1.DietrichGebert / ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
+88,144 stars
from 93,958 · score 11.39
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
29 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.thedotmack / claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
+20,671 stars
from 88,547 · score 9.94
3.career-ops-hq / career-ops
Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendly resume and cover letter, get interview prep and an application tracker. It helps you fill in each application; you press Submit. Runs locally in Codex, OpenCode and other AI CLIs, or as a Claude Code plugin.
+17,247 stars
from 62,034 · score 9.76
4.coreyhaines31 / marketingskills
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
+15,310 stars
from 42,543 · score 9.64
5.wshobson / agents
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
+3,856 stars
from 38,225 · score 8.26
6.renezander030 / capcut-cli
Independent, unofficial CLI to edit CapCut and JianYing (剪映) projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, reads draft_content.json and draft_info.json (剪映草稿) directly. Not affiliated with ByteDance.
+822 stars
from 261 · score 6.71
7.nowork-studio / notfair-plugin
Open-source SEO, GEO, and marketing skills for AI agents.
+809 stars
from 3,284 · score 6.70
8.kenryu42 / cc-safety-net
A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Devin CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.
+434 stars
from 1,449 · score 6.08
9.kyegomez / OpenMythos
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
+300 stars
from 14,614 · score 5.71
10.hyhmrright / brooks-lint
Portable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation.
+280 stars
from 1,274 · score 5.64
11.activeloopai / hivemind
Hivemind turns your traces into reusable skills across agents
+126 stars
from 1,514 · score 4.84
12.posit-dev / skills
A collection of Claude Skills from Posit
+97 stars
from 454 · score 4.58
13.MohamedAbdallah-14 / unslop
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.
+79 stars
from 91 · score 4.38
14.josstei / maestro-orchestrate
Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools
+40 stars
from 445 · score 3.71
15.iurykrieger / claude-bedrock
Second Brain automation for Obsidian vaults — entity management, ingestion, compression, and sync via Claude Code skills
+22 stars
from 87 · score 3.14
16.JeongJaeSoon / agent-guard
Real-time secret-leak guardrails for AI coding agents (Claude Code, Codex), Git hooks, and CI.
+22 stars
from 16 · score 3.14
17.thousandflowers / skillreaper
Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence
+15 stars
from 47 · score 2.77
18.EndeavorYen / chrome-cdp-exArchived
Attach a coding agent to the Chrome/Edge/Electron tab you already have open. Cookies stay. Not a fresh Playwright browser. Zero runtime npm deps.
+11 stars
from 11 · score 2.48
19.HeyRenan / showreel
Claude Code plugin for visual docs — annotated screenshots, feature demos, flow walkthrough recordings (gif/mp4), terminal captures and before/after composites, one command each. Self-contained Chromium, self-validated output, no MCP.
+10 stars
from 4 · score 2.40
20.djadmin / fort
Audit and fix your Mac's security in one command. No agent, no signup, open source.
+8 stars
from 73 · score 2.20
21.futuresearch / futuresearch-python
Forecast what will happen, including outcomes of your decisions.
+8 stars
from 49 · score 2.20
22.arturogarrido / claudinho
⚽ Live football(soccer) scores, fixtures and standings for the competition you follow (World Cup, Premier League, LALIGA, Champions League and 12 more) in your terminal, your Claude Code and Cursor CLI statusline, and MCP clients. No API key. Independent fan project. Not affiliated with FIFA, any confederation, league or club, or Anthropic.
+8 stars
from 27 · score 2.20
23.briansmith80 / claude-code-status-bar
Configurable status bar for Claude Code: usage limits with pacing markers, context window, git state, live activity, session cost, and 8 colour themes. Pure bash, zero dependencies.
+6 stars
from 16 · score 1.95
24.HMAKT99 / AKF
Trust metadata for AI agents — a stamp costs ~15 tokens, re-verifying costs 15,000. Agents stamp what they verify; the next agent runs 'akf check' and builds on it. pip install akf
+6 stars
from 14 · score 1.95
25.wei18 / Upkeep
Upkeep — an AI audit crew for your repo. Catches docs/spec/asset drift with evidence; output-only. Claude Code plugin/skill + reusable CI workflow.
+6 stars
from 10 · score 1.95
26.NakaokaRei / SwiftAutoGUI
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
+4 stars
from 90 · score 1.61
27.Myr-Aya / GouvernAI-claude-code-plugin
Runtime guardrails for Claude Code. Auto-approve what's safe, gate what's risky, block what's dangerous. Dual enforcement, full audit trail. MIT.
+4 stars
from 20 · score 1.61
28.sara-star-quant / presence
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.
+3 stars
from 5 · score 1.39
29.bennypowers / asimonim
The Design Tokens Multitool. CLI and go library; LSP and MCP; Generator and converter
+2 stars
from 28 · score 1.10