Sign in
← Back to search
github Actively maintained

frankbria/ralph-claude-code

Autonomous AI development loop for Claude Code with intelligent exit detection

1 awesome list

Quick read

Stars
9,576
Forks
727
Open issues
28
Commits
299

Activity and growth

Latest capture 2026-08-03 03:02

Stars · last 7 days
No history
Commits · last 7 days
No history
Stars since tracking
+382
Stored snapshots
6

Classification

Topics

#ai #ai-agent #ai-agents #ai-development #ai-development-tools #claude-code #claude-code-cli #development-tools #development-workflow

Metadata

Language
Shell
License
MIT
Default branch
main
Created
2025-08-27
First commit
2025-08-27
Last pushed
2026-07-18
GitHub updated
2026-08-03
Last synced
2026-08-03 03:02
Stack scanned
2026-08-03 03:02
Archived
No
Sign in to like frankbria/ralph-claude-code
README View on GitHub

AI development signals

2 paths

Agent instructions and tool configuration found in this repository.

Agent instructions

Claude Code

View paths

Growth history

Tracked growth

6 observed captures since 2026-05-25. Observed captures are shown by default.

Stars from first capture +382

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

michaelshimeles/ralphy

My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & Droid in a loop until your PRD is complete.

2,969 stars
TypeScript 0 awesome lists

mikeyobrien/ralph-orchestrator

An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration

3,121 stars
Rust 1 awesome list

maxritter/pilot-shell

How real engineers run Claude Code and Codex: spec-driven planning, enforced TDD, persistent memory, and quality enforcement on all levels. Make your agents production-ready.

2,035 stars
JavaScript 1 awesome list

sd0xdev/sd0x-dev-flow

The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. Quality gates that AI can't skip.

187 stars
JavaScript 1 awesome list