Continua provides Wheelie, an open‑source Development OS that gives software teams a unified command‑line interface for integrating LLM agents into their coding workflows. By standardizing integration points, offering one‑click installation, and exposing a JSON‑based API with ready‑made harnesses for providers like Claude and Codex, Wheelie removes setup friction and enables context‑aware, automated code changes that can be validated and submitted through Git.
Funding
$8M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
1OFounders
Product
Problem
Software development teams face fragmented tooling and steep setup overhead when integrating large language model (LLM) agents into coding workflows, leading to slow onboarding and inconsistent automation results.
Solution
Continua offers Wheelie, an open‑source Development OS that streamlines agentic coding by providing a unified command‑line interface, standardized integration points, and ready‑made harnesses for popular LLM providers such as Claude and Codex. Developers can install Wheelie with a single script, authenticate, connect to GitHub repositories, and launch context‑aware coding sessions without manual configuration. The platform supplies machine‑readable command manifests and support‑level metadata, enabling agents to programmatically discover capabilities, validate work locally, and submit changes for review. By abstracting infrastructure details and exposing a consistent JSON‑based API, Wheelie reduces the friction of adopting AI‑driven development and accelerates the delivery of automated code fixes and feature implementations.
Target Audience
Wheelie is aimed at software engineering teams, DevOps engineers, and AI‑product developers who want to embed LLM agents into their coding pipelines and need a reliable, extensible development environment.
Features
- Single‑step installation via script and Homebrew, with automatic path configuration
- Integrated authentication flow supporting multiple providers and GitHub repository linking
- Pre‑built harness projections for LLM backends (e.g., Pi, Claude, Codex) enabling plug‑and‑play model access
- Fast context packing commands that retrieve relevant code and project metadata for agent consumption
- Local work‑item management with Git‑based validation lanes and resource status reporting
- JSON‑structured command output including schema version, support state, and next‑action hints for autonomous agents
- Public command manifest and brand asset schemas for machine‑readable discovery and UI consistency