claude — independent software & tools
-
mora
Local-first, zero-egress memory for MCP agents: Gmail, Calendar, iMessage, Apple Calendar → entity graph + ranked daily brief + hybrid retrieval
-
ai-website-cloner-template
Convert websites into clean Next.js codebases using AI coding agents. This template automates extraction, component design, and site reconstruction.
-
qcobrain
Provenance-governed AI memory for agents: a self-evolving second brain in your IDE. Every write cites a source or it's refused. Markdown + grep.
-
CodeSampleX
Stop solving the same code twice — a local-first distributed reasoning cache: anonymous compatibility evidence from real environments plus verified minimal samples for coding LLMs.
-
claude-quota-gauge
Live % of your Claude Max weekly quota in your terminal — cost-weighted from local transcripts, calibrated to the real number.
-
oura-mcp
Ask your Oura Ring anything, in ChatGPT or Claude, in any language. Remote MCP server for Oura data.
-
basml-cotton-yarn-dashboard
🌾 BASML Cotton & Yarn Dashboard: A real-time cotton and yarn price monitoring dashboard with AI-powered predictive forecasting for global and Indian markets. ⚡ Quick Overview Tech: React 18, Vite, JavaScript (98.2%) Purpose: Real-time price tracking, market analysis, AI forecast
-
tsubasa
Your engineering captain: a repo-resident AI persona with a knowledge graph stored in git. Agents cite incidents, ADRs and PRs instead of guessing — 47% fewer wrong answers, 40% cheaper on a public benchmark. Claude Code plugin + CLI.
-
temple
Session manager for Claude Code and Codex — an IDE for your agent sessions, organized by project and a click away
-
claude-rpc
Discord Rich Presence (RPC) for Claude Code — live model, project, tokens, and lifetime stats in your Discord profile. Driven by Claude Code hooks.
-
claude-notch
Approve Claude Code from your Mac's notch. A native SwiftUI menu-bar app that surfaces Claude Code permission prompts, questions, cost and context usage, no tabbing back to the terminal.
-
eigenform
A local control surface over Claude Code: context surgery on sessions (fork/rewind/edit/inject), a live session forest, and a full-fidelity browser terminal — self-contained Rust binary.
-
ripwire
ripwire — the ripgrep of AI context. A zero-dependency C++23 CLI that maps any codebase into a ranked, deterministic call graph for coding agents: orientation, blast radius, tests-to-run and quality verbs, plus an MCP server. ripgrep-fast retrieval, a tripwire on every claim it emits.
-
bearing
An intel layer for AI coding agents that assumes its own rules might be wrong — and keeps the evidence. Authoritative north-stars the agent must cite, a task-core written before compaction eats it, review by an expert in YOUR domain, and an installer that verifies its own claims instead of printing success. Claude Code, Cursor, Zed, Codex.
-
inmemory
Verbatim recall across Claude Code sessions, plus a gate against oversized skills. Pure Node, no dependencies, nothing leaves your machine.
-
claude-vps-setup-prompt
Harden a Hetzner Ubuntu 24.04 VPS with Claude Code: SSH, UFW, fail2ban, updates, and optional Tailscale setup
-
claude-in-your-pocket
OpenClaude 2026: AI Coding Agent in Your Pocket – No Server, No PC
-
engram
AIエージェント用 人間型記憶基盤（MCPサーバー）— 完全日本語版。使うほど思い出しやすくなる長期記憶を Claude Code / Codex / Antigravity で共有
-
autoevolve
Agent-native evolutionary optimization. Say the goal in english, evolve code toward a measured target with a population of coding agents.
-
mcp_reverse_engineering
Analyze binaries with a sandboxed MCP tool that unifies reverse engineering utilities and adds filesystem isolation, timeouts, and input checks
-
burnless
Stop replaying the transcript: capsule session state + rolling memory for LLM CLIs (Claude Code, Codex). Measured: −90.3% vs no-cache / −30% vs cached replay at turn 10, reproducible bench. MIT, provider-agnostic.
-
STK
STK (Session Token Killer) Claude Code hook that clamps oversized Read tool results into line-numbered outlines. RTK kills tokens per command, STK per session. 85% of my oversized agent context was file reads.
-
tryjarvis
Everyone deserves a chief of staff - your personal jarvis | not a chatbot. not another ai agent. | beta
-
faceit-mcp
Connect Claude to live CS2 FACEIT data to retrieve player stats, match history, ELO trends, and head-to-head comparisons via the Model Context Protocol.
-
hermes-war-room
Visualize and manage your Hermes agent fleet through a unified browser dashboard for streamlined orchestration and task delegation.
-
docweaver
Best Free Local AI Presentation Generator 2026 - No Uploads, No Accounts
-
shipmates
🚢 A crew of IDE agnostic sub-agents, slash-command workflows and tools that drive a GitHub issue from open to a reviewed, CI-green pull request — autonomously. Flagship: /ship-issue.
-
clauster
Your homelab's Claude Code launchpad. Self-hosted web UI that spawns & manages remote-control bridges on a remote host from any browser or phone — start/stop, spawn & permission modes, CLAUDE.md editor, git clone, live log tail, cost tracking. Loopback by default; password/reverse-proxy auth. No telemetry.
-
claude-auto-tok
Automate TikTok video creation with six AI agents for trend research, scripts, voiceovers, B-roll, rendering, and QA
-
periscope-mcp
Web-app QA, testing & analysis for AI agents — 74 Playwright tools: authenticated flows (2FA/SSO), 25-action E2E workflows, hard assertions, session reports, and accessibility / SEO / GEO / Core-Web-Vitals + Lighthouse audits across a page or a full crawled site. Battle-tested by an AI agent on real apps.
-
reelier
Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at 0 tokens, and diff runs to catch drift.
-
tillm
Text-interface LLM control plane for semcod/coru shell automation (pair with gillm for GUI).
-
claudeometer
Share & pool Claude usage across your team — a free macOS menu-bar app with live quota, burn-rate alerts, and end-to-end-encrypted borrowing.
-
brand-launchpad
One Claude Code skill that turns a single project into a complete brand launch — 12 files (positioning, hero line, 30-day calendar, content system) in one run. Built on Caleb Ralston, Harry Dry, Oren John & Brier Cochran frameworks.
-
ai-mind-map
🧠 MCP Server that reduces AI coding agent token usage by 80-99%. Knowledge graph + persistent memory + smart compression for Claude, Cursor, Copilot, and any MCP-compatible agent.
-
housing-sentinel-ai
房哨兵 AI 接入中心：中国12城官方房产成交数据与进攻/防守市场信号 — MCP Server + REST API + Claude Skill | Housing Sentinel: official housing data & offense/defense market signals for 12 major Chinese cities, via MCP / REST / Claude Skill
-
grimoire-of-tools
Ultimate AI Spellbook Workflows 2026 – Build Multi-Platform Skills & Automation
-
forge
Self-hosted lifecycle platform for software powered by Claude Code. Configurable pipelines, devices you control, no credentials on the server. Apache-2.0.
-
kodelyth-ecc
70 agents · 194 skills · 97 commands · 22+ hooks · semantic intent routing · self-learning memory · MCP server. Claude Code, Windsurf, Cursor, Codex, Antigravity, Cline, Roo Code, Aider, Kimi, Gemini CLI. MIT.
-
nano-claude-code
Build a lean coding agent in Python with the same performance in far less code
-
claude-code-meter
Tray widget showing Claude Code and Codex rate-limit usage and burn pace. Windows, local-only, MIT.
-
agent-usage
Claude Code and Codex subscription limits, at a glance: a Windows desktop panel and taskbar badge, plus a CLI for macOS and Linux status bars. No credential scraping - it reads the tools you already installed.
-
subroutine
Fast, self-hosted project management for people and AI agents, in equal measure. Your coding agent files its own work, and you can check what it did. Local SQLite, no account, no cloud. CLI, HTTP API and MCP — no web UI yet.
-
second-brain
Persistent memory for Claude Code — the full plugin: hooks, skill, MCP server, workflows. A Markdown vault you own, no server and no account. Hooks-only version: continuum.
-
cap-evolve
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
-
skillist
Realtime Agent Skills registry — publish, version, improve, and deliver skills that run and improve themselves. Compliant with the agentskills.io spec. Built entirely on Cloudflare Workers.
-
claudux
Web interface for running Claude Code sessions from a browser, phone included - tmux keeps the sessions alive, ttyd brings them into the browser.
-
elite-reasoning-mcp
90+ tool Model Context Protocol server for AI coding agents: workflow flight recorder, quality-gated memory, release doctor, eval harnesses, and reasoning safety.
-
licai
本地化个人理财助手 — A股/基金/理财/现金/数字资产/机器人全资产看板 + 市场AI问答 + 个股K线盘口详情 + 板块对比 + 早盘信息简报 + 资讯AI解读。只给客观信息，不荐买卖。
-
cc-statusline-tui
Customize Claude Code statusline TUI with multi-language support and simple install options for npm, Cargo, and Homebrew
-
markdown-fetcher-mcp
HTML to Markdown Converter MCP Server 2026 - Web Scraper & Clean Markdown Generator
-
checkpoint-claudio
Persistent checkpoint system for Claude Code projects
-
claude-studio
Build Claude AI apps with a unified dev stack for code, prompts, tools, tests, and local workflow
-
context-generator
Switch AIs without re-explaining everything.
-
sreeram-agent-crew
A personal AI crew that automates daily research tasks — monitors markets, watches YouTube channels, summarises with attribution, and delivers a morning digest email. Built on CrewAI + Claude, runs free on GitHub Actions.
-
hookstack
Claude Code hooks catalogue — production-ready hooks for Claude Code, OpenAI Codex & GitHub Copilot. Install in one npx command.
-
linear-cli
Manage Linear issues directly from your terminal with this lightweight, dependency-free binary featuring over 35 commands.
-
structify-dev-flow
Plan Build Run 2026: Ultimate Claude Code Plugin for Structured Agent Development
-
tokenctl
Hierarchical org→team→dev token-budget proxy for LLM traffic: meter, soft-throttle, hard-deny, and in-flight preemption across providers on one shared wallet.
-
ClAudit
Catch false-positive Claude Code safety/policy blocks, scrub PII, and auto-file clean GitHub issues. FOSS.