Updated daily · last run Nov 20, 07:02 UTC
Trending in the bucket
Every AI dev tool the internet posted about, ranked by who's talking about it. Sorted. Mostly.
- In the bucket
- 3.1K
- Posts read
- 42.7K
- Tossed out
- 33.7K
23 tools, ranked by sources, chatter and star growth. How ranking works
- 01
#1
Skill and CLI for coding agents that generates browser review reports from a branch, with tests, UI screenshots and database change views.
HN#claude-code#codex#cursor1 post · 3 days ago★ 115
Stars:115
- 02
#2
Claude Code plugin running parallel AI testers on iOS simulators and Android emulators via GitHub Actions, producing bug reports with screen
GH#claude-code#plugin#github-action1 post · 5 days ago★ 47
Stars:47
- 03
#3
CLI that captures coding agent corrections as ast-grep, Vale, or runtime rules enforced across editors, agents, and CI.
HN#claude-code#cursor#opencode1 post · 6 days ago★ 118
Stars:118
- 04
#4
Offline diff reviewer that catches weakened tests, loosened assertions and lowered coverage, and sends coding agents back to fix the code.
HN#claude-code#codex#cursor2 posts · 9 days ago★ 11
Stars:11
- 05
#5
MIT-licensed skill adding an evidence-based code review workflow for Codex and Claude Code.
GH#claude-code#codex#plugin2 posts · 23 days ago★ 93 +4/wk
Stars:93
+4 this week
- 06
#6
Unity Editor performance profiling agent that captures frames, generates rule-based findings with evidence chains, and offers optional LLM a
GH#any-model#mcp-server#plugin1 post · Oct 3★ 13
Stars:13
- 07
#7
Claude Code plugin and CLI that model-checks stateful code by exploring reachable states and flagging rule violations with counterexample pa
HN#claude-code#cli#plugin1 post · Jul 15★ 14
Stars:14
- 08
#8
Self-hosted code review tool for local git repos; reviews uncommitted AI agent work via desktop app, browser, or MCP server.
GHHN#claude-code#codex#gemini-cli2 posts · Sep 15★ 18
Stars:18
- 09
#9
Open-source AI-first browser testing and automation platform with Playwright runners, MCP server, and Claude/Codex plugins.
HN#claude-code#codex#mcp-server1 post · Sep 12★ 50
Stars:50
- 10#10
macOS app that shows a PR's blast radius as user journeys and runs Claude Code reviews on the change.
HN#claude-code#macos#desktop-app1 post · Sep 28
no public repo
- 11
#11
CLI audit protocol with 20 adversarial passes and a false-positive verifier for auditing AI-written code via any coding agent.
GH#any-agent#cli#plugin1 post · Aug 23★ 40
Stars:40
- 12
#12
A Claude Code plugin that runs a read-only production-readiness audit with eight specialist lenses and a go/no-go verdict.
GH#claude-code#codex#opencode1 post · Aug 29★ 29
Stars:29
- 13
#13
Python tool that captures browser state, diffs UI versions, and runs deterministic layout and axe-core accessibility checks with optional LL
HN#claude-code#cursor#openai1 post · Aug 23★ 17
Stars:17
- 14
#14
Open-source AI code review plugin that posts reviews and one fix commit directly on GitHub, GitLab and Bitbucket PRs via coding agent CLIs.
GH#claude-code#cursor#codex1 post · Jul 14★ 43
Stars:43
- 15
#15
Supervises multi-agent code review by running claude and codex CLI subprocesses and returning structured, auditable findings.
GH#claude-code#codex#cli1 post · Jul 26★ 99
Stars:99
- 16
#16
Skills for coding agents that run two-model debate reviews of PRs/MRs and work review rounds until merge-ready.
GH#any-agent#claude#openai1 post · Aug 21★ 135
Stars:135
- 17
#17
An agent skill that runs risk-first PR/branch code review with fixed passes: risk triage, agent-authored checks, call-graph pincer, and stru
GH#plugin#any-agent1 post · Jul 25★ 18
Stars:18
- 18
#18
Static analysis for PHP that catches debt AI agents introduce, with Claude Code hooks, git-diff review, CI gating and an MCP server.
GH#claude-code#any-agent#mcp-server1 post · Sep 10★ 157
Stars:157
- 19
#19
Local AI tool that prioritizes and explains coding-agent PR changes (P0/P1/P2) via a Chrome extension on GitHub's Files changed page.
HN#openai#any-agent#cli1 post · Sep 25★ 148
Stars:148
- 20
#20
Adversarial verification skill for coding agents that tests whether a delivered change actually works and reports a READY/NOT READY verdict.
GH#any-agent#plugin1 post · Aug 15★ 10
Stars:10
- 21
#21
Local Windows connector that lets RealPLC AI generate, validate, diagnose and fix PLC programs in CODESYS and TIA Portal.
Stars:33
- 22
#22
Codex skill that breaks AI-written code into explained functional blocks and verifies goals against recorded evidence, generating HTML/Markd
Stars:134
+1 this week
- 23
#23
CLI and MCP server that visualizes Vivado/Zynq/PYNQ projects and checks clock-domain crossings, constraints and build failures for AI agents
GH#claude-code#codex#gemini-cli1 post · 26 days ago★ 28
Stars:28