nanocodex logo

nanocodex

Free

Building blocks for frontier OpenAI agents in Rust. Nanocodex empowers you with Codex-level performance anywhere.

Visit Website

At a glance

Explore the listed capabilities, then check the details that matter to you.

  • Build agents with owned lifecycles
  • Keep cloneable agent handles
  • Await typed turn results
ai-agentaiai-agentsanthropicchatgptai assistantautomation
nanocodex screenshot 1

Overview

Nanocodex is a Rust crate that serves as the batteries-included façade for the Nanocodex frontier-agent building blocks. It contains no second runtime implementation; instead, it re-exports the owned agent lifecycle and gives lower-level crates stable, named module paths. Depending on nanocodex-agent directly creates the same agent. The crate provides a quick start for building one owned agent, keeping its cheap cloneable handle, and awaiting typed turn results. It supports OpenAI and, when the claude feature is enabled, Anthropic Messages with the same owned agent lifecycle and durability extension. Default features remain durability, mcp, openai, and tools. The root exports only golden-path types, while named modules offer more control for embedding needs. Harness composes explicitly registered construction recipes. When the provider reports aggregate usage for a completed turn, Nanocodex automatically applies the selected model’s published standard or priority rates.

Pricing

Free

Detailed plans have not been confirmed in our catalog. Check the official website for current limits and billing terms.

Visit Website

Prices and limits may change. Confirm the currency, billing period, seat minimum and usage caps on the official website.

Use Cases

  • Developers use nanocodex to build one owned agent, keep its cheap cloneable handle, and await typed turn results.
  • Developers use nanocodex to enable Anthropic Messages with the same owned agent lifecycle and durability extension.
  • Developers use nanocodex to compose explicitly registered construction recipes for native harnesses.
  • Developers use nanocodex to automatically apply the selected model’s published standard or priority rates for cost estimates.
  • Developers use nanocodex to reach named modules when an embedding needs more control.
  • Developers use nanocodex to rely on default features durability, mcp, openai, and tools.

Features

Build agents with owned lifecycles

Keep cloneable agent handles

Await typed turn results

Extend agent durability

Use tools through agent defaults

Compose registered construction recipes

Access named modules for embedding

Reviews

No reviews yet. Be the first to share your experience!