prime-radiant-inc/sprout

54 stars · Last commit 2026-06-06

Experimental self-improving multi-agent coding system: a root agent recursively decomposes goals and delegates to specialist subagents, learning from failures by mutating a git-backed agent genome. Supports Claude, GPT, and Gemini.

README preview

# 🌱 Sprout

A self-improving, multi-agent AI system that decomposes tasks and delegates to specialist agents. Sprout is an autonomous coding assistant built on a recursive agent architecture — where every action is a goal-directed delegation to a subagent.

## Overview

Sprout operates on a simple but powerful loop:

```
Perceive → Recall → Plan → Act → Verify ─── loop
                                  │
                                  └──→ Learn (async)
```

A **root agent** receives your goal, breaks it into subgoals, and delegates each to a specialist. Specialists can be orchestrators themselves (delegating further) or leaf workers that execute primitives directly. The system learns from its mistakes — stumbles, failures, and inefficiencies are detected and fed into an asynchronous learning pipeline that mutates the agent genome over time.

## Key Concepts

- **Agents all the way down** — Every action is a delegation to a subagent. The root never executes tools directly.
- **Genome** — A git-backed knowledge base storing agent definitions, memories, routing rules, and learned behaviors. Every mutation is committed for full auditability and rollback.

View full repository on GitHub →