# anthropics/claude-code-action

> A GitHub Action that runs Claude Code on PRs and issues: answers questions, reviews code, and implements changes triggered by @claude mentions or explicit prompts. Supports Anthropic API, Bedrock, Vertex AI, and Microsoft Foundry.

- Magnitude: 2.5 out of 10 — Steady
- Stars: 8,970 total · +20 stars today, ≈ 33 by evening
- Star trust: star growth looks organic
- Category: AI agents · Language: TypeScript · License: MIT · Created: 2025-05-19 · Last push: 2026-09-25
- GitHub: https://github.com/anthropics/claude-code-action · Page: https://gitnova.dev/en/r/anthropics/claude-code-action

## Useful for

- Set up automatic PR review that analyzes changes and suggests improvements
- Trigger simple fixes and refactoring by mentioning @claude in an issue
- Automate issue triage and labeling via a custom prompt

## Why it’s here

- 20 stars so far today, about 33 expected by the end of the day. The usual pace is 9 per day, so that's 3.9× as much.
- Over the last two days the pace is 2.9× that of the previous week and a half.
- GitHub Trending today: #12, +15 stars.
- GitHub Trending TypeScript today: #4, +15 stars.
- Recent forks include notable developers: @ovr (653 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 2,155
- Issues and pull requests: 1,779
- Watchers: 52
- Average over the last week: 12 per day
- Usual pace: 9 per day
- Stars in the last hour (measured): 10
- Latest release: v1 (2025-08-26)

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-08-28 … 2026-09-26: 6, 9, 6, 5, 10, 7, 4, 7, 6, 6, 11, 7, 11, 7, 14, 6, 7, 12, 9, 10, 6, 9, 4, 8, 5, 9, 9, 5, 14, 20

## Spotted in now

- GitHub Trending today: #12, +15 stars
- GitHub Trending TypeScript today: #4, +15 stars

## More in this category

1. **paperclipai/paperclip** — 8.9 · Breakout · AI agents · TypeScript · +548 stars today, ≈ 1,393 by evening
   Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage them like employees.
   Full card: https://gitnova.dev/en/r/paperclipai/paperclip.md
2. **vectorize-io/hindsight** — 8.5 · Breakout · AI agents · Python · +442 stars today, ≈ 1,134 by evening
   Hindsight is a long-term memory system for AI agents that stores facts and observations rather than just conversation history, reporting state-of-the-art results on the LongMemEval benchmark. It runs as a server (Docker, pip, Helm) or…
   Full card: https://gitnova.dev/en/r/vectorize-io/hindsight.md
3. **google/ax** — 6.9 · Peaking · AI agents · Go · +120 stars today, ≈ 382 by evening
   A declarative orchestrator for running autonomous AI agent workloads in a cluster, using a Kubernetes-like model with Task, Workspace, Gateway, and Model manifests. It sandboxes agents, pre-wires their environment, and restricts network…
   Full card: https://gitnova.dev/en/r/google/ax.md
4. **supermemoryai/company-brain** — 6.6 · Early signal · AI agents · TypeScript · +129 stars today, ≈ 231 by evening
   Open-source version of a company brain for Slack: it remembers team conversations, answers from them, and performs tasks in connected tools (GitHub, Linear, Notion, etc.). Runs on your own Cloudflare account.
   Full card: https://gitnova.dev/en/r/supermemoryai/company-brain.md
5. **androoAGI/starnet** — 6.4 · Early signal · AI agents · JavaScript · +40 stars today, ≈ 127 by evening
   A local-first desktop app where AI agents do real work with real models and tools, and a pixel-art station projects live runtime state. Lets you create teams of agents with distinct permissions and run them concurrently.
   Full card: https://gitnova.dev/en/r/androoAGI/starnet.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-26 12:21 UTC, updated every 30 minutes.