PyPI agents

Claude Code workflow and agent management framework - Multi-agent orchestration, skills system, MCP integration, session management, and semantic code search for AI-powered development

Claude Code usage dashboard across multiple devices

Claude Multi-Agent Project Management Framework for AI-driven orchestration

Claude Proxy Router - 智能代理路由器

MCP server for inter-session communication between Claude Code sessions in iTerm2

Claude Code統合ツールシステム - フック・規約管理CLI

CLI daemon that proxies code execution to remote Jupyter kernels with local notebook logging

Transform Claude Code transcript JSONL files to terminal and HTML views

Cross-platform notification system for Claude Code hooks with intelligent project detection

Personal AI project management hub — North Star milestone tracking, live Claude sessions, CTX context alignment.

Autonomous development framework for the Django-Bolt ecosystem — Rust-powered Django APIs

Access Claude Code CLI from your mobile device over WiFi

VPN-style one-click toggle to route Claude Code (CLI + VSCode) to custom model endpoints (DeepSeek, NVIDIA NIMs, OpenRouter, Ollama, ...).

Claude API to OpenAI API adapter

Thin OpenAI-compatible API proxy backed by Anthropic Vertex AI

A tool to manage OpenRouter integration with Claude Code.

Route Claude Code through OpenRouter to alternative models

Orchestrate multiple Claude Code instances to work in parallel

Hierarchical AI agent organization framework for Claude Code

Python runtime for claude-org-ja: dispatcher, state schema, and reference role prompts.

Claude -p compatible wrapper backed by interactive Claude Code subscription sessions

Parse and analyze Claude Code JSONL exports

MCP server for Pascal/Delphi/Lazarus compilation and execution with Claude

Convert PDFs (especially Claude Web UI research exports) to Markdown with hyperlinks and visual structure preserved.

OCR plugin for claude-pdf2md — recognise text in scanned PDFs via Tesseract (and other backends) and feed it into the existing PDF→Markdown pipeline.

Inspect and tail Claude Code session transcripts — list sessions, slice conversations, watch live.

A virtual pet for Claude Code with daemon mode, IPC, conversation history, and enhanced security

Claude Code CLI Pilot - Your development workflow companion

A pip-installable Python CLI that pipes stdin into Claude with Pydantic-validated structured outputs.

Check your Claude plan usage limits from the terminal — no more switching to the desktop app

Claude MCP plugin for Kubernetes cluster awareness, diagnostics, and remediation

プロ級の実装を自動化する日本語完全対応の開発プラットフォーム - Claude Code統合により、会話だけで開発が完結

Run Claude Code CLI in a Podman container with tmux, GitHub access, and persistent config

Portable Claude Code workspace archives

Email search and management tool using MCP protocol

Prime your repo for Claude Code with context-aware knowledge architecture

Persistent agent memory for AI coding assistants

A TUI-based Claude Code configuration profile switcher

Manage multiple Claude Code profiles — credentials, skills, and memories across nodes

Prometheus exporter for Claude API usage and cost metrics

Developer-native TUI for refining prompts using Claude Code

Claude Code efficiency and hygiene toolkit. Surfaces token spend across the 5h / 7d / Sonnet-7d billing windows with per-model / per-agent / per-skill attribution, and audits your effective Claude Code configuration (custom + plugin agents and skills) for overlap and conflicts. Ships an interactive dashboard, a conversational usage-analysis skill, and a structured config-audit skill.

A production-ready Claude API proxy server

A lightweight framework for implementing Claude Code hooks in Python.

Lightweight Python LSP MCP server + grep-intercept hook for Claude Code

A tool for uploading and managing projects in Claude.ai

Claude Code plugin: ruff + mypy + pytest + uv hooks and Python skills.

Ralph Loop Harness: iterative Claude runner + stream-json renderer

Claude API reimplementation

Automatic, cheap, precise query of Claude Code session archives via SQLite FTS5 + hooks.

Recapture what you built with Claude — conversation history analyzer and report generator

Compatibility package; use agentrelay-cli

Sync local Claude Code environments to remote machines

High-performance CLI tool to find and repair broken Claude conversation sessions

Migrate Claude Code project state when your project folder moves — rewires cwd paths across sessions, ~/.claude.json, and worktrees.

Durable, hierarchical, repo-scoped memory for Claude Code. Local-first MCP server with hybrid lexical + vector retrieval over your codebase, docs, and accumulated decisions.

Diagnose and recover corrupted Claude Code session JSONL files

TUI session picker for Claude Code --resume

Sprint retro for your Claude Code sessions

Local PR review system for Claude Code - GitHub-style code review without leaving your terminal

Run Claude CLI subprocesses with automatic multi-account rotation and rate limit handling

Embedding-based scaffold router for Claude API. Routes tasks to the right scaffold using centroid matching. By Hermes Labs.

Reusable Claude Agent SDK wrapper with bug workarounds, retry, and timeout

The easiest way to build AI agents with Claude. CLI, SDK, and Cloud — 5 lines to start.

A zero-dependency Claude Code PreToolUse guard that blocks destructive shell commands before they run.

A Redux Saga-like effect system for Python, designed for Claude Code hooks

Semantic checkpointing for Claude Code

A Claude Code hook that scores and remembers bad responses, then injects them back into future turns

Lightweight viewer for Claude Code session transcripts

A placeholder for the Claude SDK Python package

A lightweight Python SDK for Claude Code CLI using subprocess

Add your description here

Secret scanning CLI for Claude Code

Manage a local registry of Claude CLI auth snapshots plus simple SDK token entries.

Scaffold a .claude/ governance framework for self-improving AI agents

Git-backed Claude Code session backup with timeline view, folder analysis, deletion detection, and session restore.

Track Claude Code's 5-hour session usage from local JSONL and pause tool calls before hitting the limit. No API calls, no network.

Shared session discovery, caching, and classification for Claude Code tools

Index, search, and analyze your Claude Code sessions

Session management for Claude CLI - preserve context across projects

MCP server for managing Claude Code conversation sessions

Sync Claude Code sessions across Windows, macOS, and Linux

Monitor running Claude Code sessions in your terminal

Search and view Claude Code session logs

Intelligent scaffolding system for Claude Code configurations - Generate optimal .claude setups for any project

Scan your Claude Code setup for behavioral discipline gaps vs. production-grade patterns. Get a scored report with copy-paste fixes.

CLI launcher for Claude Code through the claude.shop proxy.

Security auditing tool for Claude Skills - Detect malicious patterns before installing third-party skills

Linter for Claude Code SKILL.md files. Validates YAML frontmatter, required fields, description length, and common secret patterns.

Manage Claude Code skills from multiple sources with symlink-based deployment

Curated catalog of Claude Code skills with an interactive installer.

CLI tool to manage Claude Code skills (~/.claude/skills/)

Lightweight MCP proxy for Claude Skills (auto-downloads backend)

Heavy backend for Claude Skills MCP server with vector search (Streamable HTTP)

MCP server for Claude Code slash commands

MCP server for AI interaction with live Smalltalk images (Cuis and Squeak)

Self-improving Claude Code, Codex, and OpenCode plugin that turns corrections into Preferences, Project-specific skills, and Shared skills

Claude Code hooks that preserve task state and user preferences across auto-compaction

Semantic search across Claude Code sessions to find the best context for new tasks

Lossless structural codec for Claude Code session JSONLs — portable conversation snapshots that move between devices, plus a built-in localhost chat surface that keeps your API key out of the browser.