Skip to content
Agent Search Engine.

Open source · Rust

Best Rust AI agents

The 12 open-source AI agents written in Rust in this index, ordered by recorded GitHub star count, never by sponsorship. Stars are repository-interest signals, not performance or maintenance guarantees. Zed leads the set at 95,142 GitHub stars, and 11 of the 12 have a recorded repository push in the last 90 days. These records have Rust as their primary repository language and recognized open-source software licenses recorded in this index; check the current licenses, deployment requirements, and model or API costs. Right now it's led by Zed (95k stars), with openinterpreter and goose following. Order follows the recorded star counts; repository activity is shown separately.

12 open-source records · the full index · more best-of lists · how we rank

Tools in this collection

ZedAgentA high-performance, multiplayer code editor with AI agent features, from the creators of Atom and Tree-sitter.Costs not checkedOpen sourceRust · recorded license: GPL-3.0-or-laterRecord checked · Recent push 95kGitHub starsopeninterpreterAgentA lightweight coding agent for open models like Deepseek, Kimi, and QwenCosts not checkedOpen sourceRust · recorded license: Apache-2.0Record checked · Recent push 69kGitHub starsgooseAgentan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLMCosts not checkedOpen sourceRust · recorded license: Apache-2.0Record checked · Recent push 57kGitHub starsjcodeAgentCoding Agent HarnessCosts not checkedOpen sourceRust · recorded license: MITRecord checked · Recent push 22kGitHub starsWindmillPlatformAn open-source developer platform that turns scripts into webhooks, workflows and internal UIs.Costs not checkedOpen sourceRust · recorded license: AGPL-3.0Record checked · Recent push 19kGitHub starsagentgatewayInfrastructureAn open-source Rust proxy for agent-to-LLM, agent-to-tool (MCP) and agent-to-agent (A2A) traffic.Costs not checkedOpen sourceRust · recorded license: Apache-2.0Record checked · Recent push 6.2kGitHub starsRMCP: MCP Rust SDK (official)SDK / libraryThe official Rust SDK for MCP, built on the tokio async runtime.Costs not checkedOpen sourceRust · recorded license: MIT AND Apache-2.0Record checked · Recent push 4.1kGitHub starsmoltisAgentA secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools.Costs not checkedOpen sourceRust · recorded license: MITRecord checked · Recent push 3.0kGitHub starszerostackAgentLightweight coding agent written in Rust, optimized for memory footprint and performanceCosts not checkedOpen sourceRust · recorded license: GPL-3.0Record checked · Recent push 1.8kGitHub starsrustpbxInfrastructureA PBX written by rustCosts not checkedOpen sourceRust · recorded license: MITRecord checked · Recent push 845GitHub starsechokit_serverPlatformOpen Source Voice Agent PlatformCosts not checkedOpen sourceRust · recorded license: GPL-3.0Record checked 591GitHub starsxybridSDK / libraryBuild apps powered by on-device AICosts not checkedOpen sourceRust · recorded license: Apache-2.0Record checked · Recent push 524GitHub stars

Frequently asked

What are the best Rust AI agents?
By recorded GitHub star count, Zed, openinterpreter and goose lead the Rust AI agents in this index of 12. The full list is below; star count does not prove suitability or continued maintenance. Sponsorship does not affect its order.
Are these Rust AI agents open source and free?
These records have recognized open-source software licenses recorded and are written primarily in Rust in this index. Apache-2.0 is the most common licence here, on 4 of 12, across 6 licences in total. Check each license and deployment requirements. Hosting, model, API, and managed-service costs may apply.
Why choose Rust AI agents specifically?
Staying in your team's primary language — Rust — can help your team inspect and modify code it understands. Repository language does not establish supported user languages, SDKs or an offline deployment. 11 of these 12 have a recorded push within 90 days. A quiet repository alone does not establish whether the project is complete, supported or abandoned.