Products
Everruns is a durable runtime for AI agents — and a growing ecosystem of open-source tools built on top of it. Everything here is MIT-licensed and runs inside your own infrastructure.
Products
Durable infrastructure for building, running, and shipping AI agents.
The headless, durable agentic harness engine. Define agents and tools, compose them into reusable harnesses, and ship them to Slack, web chat, scheduled jobs, webhooks, or a plain HTTP API.
The fully managed edition of the Everruns platform — hosted server, database, and workers, with teams and sign-in built in. In development; join the launch list.
The Rust + PostgreSQL durable execution engine that powers the platform — embeddable in-process so a single binary can run durable agents with no external services.
Official client libraries for the Everruns API — typed, async SDKs for Rust, Python, and TypeScript with a consistent surface across languages.
Experimental terminal coding agent built on the Everruns Runtime. One binary that plans, edits, runs, and verifies code in your repository — autonomous by default.
Open-source toolkits
Composable libraries that power Everruns agents — usable on their own in any stack.
A virtual Bash interpreter with an in-process virtual filesystem — a sandbox for running untrusted scripts from AI agents and users, with no containers or subprocesses.
AI-friendly web fetching: turn URLs into clean, LLM-ready Markdown. Available as a CLI, an MCP server, and a library, with SSRF protection built in.
