Live index of Claude Code extensions, hooks, and plugins — refreshed every 15 minutes from GitHub
⭐ Star this repo to bookmark — fresh data every 15 minutes
Automatically discovers and indexes Claude Code plugins, extensions, and hook configurations by scanning GitHub topics, repositories, and release activity. Generates a browsable markdown catalog and JSON API updated every 15 minutes via GitHub Actions, so users never need to manually search for new tooling.
This list is auto-updated every 15 minutes by a GitHub Actions cron. Each commit reflects a real change in the upstream data source — new items added, expired items removed — so you can rely on what you see being current.
⏰ Last updated: 2026-09-01 05:00 UTC
Data source:
GitHub Search APIThe table below is rewritten on every cron tick. Star the repo to bookmark.
| # | Name | ⭐ | Lang | Updated | Description |
|---|---|---|---|---|---|
| 1 | uniqueplume/AI-Token-Optimizer-Claude-Codex-Cursor | 20 | C# | 2026-09-01 | Local AI Context Compressor with Claude Code, Codex and Cursor profiles, duplicate-context removal, Git diff prioritizat |
| 2 | mat-lucie/outbound-sales-agent | 6 | Python | 2026-09-01 | Agent-operated outbound sales engine: LinkedIn + email cadence, two-stage ICP qualifier, learning loop. CRM-agnostic (At |
| 3 | CaptainCodeAU/cc-warehouse | 3 | Python | 2026-09-01 | Turn your Claude Code sessions into a readable, permanent archive. Captures each session as it ends, keeps the original |
| 4 | looplj/axonhub | 5136 | Go | 2026-09-01 | ⚡️ Open-source AI Gateway — Use any SDK to call 100+ LLMs. Built-in failover, load balancing, cost control & end-to-end |
| 5 | Zenetusken/consolidate-memory | 5 | Python | 2026-09-01 | Sleep-time memory consolidation for Claude Code agents, with a cross-project shared-consciousness layer. |
| 6 | YGao2005/scholar-feed-mcp | 10 | TypeScript | 2026-09-01 | MCP server for searching 600,000+ CS/AI research papers with citation graphs, full text, embeddings, and BibTeX. Works w |
| 7 | omnigent-ai/omnigent | 9569 | Python | 2026-09-01 | Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom a |
| 8 | derek-larson14/obsidian-claude-sidebar | 445 | JavaScript | 2026-09-01 | Run Claude Code, Codex, and other agent CLIs in Obsidian |
| 9 | sudokar/openspec-plus | 154 | — | 2026-09-01 | OpenSpec Plus — Agentic skills that enhance OpenSpec's Spec-Driven Development through better discovery, requirements, d |
| 10 | ai4curation/ai-gene-review | 24 | HTML | 2026-09-01 | Demonstration of AI review of existing functional annotations |
| 11 | PTD1012/jamdesk-doc-weaver | 0 | HTML | 2026-09-01 | Jamdesk Pro Plugin 2026: Build AI Docs Fast with Claude 4 Code |
| 12 | TheHefty/jvsl.monorepo.agents.template | 0 | Shell | 2026-09-01 | Reference monorepo that has already adopted the code-server dev-container template, plus the scaffolding a new project s |
| 13 | jmagly/aiwg | 206 | TypeScript | 2026-09-01 | Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and multi-platfo |
| 14 | thecoderbuddy/agile-team-skill | 9 | Shell | 2026-09-01 | An AI-powered agile team for any software project. Ship with the discipline of a senior team — even when you're building |
| 15 | sodam-ai/SoDam-Agentic-Eng | 2 | JavaScript | 2026-09-01 | 초보 바이브코더를 위한 Claude Code/Codex 플러그인 — 계획 먼저·쉬운 검토·안전 차단+기록(F6)·Codex 안전 패리티(F7)·쉬운 모드(F8) (Apache-2.0) |
| 16 | andr-ca/agentharness | 1 | Python | 2026-09-01 | Portable engineering policies for coding agents — git, testing, logging, and language conventions written once and refer |
| 17 | cryptozachla/app-doctor | 1 | — | 2026-09-01 | Audit any web app's security (39-point checklist) AND launch-readiness (legal, auth, polish, retention), report exactly |
| 18 | shimo4228/akc-cycle | 1 | Python | 2026-09-01 | The Agent Knowledge Cycle as a single behavioral rules file — install all six phases without the six standalone skills. |
| 19 | ihudak/ihudak-claude-plugins | 2 | Shell | 2026-09-01 | Claude Code plugins for the full feature lifecycle: idea → Value Increment → ARD → spec → design → Epics → implementatio |
| 20 | ederwii/tldr-experts | 0 | TypeScript | 2026-09-01 | tldr-experts (tldrx): a lightweight, file-based AI development workflow — one loop, five phases, experts on disk. Pre-al |
| 21 | MaoyuanYang/foundry | 1 | JavaScript | 2026-09-01 | Foundry — AI-native, spec-driven development suite for coding agents: greenfield (0->1), brownfield takeover, and contin |
| 22 | h0x91b/dev-3.0 | 249 | TypeScript | 2026-09-01 | Mission control for the One Person Studio — run a fleet of AI coding agents in parallel without losing your mind. Kanban |
| 23 | YMGlink/nrev-workbench-mcp | 0 | HTML | 2026-09-01 | Best 31 MCP Tools for nRev Workflow 2026 - Build & Debug |
| 24 | shimo4228/claude-harness | 2 | Python | 2026-09-01 | Curated, MIT-licensed Agent Skills, subagents & rules from shimo4228's harness — open Agent Skills standard, not Claude- |
| 25 | geml-spec/geml | 25 | JavaScript | 2026-09-01 | One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiabl |
| 26 | diegosouzapw/OmniRoute | 59404 | TypeScript | 2026-09-01 | Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, |
| 27 | yennanliu/finance_data | 2 | Python | 2026-09-01 | AI-gen/NotebookLLM U.S. stock reports and a suite of tools for downloading, organizing, and managing SEC financial fili |
| 28 | yangbobo2021/relay-dsh-plugin-claude | 4 | JavaScript | 2026-09-01 | Claude Code integration plugin for DeepSeek Harness, providing native Claude conversations powered by the Claude Agent S |
| 29 | Kweiza/ccdaddy | 0 | Go | 2026-09-01 | Claude Code Daemon: Always Drilling Don't Yap - manage multiple Claude Code accounts and auto-switch before a rate limit |
| 30 | boxdawn/boxdawn | 5 | Python | 2026-09-01 | Open your AI agents' black box. The waste is between your agents, not inside them. Four deterministic detectors over one |
| 31 | skymanbp/CodeEraser | 20 | Rust | 2026-09-01 | An eraser against LLM-induced code & document entropy. Support if you like it! |
| 32 | kookr-ai/kookr | 3 | TypeScript | 2026-09-01 | A smart attention router for developers running multiple AI coding agents. |
| 33 | manaflow-ai/cmux | 26636 | Swift | 2026-09-01 | Open source Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents. Built for multitaski |
| 34 | albertwujj/agent-term | 3 | JavaScript | 2026-09-01 | Steer a fleet of coding agents: integrated, open, and yours to reshape |
| 35 | stablyai/orca | 58572 | TypeScript | 2026-09-01 | Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available |
| 36 | Santosh-Prasad-Verma/ClaudeGate | 23 | Python | 2026-09-01 | High-performance bridge proxy connecting Claude Code CLI & Anthropic SDK to ANY OpenAI-compatible LLM provider (DeepSeek |
| 37 | jasonrundell/back-to-you | 0 | JavaScript | 2026-09-01 | A voice for Claude Code — hear when a task finishes or needs your call, without watching the terminal. |
| 38 | Win-Hao/caseboard | 0 | JavaScript | 2026-09-01 | Agent skill: pin any topic to an interactive 3D detective evidence board — Vite + three.js, zero image assets, determini |
| 39 | zz-plant/ambit | 0 | TypeScript | 2026-09-01 | The meta-MCP capability graph for AI agent environments |
| 40 | kai-kou/gem-hunter | 0 | TypeScript | 2026-09-01 | star の多さでは埋もれてしまう「実際に使われている OSS」を、個人開発者が見つけられるようにする検索プラットフォーム |
| 41 | yadam119988/method-mosaic | 0 | HTML | 2026-09-01 | Kimono AI 2026: Installable Claude Code Skill Catalog for Multi-Repo AI Development Lifecycle |
| 42 | shimo4228/agent-knowledge-cycle | 3 | — | 2026-09-01 | Agent Knowledge Cycle (AKC) — a knowledge cycle for AI agents: agent behavior compounds, human judgment sharpens. Six ph |
| 43 | itzikiusa/otto_os | 0 | Rust | 2026-09-01 | Agentic development environment for macOS: Claude Code / Codex sessions, multi-agent orchestration, git/PR review, DB & |
| 44 | RizRiyz/luvus | 628 | Rust | 2026-09-01 | Mission control for your AI agents |
| 45 | everyapi-ai/everyapi-ai | 2 | Go | 2026-09-01 | EveryAPI CLI: Claude Code / Codex / Gemini CLI integration + MCP server |
| 46 | B1ueMu3ic4m/OPCCompany | 0 | Swift | 2026-09-01 | Watch your AI coding agents run a company — a 2D macOS office where a CTO agent breaks down goals and AI employees work |
| 47 | AvesAlight/roost | 1 | TypeScript | 2026-09-01 | Your own team of Claude Code agents you can join. |
| 48 | saramjh/interaction-doctor | 0 | HTML | 2026-09-01 | A conflict matrix for touch gestures. Drag vs scroll, tap vs long-press, and the rest. |
| 49 | chippingway/orchestrator | 10 | Python | 2026-09-01 | Orchestrator for automated GitHub issue monitoring and agentic development across multiple repositories. |
| 50 | TheHefty/jvsl.env.agents.code-server | 0 | Shell | 2026-09-01 | A code-server dev container for agent work: the Claude Code and Codex CLIs, both sandboxed by default with ai-jail throu |
Every 15 minutes, a GitHub Action runs tracker.py. That script:
- Fetches the latest state from
GitHub Search API. - Diffs against
data/items.json(the previous snapshot). - Rewrites the table above between the
<!-- TRACKER_TABLE_* -->markers. - Commits
feat: +N added, -M removed (timestamp)if anything changed.
No external services. No paid APIs. Just a public data source and a free GitHub Action.
See CONTRIBUTING.md — usually you don't need to: the tracker keeps itself current.
If you spot a data-source bug or want to suggest a new column for the table, open
an issue.
If you find this useful, you might also like these other auto-updated trackers from the same maintainer — same mechanism, different upstream:
- trending-claude-skills — What's shipping in Claude Skills this week (
topic:claude-skills) - mcp-servers-live — Live index of newest MCP servers (
topic:mcp-server) - cursor-rules-live — Newest Cursor rules and .cursorrules patterns (
topic:cursor-rules) - llm-agents-radar — Newest LLM agent frameworks (
topic:llm-agent) - rag-radar — Newest RAG implementations and tools (
topic:rag) - llm-eval-tracker — Newest LLM evaluation tools and benchmarks (
topic:llm-eval) - agent-framework-radar — Newest agent frameworks shipping on GitHub (
topic:agent-framework) - vector-db-live — Newest vector DB projects and integrations (
topic:vector-database) - llmops-radar — Newest LLMOps tooling (observability, deployment) (
topic:llmops) - prompt-tools-live — Newest prompt-engineering tools and prompt repos (
topic:prompt-engineering) - agent-eval-harness — Live benchmark of AI coding agents (
topic:llm-eval) - skills-tracker — Tracking new GitHub 'skills' repos (
topic:agent-skills) - awesome-agent-skills — Curated auto-updated awesome-list of AI agent skills (
topic:agent-skills)
MIT — see LICENSE.