Continuous Claude
run Claude Code in a loop
Details
- External ID
- 45938517
- Source
- HN
- Company
- —
- Product
- Continuous Claude
- Website domain
- github.com
- Launched
- Nov. 15, 2025
- Cohort
- —
- Upvotes
- 170
- Upvotes percentile
- 0.9432314410480349
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
Continuous Claude is a CLI wrapper I made that runs Claude Code in an iterative loop with persistent context, automatically driving a PR-based workflow. Each iteration creates a branch, applies a focused code change, generates a commit, opens a PR via GitHub's CLI, waits for required checks and reviews, merges if green, and records state into a shared notes file.This avoids the typical stateless one-shot pattern of current coding agents and enables multi-step changes without losing intermediate reasoning, test failures, or partial progress.The tool is useful for tasks that require many small, serial modifications: increasing test coverage, large refactors, dependency upgrades guided by release notes, or framework migrations.Blog post about this: https://anandchowdhary.com/blog/2025/running-claude-code-in-...
Enrichment
- Theme
- Claude integrations and coding agents
- Vertical
- Horizontal
- Function
- Agent / copilot
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- run claude code in a loop
- Manually corrected
- False
Could you build this?
Yes This is a straightforward CLI orchestration script that loops over the Claude Code CLI and GitHub CLI (gh) to create branches, commit code, and poll PR status.
Discussion
20 comments analyzed.
Competitors mentioned: Copilot, Claude/Claude Code, ChatGPT Codex
Concerns raised: Test coverage increases without improving actual bug detection, Generated tests don't verify correctness, just print passing results, LLMs struggle with complexity and object-oriented design patterns, High cost when running in continuous loops, API rate limiting and usage throttling on paid plans
Feature requests: Automatic code review integration in CI/CD pipelines, Ability to read and address inline comments iteratively, Better handling of complex refactoring beyond trivial tasks
Competitors
Other products that read as similar to this one — 423 launches clear the similarity bar, closest 8 shown.
Attention rank: #21 of 424 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 9 days after the earliest competitor.
- Decipher x Claude Code · hn · 2026-03-04 · 5 upvotes · similarity 0.55
- Claude Code Scheduler · hn · 2026-01-14 · 7 upvotes · similarity 0.55
- Claude Code Scheduled Tasks · ph · 2026-03-22 · 465 upvotes · similarity 0.54
- Ralphex · hn · 2026-01-28 · 9 upvotes · similarity 0.54
- Claude Code Routines · ph · 2026-04-15 · 599 upvotes · similarity 0.52
- claude-code-github-examples · github · 2026-09-21 · 10 upvotes · similarity 0.52
- CodeYam Memory · hn · 2026-03-04 · 17 upvotes · similarity 0.50
- Claude Code auto-fix · ph · 2026-03-27 · 361 upvotes · similarity 0.50
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.