📦hydro-project / infinity
← 返回首页
An agent runtime and tool protocol for principled agent concurrency
⚖️ Apache-2.0#agents#concurrency#distributed-systems#rust🌐 infinity.hydro.run📅 创建于 2026-04-13🔄 更新于 2026-10-29

📄 仓库 README

在 GitHub 查看 ↗
来自 GitHub 仓库自述文件 · 版权归原作者所有

Infinity

Infinity is a Rust framework for building massively concurrent agentic systems, light enough to fit 75k agents in the memory of a Raspberry Pi. Infinity does for agents what async did for threads: instead of blocking on slow tools, Infinity agents run them concurrently, yield while they wait, and cost nothing until the next event arrives.

let system = AgentSystemBuilder::new_local(
    InMemoryConversationStore::new(),
    InMemoryStateStore::new(),
    StaticModel::new(provider, "global.anthropic.claude-sonnet-4-6").await?,
)
.start();

let mut thread = system.thread_builder().launch().await;
thread.send_user_text("Write a haiku about Rust").await?;

while let Some(event) = thread.recv().await {
    println!("{event:?}");
}

Between turns, an agent is pure data, just its conversation history with no task, no stack, and no open connection, so a waiting agent hibernates for free and wakes on the next message. The same agent code runs unchanged in a resident process on your laptop and on serverless platforms like AWS Lambda, where scale to zero is the default.

Get started today at infinity.hydro.run!

Learn More

  • Infinity Runtime: Build your first agent with the quickstart, see how yielding turns and hibernation work in the architecture guide, and deploy on AWS Lambda with the included CDK constructs.

  • Reactive Agent Protocol (RAP): Serve tools over the network without holding a connection open: results and subscription events are delivered whenever they are ready, even to agents that currently have no process at all. Existing MCP servers run unchanged through a compatibility layer, and anyone can implement the open specification.

  • Infinity Code: A coding agent built on the runtime for concurrent work: it runs builds and tests in the background while their output streams in, edits in parallel threads with stacked sandboxes, and hands you each result as a diff to review.

📈 近 7 天 Star 趋势

每日新增 Star(柱)与累计 Star(线)· 数据来自 GitHub

🏆 排名变化趋势

在各榜单中的排名历史(数字越小越靠前)

📋 历史上榜记录

每次快照的详细数据
日期 榜单 排名 周期新增 总 STAR