#claude-code

An agent composition framework that builds stacks and compiles specialized subagents for Claude Code

The smallest change that ruins an attacker's day.

Modular development framework with multi-vault secrets, Claude Code integration, extensible hooks, and health checks.

Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.

Agent-native investment research workspace for evidence-tracked, refreshable investment theses across equities, earnings, macro, and portfolio review.

Auto-retry Claude Code on subscription rate limits, API overload (529/5xx) and safeguard false positives — waits for the printed reset, exponential backoff, tmux-based

No repository description published.

MCP server for Sublime Text 4 — lets Claude Code read and control a running ST instance

Set bounded, verifiable coding loops for Codex, Claude Code, Cursor, and SKILL.md-compatible agents.

A lightweight bridge that connects Claude Code to Genudo's Model Context Protocol (MCP) server, enabling AI-powered workflow automation directly from your Claude Code interface.

Switch between multiple Claude Code providers (Kimi, GLM, MiniMax, etc.) with a single command.

Unofficial, agent-friendly Mercadona shopping CLI (Go) — search products, read prices, build a cart and prepare checkout from the terminal. BYO credentials.

Persistent memory for AI coding agents — your agent stops forgetting between sessions. One Go binary, one SQLite file.

Practical patterns, starters & CLI tools for loop working with AI agents.

One Agent Client Protocol surface, three CLI backends. Drive Claude Code, codex, and opencode without backend-specific orchestrator code.

Your AI finds the open-source tool it needs on GitHub. Legwork installs it in a sandbox.

Compounding Context for AI Coding Assistants — MCP graph engine for Claude Code, Cursor, Copilot, Gemini, OpenCode

Pin feedback to the live UI. Hand it to Claude. An embeddable visual-feedback SDK — inspect an element, pin a comment, capture a screenshot; comments re-anchor across redeploys and reach Claude Code via MCP.

Live Markdown viewer for reviewing AI-agent output — change highlighting, unread badges, full-text search, Marp slides, PDF export. Zero-build Node.js.

Guardrails for AI agents, with a receipt. Blocks destructive tool calls before they run and signs every decision into a hash-chained record anyone can verify with an open-source tool.

Orchestration system for long-running complex agent tasks

What a block of AI-assisted work cost — real, API-equivalent, vendor quote — from the usage already on disk (Claude Code, Codex CLI, Gemini CLI, Grok Build CLI, your own logs)

Transparent logging proxy for Claude Code — audit what eats your context, with local ClickHouse/Loki/Grafana analytics

AI orchestration tool for Claude Code with MCP state management, review workflows, and plugin auto-update

微信读书 CLI / WeRead CLI: 基于官方支持 API，面向人类与 AI Agent 的书架、笔记、划线、书评、阅读统计和推荐工具。Official API-based WeRead command-line tool with Agent Skill support.

The Git CLI that is safe to hand to your AI Agents: no sharp edges by design, commit concurrency built-in, Git-compatible because it uses Git plumbing under the hood

Low-noise Slack notifications for Claude Code that only fire when the agent is really done

Run a close-to-real Claude Code session programmatically via the Agent SDK and expose it to a host app as something it can embed, watch, and control. Runner + wire protocol + gateway + embeddable panel.

Local TUI orchestrator for long-running, auditable coding-agent sessions

Autonomous agent ecosystem — CLI tools that provision, scaffold, and maintain Claude Code agent ecosystems