Back to Tool
B

Bello

Tool Oct 20, 2026

An MIT-licensed coding-agent orchestrator with optional supervision, completion review, adversarial checks and context compaction across subscription and API backends.

Visit primary link 2 sources attached
Bello's author chart compares Raw and Smart Execution for Sonnet 5 and Astra, showing lower API-equivalent cost and solution time with slightly lower scores.
Maintainer-reported Smart Execution comparison, three runs per model and setup. Both models show lower API-equivalent costs and shorter solver times alongside slightly lower mean scores. These are small author-run measurements, not an AITrending replication or a guarantee of savings. Source: Makson179 / Bello contributors
agent-ecosystemcoding-agents

What happened lately

Bello timeline

Bello wraps coding tasks in a disposable workspace and returns a patch to the user’s project. A coder can work alongside optional runtime supervision, completion review, an adversary and a local log distiller. Each model role can have its own provider and configuration. Bello is an orchestrator, not a new model or an included inference subscription.

The documented installation is pipx install bello, followed by bello doctor. It requires Python 3.11 or newer and Git. Linux needs bubblewrap; native Windows requires the documented sandbox preparation. Users bring Codex or Claude Code subscriptions or supported API-provider credentials. Claude support requires the claude extra, while the API runtime requires Node.js 22.19 or newer.

Version 0.8.0 adds Goal mode and optional No Need For Context compaction, and enables Smart Execution for new configurations. Native Codex features use a compatible pinned helper rather than replacing the global CLI. Bello’s application code is MIT-licensed; its separately distributed distiller model uses Apache 2.0.