anthropic — independent software & tools
-
@drawio/mcp
Official draw.io MCP server for LLMs - Open diagrams in draw.io editor
-
@earendil-works/pi-ai
Unified LLM API with automatic model discovery and provider configuration
-
@fatihkan/badi
Workflow management CLI for Claude Code, Cursor, and Gemini CLI — 30 AI agents (incl. a virtual eng team, ads strategist, market/SEO/data analysts), 86 commands, OWASP security scans. Built for Anthropic Claude Opus and Sonnet.
-
@juspay/neurolink
Universal AI Development Platform with working MCP integration, multi-provider support, voice (TTS/STT/realtime), and professional CLI. 58+ external MCP servers discoverable, multimodal file processing, RAG pipelines. Build, test, and deploy AI applicatio
-
@keleshteri/pageindex-rag
Vectorless RAG using LLM-driven hierarchical document indexing — PDF and Markdown/Obsidian vault support
-
@langchain/anthropic
Anthropic integrations for LangChain.js
-
loki-mode
Loki Mode by Autonomi. Autonomous spec-to-product system: takes a PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief to a deployed app via the RARV-C closure loop with 8 quality gates. Provider-agnostic (Claude Code, OpenAI Codex, Cline, Aider).
-
loki-mode-sdk
TypeScript SDK for Loki Mode - autonomous multi-agent development platform
-
@mcp-b/transports
Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs
-
mcp-framework
Framework for building Model Context Protocol (MCP) servers in Typescript
-
mcp-memory-graph
Local-first memory MCP server for Claude Code and any MCP client: hybrid vector + knowledge-graph search, bi-temporal recall, Obsidian sync. Runs 100% on your machine, $0/token.
-
mcp-registry-spec-sdk
A minimal, typed client for the official Model Context Protocol (MCP) Registry API.
-
mcp-server-kubernetes
MCP server for interacting with Kubernetes clusters via kubectl
-
nothumanallowed
Local AI assistant: 80 tools (Gmail, Calendar, Drive, GitHub, Slack, browser, code, files), 38 agents, visual workflows (Studio, AWF, WebCraft). Install with `npm i -g nothumanallowed`, run with `nha ui`. Free tier built-in (Liara), no API key required. Y
-
octocode-mcp
Model Context Protocol (MCP) server for advanced GitHub repository analysis and code discovery. Provides AI assistants with powerful tools to search, analyze, and understand codebases across GitHub.
-
@posthog/ai
PostHog Node.js AI integrations
-
specrails-core
AI agent workflow system for Claude Code — installs 12 specialized agents, orchestration commands, and persona-driven product discovery into any repository
-
@structured-world/gitlab-mcp
Advanced GitLab MCP server
-
@surething/cockpit
The open-source Claude Code GUI — an IDE-like workbench for parallel AI coding. Drive Claude (default), Codex, DeepSeek, Kimi, or local Ollama in tabs. Terminal, browser & DB bubbles, code review. Self-host on a shared dev box — a seat for every teammate.
-
takt
Workflow control for AI coding agents
-
tavily-mcp
MCP server for advanced web search using Tavily
-
claude-skills-marketplace
🛠️ Transform Claude into a System Architect, generating detailed project documentation for AI-assisted software development with clear boundaries and traceable requirements.
-
exobrain-harness
🧠 A self-hosted AI exobrain. Claude Code wired into 50+ skills, launchd watchers, and MCP servers, fusing voice transcripts, handwritten notes, calendar, tasks, and health data into one always-on accountability partner that makes sure nothing falls through the cracks.
-
claude-sdlc-wizard
SDLC enforcement for Claude Code — hooks, skills, and wizard setup in one command. TDD, planning, self-review, CI shepherd.
-
cc-docs
Auto-updated mirror of Claude Code documentation from code.claude.com, refreshed every hour via GitHub Actions
-
codilay
Build and maintain codebase docs with an AI agent that maps module links, updates knowledge, and supports search and chat
-
claude-mob-programming-skill
Enable collaborative coding in Claude Code with automated expert roles for test-driven, quality-checked mob and pair programming workflows.
-
claude-code-law-zero
-
ClaudeUsageBar
📊 Track your Claude.ai usage seamlessly with this lightweight macOS menu bar app, providing real-time updates and notifications.
-
coco
AI-powered Git Assistant for CLI
-
OBSICLAUDE
Manage and enhance your Obsidian vault using Claude with tools to create, edit, move, search, and organize through natural language commands.
-
harakiro-marketplace
Claude Code plugin marketplace — AI development tools by harakiro
-
gemini_cli_skill
🚀 Enhance Claude Code with Gemini CLI for better code generation, reviews, testing, documentation, and architecture analysis.
-
claudetop
Track Claude Code token use and spending in real time to monitor costs and optimize your daily $20 budget efficiently.
-
claude-history-sync
Sync Claude Code history across machines with Google Drive, keep conversations tied to each git repo, and preserve renamed chats
-
agent-commands
🚀 Automate project handoffs and resumption with these command files and skills, enhancing workflow continuity across your development tasks.
-
ynab-mcp-server
MCP server for YNAB (You Need A Budget) — full API coverage. Budget tracking, transaction categorization, account management, goal monitoring, and financial reporting through AI.
-
prompt-library
📚 Discover and customize prompts for various use cases with our structured library, designed for clarity and ease of use.
-
conductor
A Rust terminal UI for AI-assisted development: manage multiple git worktrees, run Claude Code sessions in embedded PTYs, and review diffs with structured inline comments — all from one TUI.
-
codeoid
Identity-first control plane for AI coding agents — multi-session, multi-frontend (TUI · web · Telegram), with cross-session memory and per-agent ZeroID identity.
-
ClaudeCodeStatusLine
Display real-time Claude Code model info, token usage, and rate limits in a compact status line without affecting performance or token counts.
-
LaunchPad-v2
AI founder co-pilot that validates startup ideas through a 7-stage journey — autonomous competitor watchers, signal-to-knowledge graph, approve-first agent actions, real-time market research. OpenClaw-inspired multi-agent architecture on Next.js + PostgreSQL + Claude.
-
Claude-cod-top-2026
Still trusting results that AI generated, tested, and declared successful by itself? This Claude Code methodology adds evidence markers, audit gates, anti-hallucination rules, and Validation Theater detection to keep AI-assisted development verifiable.
-
soft-ue-cli
Control Unreal Engine 5 from the command line with Python CLI tools for AI agents, Blueprints, actors, screenshots, profiling, and more
-
faf-one-svelte-new
Official website for .faf — faf.one. SvelteKit, auto-deploys on push
-
nanobot
AI Agent Platform built in Rust — Multi-model, MCP tools, 14+ channel integrations. Self-host or use teai.io
-
cxusage
📊 Analyze Codex daily usage from session logs, aggregating token counts by day or model. Output options include plain, Markdown, or JSON.
-
@andersmyrmel/vard
Lightweight prompt injection detection for LLM applications. Zod-inspired chainable API for prompt security.
-
openskills
Universal skills loader for AI coding agents - install and load Anthropic SKILL.md format skills in any agent
-
task-master-ai
A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.
-
@tokenlens/models
Tree-shakeable static models.dev catalog split by provider for TokenLens.
-
tokenx
Fast token estimation at 96% accuracy of a full tokenizer in a 2kB bundle