MCP servers and skills: search, filter by where they run, and compare.
Anthropic organization usage and cost reporting through an admin API key connected by the user.
Hosted by authorMITFew starsNo key
MCP server for the Anthropic Admin API — manage your Claude org from any MCP-compatible client. Full coverage of Usage/Cost API plus org/workspace/member/key management, with audit logging and safety
PythonMITFew starsNeeds a key
Audits Claude-directing artifacts (CLAUDE.md, SKILL.md, subagent, hook, MCP, prompts, api_config) against 189 cited Anthropic rules across 11 dimensions. Cite or stay silent. Voice drift trumps score.
SkillMIT★ 19No key
Svensk komplement-stack till Anthropics Claude for Small Business. 11 Claude Skills för Bokio, moms, AGI, K10 och svenskt regelverk.
SkillMIT★ 10No key
Claude Code skill for Anthropic Managed Agents — create / run / audit the cloud-hosted agent API end-to-end. 教 Claude 用 Anthropic 托管代理 API 的 skill,覆盖创建/运行/审计全流程。
SkillMIT★ 11No key
修复 Claude Code Desktop 接入 DeepSeek/第三方模型后能力缺失、联网失败、频繁权限弹窗的 Claude Skill
SkillMIT★ 7No key
An xlsx file translation tool that preserves formatting, formulas, and data integrity.
Node.jsMIT★ 2Few starsNeeds a key
Pure-Rust async runtime for LLM agents. Multi-provider (Anthropic/OpenAI/Ollama), tool-capable end-to-end, structured permissions, real MCP support, USD cost tracking, Files API, optional FS+search to
SkillMIT★ 18No key
Self-hostable channel-native AI teammate for Slack. Open source alternative to Claude Tag. LLM-agnostic.
PythonMIT★ 17No key
CLI (npm + PyPI) and GitHub Action that scores AI-generated UI for genericness using an Anthropic LLM-judge rubric, with a --json mode and library API for CI and agent quality gates
PythonApache-2.0Few starsNo key
Convert any JSON Schema into a valid tool / function calling schema for OpenAI, Anthropic, Gemini and MCP. Zero dependencies.
Node.jsMIT★ 2Few starsNo key
A modular Python client for connecting to MCP servers, integrating with Anthropic Claude, and exposing a FastAPI-based API for handling queries and tool calls.
SkillMIT★ 4Few starsNo key
Local-first flight recorder for AI agents: every LLM call, tool call, cost, and loop captured by a transparent proxy. Zero code changes.
PythonMIT★ 7No key
Rust-native, local-first, auditable structured extraction with schemas, benchmarks, persistence, and operational reliability
SkillApache-2.0★ 5No key
FeedOracle × Claude Managed Agents — Compliance intelligence agent with 5 MCP servers (79 tools). MiCA, stablecoin risk, macro regime, agent governance.
Hosted by authorMITFew starsNo key
Claude Code forgets everything when a session ends. This fixes that — persistent memory across sessions, automatic context injection, and cache optimization so you pay less for every turn.
SkillMIT★ 5No key
AI SDK for Rust: text generation, streaming, tools with approval, agents, structured output, MCP client and more modalities across OpenAI, Anthropic, Google and OpenAI-compatible providers
SkillApache-2.0★ 4Few starsNo key
One command. Your entire Claude Code setup. Done.
SkillMIT★ 4Few starsNo key
.NET orchestrator for executing Anthropic-style AI Skills with Azure OpenAI and MCP tool support
SkillMIT★ 17No key
Cut Claude Code spend without sacrificing quality — and prove it. Haiku/Sonnet/Opus router with real $-saved numbers, not vibes.
SkillMIT★ 3Few starsNo key
The agentic browser for your AI apps and agents, with built-in MCP and A2A support.
SkillApache-2.0★ 5No key
MCP server that delegates Claude Code subagents to local models (LiteLLM/llama.cpp/Ollama), DeepSeek, AWS Bedrock, or any OpenAI/Anthropic-compatible backend — without losing the Claude Code orchestra
PythonMIT★ 17No key
Real-time collaborative coding for two developers on the same codebase. Host a session, share a join command, and both get Claude Code connected to your project—with file locking and host approval to
PythonMITFew starsNo key
Zero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model
SkillApache-2.0★ 12No key
Who stands behind it
