AnandChowdhary/continuous-claude
🔂 Ralph loop with PRs: Run Claude Code in a continuous loop, autonomously creating PRs, waiting for checks, and merging
Maintains persistent context across loop iterations via a shared markdown file, preventing context drift and enabling self-directed progress toward larger goals. Uses GitHub's native PR workflow (checks, reviews, merging) as the coordination mechanism, treating each Claude Code invocation as an idempotent attempt that either succeeds or fails gracefully. Designed for multi-day tasks like large refactoring, test coverage expansion, or dependency updates where individual iterations build incrementally on prior knowledge.
1,253 stars. Actively maintained with 4 commits in the last 30 days.
Stars
1,253
Forks
88
Language
Shell
License
MIT
Category
Last pushed
Jan 27, 2026
Commits (30d)
4
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/AnandChowdhary/continuous-claude"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related agents
mikeyobrien/ralph-orchestrator
An improved implementation of the Ralph Wiggum technique for autonomous AI agent orchestration
multivmlabs/ralph-starter
Bootstrap projects from Figma, Linear, Notion & GitHub specs. The only AI ralph with source integrations.
alfredolopez80/multi-agent-ralph-loop
Orchestration system for Claude Code with memory-driven planning, multi-agent coordination,...
YW1975/Ralph-Lisa-Loop
Dual-agent AI code review loop — consensus at every step, not after the fact. Used to evolve an...
tzachbon/smart-ralph
Spec-driven development with smart compaction. Claude Code plugin combining Ralph Wiggum loop...