Updated daily · last run Nov 21, 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
- 43K
- Tossed out
- 33.7K
28 tools, ranked by sources, chatter and star growth. How ranking works
- 01
#1
Open-source test runner for coding agents and skills that asserts on tool calls, commands, files, HTTP requests, and answers.
HN#claude-code#codex#opencode2 posts · 3 days ago★ 12
Stars:12
- 02
#2
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 · 4 days ago★ 121
Stars:121
- 03
#3
Pytest plugin that records test dependencies and runs only the tests a change can affect, for AI coding agents and CI.
GH#claude-code#codex#cursor1 post · 5 days ago★ 12
Stars:12
- 04
#4
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 · 7 days ago★ 118
Stars:118
- 05
#5
Live AI code reviewer that runs alongside coding agents, reviews sessions against intent, and routes work across model subscriptions.
GHHN#claude-code#codex#cursor3 posts · 7 days ago★ 136
Stars:136
- 06
#6
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 · 10 days ago★ 11
Stars:11
- 07
#7
Headless browser QA tool that crawls apps, traps runtime/network/layout/a11y failures, and returns bug reports for coding agents to fix.
GH#claude-code#codex#cursor1 post · 15 days ago★ 48 +23/wk
Stars:48
+23 this week
- 08
#8
Lints rendered UI in a real browser for overflow, contrast, overlap and layout defects, built as a quality gate for AI coding agents.
GH#claude-code#cursor#codex1 post · 28 days ago★ 686 +172/wk
Stars:686
+172 this week
- 09
#9
Open-source AI code review CLI from Alibaba using deterministic pipelines plus an LLM agent for line-level review comments.
GH#claude-code#codex#cursor1 post · Oct 10★ 54.9K +3.3K/wk
Stars:54.9K
+3.3K this week
- 10
#10
SDK and MCP server that lets coding agents verify their changes against the running app, returning pass/fail verdicts with file:line evidenc
HN#claude-code#cursor#codex1 post · Oct 20★ 1.3K +43/wk
Stars:1.3K
+43 this week
- 11
#11
A semantic linter that uses decision models to find code defects and supports custom rules and coding-agent integrations.
GHHN#cli#claude-code#cursor4 posts · 29 days ago★ 309
Stars:309
- 12#12
Local tool that snapshots pages before an AI agent works and pixel-diffs after, flagging changed surfaces before git commit.
HN#claude-code#cursor#copilot1 post · Aug 13
no public repo
- 13
#13
CLI scanner that audits Cargo workspaces with 126 rules, scores code health, and hands findings to coding agents or CI.
HN#claude-code#codex#cursor1 post · Aug 19★ 19
Stars:19
- 14
#14
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
- 15
#15
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
- 16#16
VS Code and Cursor extension that fixes bugs with AI, explains root causes, and generates regression tests.
HN#vscode#cursor#editor-extension1 post · Jul 30
no public repo
- 17
#17
Local review workspace that helps humans review agent-written code with impact analysis, provenance, verification evidence, and durable revi
HN#claude-code#codex#cursor1 post · Jul 21★ 72
Stars:72
- 18#18
Local review daemon that reviews each commit in the background using coding agents, with findings tracked in a persistent ledger.
HN#claude-code#codex#cursor1 post · Aug 13
- 19
#19
Extracts a design contract from a reference page and measures an implementation against it, with an MCP server for coding agents.
GH#claude-code#cursor#any-agent1 post · Sep 5★ 17
Stars:17
- 20
#20
Verification layer for coding agents that turns command output into evidence, computes completion state, and marks evidence stale when files
GH#claude-code#codex#gemini-cli1 post · Sep 9★ 14
Stars:14
- 21
#21
Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees those criteria.
GH#claude-code#codex#cursor1 post · Sep 6★ 16
Stars:16
- 22
#22
AI agent for two-stage code review of 1C:Enterprise BSL modules and SKD queries, runnable from Jira or IDE agents.
Stars:29
- 23
#23
MCP review gate that has other vendors' models review a coding agent's plan and diff, with dedup, a rounds log and a local SQLite record.
GH#mcp-server#vscode#claude-code1 post · Aug 31★ 13
Stars:13
- 24
#24
Agent skill that pentests your running app: finds, proves, patches and re-verifies real vulnerabilities via /hack-me.
GH#claude-code#codex#cursor1 post · Sep 15★ 48
Stars:48
- 25
#25
Open-source load testing tool that agents write and run; single binary, 14 protocols, CI/CD gates, built-in MCP server.
HN#claude-code#cursor#mcp-server1 post · Oct 20★ 12
Stars:12