixed so one invocation exports as one trace rather than several disconnected ones. All 43 crates are available on crates.io.

Milestone: ADK-Rust has crossed 500K total crates.io downloads across the workspace crates.

Coming from 1.x: six APIs changed shape and the fan-in default changed behaviour without an API change. See the migration guide and the CHANGELOG.

🎬 Rust & Beyond Podcast — Episode 3: Agents That Act

ADK-Rust v2.0.0 — Agents That Act. Eight chapters on agents that run on their own and finish what they start: a workflow that resumes exactly where it stopped, a graph that changes course when the problem does, and approvals you can trust down to the digest. 42 crates, 4,300+ tests, sub-millisecond loop overhead.

▶️ Watch on YouTube — 40 min 50 sec · Hosts: James (Fenrir) & Ada (Kore) · Video with slides

"Show me." — Ada, thirty seconds in, declining to be told about the visual builder

Previous episodes

🎧 Episode 2: v1.0.0 — The Stable Foundation

A deep-dive into what shipped, who built it, and where it was going. 39 crates. 130K downloads. Semver stable.

▶️ Watch on YouTube — 10 min 12 sec · Hosts: James (Fenrir) & Ada (Kore)

"We believe the next generation of software will be built by composing autonomous agents, not by writing every line of logic by hand. And we believe Rust is the right language for the runtime those agents live in." — James

🎧 Episode 1: What is ADK-Rust?

2 min 21 sec · Generated entirely by ADK-Rust using Gemini 3.1 Flash TTS

# Episode 3 assets
docs/podcast/episode-3-script.md      # Full script, eight chapters
docs/podcast/episode-3-slides.md      # Marp slide deck
docs/podcast/adk-rust-episode-3.mp4   # Final video
docs/podcast/episode-3-narration.mp3  # Audio-only

Build and test an agent in five minutes

Scaffold an OpenAI agent with the HTTP runtime and embedded UI:

cargo install cargo-adk
cargo adk new quickstart_agent --template api --provider openai
cd quickstart_agent
cp .env.example .env
# Open .env and replace the OPENAI_API_KEY placeholder, then:
cargo run

Open http://127.0.0.1:8080/ui/, enter a prompt, and press Enter. The UI creates the session, streams the run, renders Markdown and tool results, animates the active agent or workflow edge, and keeps the event timeline, state, artifacts, and telemetry beside the conversation.

The animation uses the richer team showcase so the topology is visible; the single-agent project you just generated uses the same UI with a one-node graph. Confirm the server independently with:

curl -fsS http://127.0.0.1:8080/api/health

The five-minute quickstart explains the generated files and the console-only alternative. The runnable runtime_ui_showcase reproduces the UI above with tool, graph, and team agents.

Add ADK-Rust to an existing project

[dependencies]
adk-rust = "2.2.0"                                        # Gemini, agents, runner, sessions
# adk-rust = { version = "2.2.0", features = ["standard"] }  # + server, auth, graph, eval

A tier is a starting point, not a ceiling. Add any single capability on top of one without moving to the next tier, so features = ["minimal", "audio"] gives you the minimal build plus audio. AGENTS.md lists every feature you can add this way.

One agent, end to end

use adk_rust::prelude::*;
use adk_rust::Launcher;

#[tokio::main]
async fn main() -> AnyhowResult<()> {
    dotenvy::dotenv().ok();
    let model = GeminiModel::new(&std::env::var("GOOGLE_API_KEY")?, "gemini-3.7-flash")?;

    let agent = LlmAgentBuilder::new("assistant")
        .instruction("You are a helpful assistant. Be concise and accurate.")
        .model(Arc::new(model))
        .build()?;

    Launcher::new(Arc::new(agent)).run().await?;
    Ok(())
}

Swap the provider by swapping the client. The agent, runner and tools are unchanged:

Or let it choose: adk_rust::run(instructions, input) picks a provider from the environment, among those you compiled in.

Models

Defaults are curated in adk_model::catalog and were checked on 23 August 2026. Deployment-scoped providers such as Bedrock and Azure AI still require the model or deployment identifier available in your own account and region.

Use adk_model::catalog::recommended_model(provider) for ADK's portable default, MODEL_CATALOG for user-facing pickers, and validate_model_selection when accepting configuration. Unknown IDs remain valid for private deployments and new releases; known retired IDs include an actionable replacement.

What you can build

Each row links to its guide and a runnable example.

Scaffold a project

cargo install cargo-adk

cargo adk new my-agent                       # basic Gemini agent (alias for --template llm)
cargo adk new my-agent --template tools      # agent with #[tool] custom tools
cargo adk new my-agent --template rag        # RAG with vector search
cargo adk new my-agent --template api        # REST server
cargo adk new my-agent --template graph      # graph workflow with checkpoints
cargo adk new my-agent --template realtime   # realtime voice agent
cargo adk new my-agent --template agent-engine # Gemini Enterprise Agent Engine BYOC

# Compose addons with any template
cargo adk new my-agent --template tools --addon telemetry --addon sessions
cargo adk new my-agent --addon mcp --addon guardrails

cd my-agent
cp .env.example .env    # add your API key
cargo run

Agent types — the core agent structure.

Enterprise patterns — pre-composed, several capabilities already wired together.

Addons — composable with any template, and with each other.

cargo adk build compiles the project without deploying, and cargo adk validate checks an agent definition without building. cargo adk templates and cargo adk addons print these lists.

Crates

Extracted to standalone repos: adk-ui (dynamic UI generation), adk-studio (visual agent builder), adk-playground (120+ examples).

Performance

Measured with cargo adk bench against gemini-2.5-flash, same workload and prompt for every framework.

Cold start is process launch to first API call. Overhead is turn time minus the LLM round trip. Apple M-series, macOS, June 2026. Run it yourself with cargo adk bench --dry-run to see the cost estimate first.

Develop

devenv shell            # reproducible toolchain, or ./scripts/setup-dev.sh
make build              # cargo build --workspace
make test               # cargo nextest run --workspace
make clippy             # -D warnings

AGENTS.md documents the conventions CI enforces, including the per-platform tool matrix and the CI cost tiers. CONTRIBUTING.md covers the workflow and the required checks.

Documentation

• Official docs — guides for every capability above
• Wiki — tutorials and quickstarts
• docs.rs — API reference
• Examples — 110 standalone crates, plus 120+ in the playground

Companion projects

Project

• ROADMAP.md — v2.2.0 (current). Longer-term direction and why both orchestration APIs are supported
• CHANGELOG.md — every release
• CONTRIBUTORS.md — the people who built this
• STABILITY.md — crate stability tiers and the deprecation policy
• Discussions — ideas and questions

Related: Google's ADK · MCP · Gemini API

Sponsors

ADK-Rust is Apache 2.0 and developed in the open. Sponsorship pays for the CI minutes, model-provider credits, and benchmark hardware the project runs on.

Thank you to our sponsors:

Become a sponsor — monthly tiers from $5, or a one-off contribution. Sponsors are listed here and on the sponsors page.

Star History

License

Apache 2.0. See LICENSE.