#claude-code

Persistent memory & code intelligence server for AI coding agents. Deploy on VPS for shared memory across machines. Hybrid search (BM25 + pgvector), knowledge graph, impact analysis. 14 MCP tools. Works with Claude Code, OpenCode, Cursor, and any MCP client.

Canary is a local Interactive Brokers risk desk for MCP, CLI, the paired app, and Go. Standard binaries and every MCP tool are read-only; gated broker actions require the separate trading build.

PHP and Laravel Cursor rules — coding standards, testing, and conventions for the Cursor editor. Install via Composer.

📼 A declarative AI agent environment manager, written in Rust

El repositorio no publica descripción.

One TUI for every AI coding agent session — Claude Code, Codex, Cursor, and more — in sync across every device.

Manage multiple AI terminal agents like Claude Code, Codex, OpenCode, and Amp.

pick any past Claude Code session via fzf, then resume it from the right cwd

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status line (industry-first Codex faux statusline), GitHub-style heatmap, multi-model cost analysis

Open source input firewall for AI agents, beta. A local scanner checks text, code, PDFs, images, QR codes, audio and video with 1,583 patterns across 117 categories and reports findings and incomplete scans. A Claude Code hook blocks secret material in tool calls and the paths and hosts your policy lists before tools run.

Hook system and MCP tool server for Claude Code agents. Designed for agenticore — fork and extend for custom workflows.

Read-only VMware vCenter/ESXi monitoring — code-level enforced safety, zero destructive operations

MCP memory server for Claude Code, Cursor, and any MCP client. Pure Go. Single binary.

El repositorio no publica descripción.

Stop repeating yourself to Claude.

The governance layer for LLM-maintained Markdown wikis.

Use your favorite coding agent with any model.

Intent-driven AgentOS for graph-based engineering workflows and agent orchestration

El repositorio no publica descripción.

A TypeScript CLI that assembles AI-powered prompts at runtime to guide you from "I have an idea" to working software. Scaffold walks you through 54 structured pipeline steps — organized into 15 phases — and Codex, Claude Code, or Gemini handles the research, planning, and implementation for you.

Build Your Agent Company with OMC

El repositorio no publica descripción.

Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.

Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The engine behind Geny. Apache-2.0.

Voice I/O MCP for AI coding agents — local TTS + STT, 2 tools (`voice_speak`, `voice_ask`) with ToolAnnotations

Verifies and compiles reduced-motion-safe, on-budget UI animation for AI-generated web apps: schema-validated specs to deterministic vanilla-GSAP + CSS, WCAG 2.2.2 / 2.3.3 checks. MIT core, keyless MCP server, free web check at motionspec.dev/motion-check. Not Motion.dev/Framer Motion, not the Android/iOS MotionSpec class, not a video generator.

MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

Workspace and context manager for domain specific AI automation and large scale AI workflows

PTY session management, WebSocket streaming, and REST API server for Claude Code conversations

Discover, curate, and activate skills across 12 coding agents—then hand off and coordinate work between Claude Code and Codex.