Agent Claude Code
Analyze agent execution transcripts — answer questions about tool usage, reasoning, turns, parallel calls, stumbles, and behavior patterns.
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.
This repository also configures its own agents. See what sprout tells them →
Agent Claude Code
Analyze agent execution transcripts — answer questions about tool usage, reasoning, turns, parallel calls, stumbles, and behavior patterns.
Agent Claude Code
Ask to fetch web pages, call REST APIs, or download data from URLs — parses responses and extracts relevant content.
Agent Claude Code
Verify that work is complete by gathering fresh evidence — run tests, check requirements, confirm claims.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: