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
11 tools, ranked by sources, chatter and star growth. How ranking works
- 01
#1
Open-source AI code review agent that runs /review, /improve and /describe commands on pull requests across major git providers.
GH#github-action#cli#any-model1 post · 16 days ago★ 16.5K +336/wk
Stars:16.5K
+336 this week
- 02
#2
Self-hosted open-source GitHub App that runs AI agents to review pull requests for bugs, security issues, and repo guideline violations.
Stars:39
- 03
#3
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
- 04
#4
Self-hosted GitHub PR review bot that reviews pull requests with inline findings and structured summaries using your own Codex or Claude sub
HN#self-hosted#github-action#codex1 post · Jul 14★ 14
Stars:14
- 05
#5
Open-source CLI that runs AI security-review agents on a repository, validates findings, and keeps results in a local SQLite ledger.
HN#any-model#cli#macos1 post · Aug 14★ 10
Stars:10
- 06
#6
Self-hosted tool that captures user sessions and errors, investigates bugs with AI, and opens verified fix pull requests.
HN#claude-code#any-agent#claude2 posts · 24 days ago★ 50
Stars:50
- 07
#7
Self-hosted LLM code review platform: diffs in, structured line-pinned findings out, with RAG over the codebase and local inference.
GH#self-hosted#docker#web-app1 post · Jul 26★ 18
Stars:18
- 08
#8
Self-hosted LLM code review agent for GitLab, Forgejo, and GitHub with bring-your-own-model support.
HN#any-model#self-hosted#docker2 posts · Sep 8★ 115
Stars:115
- 09
#9
CLI for evaluating Agent Skills, agents, and workspaces with declarative eval cases, judging, and CI reports.
HN#claude-code#codex#cli1 post · Jul 30★ 1.2K
Stars:1.2K
- 10
#10
CLI that diffs AI agent traces between runs, flagging changed tool calls, args, costs, latency and outputs after model or prompt changes.
GH#cli#any-agent#any-model1 post · Jul 22★ 21
Stars:21
- 11
#11
Self-evolving CI/CD pipeline that rebuilds app twins on push, drafts and replays business-journey tests, and repairs failed builds via AI ag
GH#github-action#openai#claude1 post · Sep 24★ 39
Stars:39