Agentic Blueprints 14
Filtersactive
E2E Test Author
Turns a user story into browser tests: plans the scenarios, writes Playwright code, runs it against the real page, and self-heals until it passes for the right reason.
Code Reviewer
Diff-aware multi-pass reviewer: finds bugs, then a skeptic agent verifies each before reporting.
Bug Reproducer
Reads a GitHub issue and loops a coder against a verifier until it produces a minimal failing test that actually reproduces the bug.
Repo Q&A
Answers questions about a codebase with citations to the exact file — and says so honestly when the answer isn't in the repo.
Flaky Test Triage
A scheduled sweep of CI history clusters intermittent failures, decides flake vs. real regression, and branches: quarantine or escalate.
Docs Drift Sync
Watches merged changes for the ones that make your docs wrong, drafts the fix, and opens a documentation PR — reviewed before it lands.
Release Notes Writer
Reads every PR merged since your last tag, groups them by theme, and writes human release notes ready to post.

Gitty
A CLI multi-agent tool that reads your GitHub issues and PRs and drafts the mundane replies so maintainers keep their focus.

Code-Execution Group Chat
An assistant writes code and an executor agent runs it in the same chat, feeding real output back until the task is solved.

Multimodal Coding Agent Team
A coding team that accepts images too: a vision agent reads screenshots of problems, a coding agent solves them with live code execution.

Code Assistant with Self-Correction
Generates code grounded in docs, executes it, and loops on the errors — reflecting on failures before retrying until tests pass.

USACO Competitive Programming Agent
Solves olympiad programming problems with episodic retrieval of similar solved problems plus a reflect-and-retry execution loop.
