shared-context

Where people and agents build in tune.

EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 20+ AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.

Multiple agents, one source of truth: a Planner/Coder/Reviewer demo of how a shared Statewave subject prevents parallel-agent context collisions.

Desktop workspace for managing agent trees, shared context, and live multi-agent coding sessions.

The open specification for the shared context layer of AI-native teams

Git-native ADRs as shared, enforceable context for AI coding agents and humans.

Personal fork of LuxenAI/agent-tree with my implementation work on the Luxen desktop workspace for multi-agent sessions.

MCP server that acts as a shared memory hub across multiple LLMs (Claude, Gemini, Copilot). Any agent entering a project immediately understands its architecture, patterns, and decisions — and can pick up exactly where the previous LLM left off.

Lightweight MCP server for sharing project context between AI agents across machines

MCP server for shared context caching — AI agents share computed results to reduce token cost and latency

Generic AsyncLocalStorage wrapper for context management

This component is an rpc accessible service to a shared context inside of a distributed system

MCP server, CLI, and Agent Skills for shared, versioned context across Claude Code, Codex, Cursor, Gemini CLI, humans, and AI agents

Shared context and memory coordination layer for swarms of parallel AI agents. Documented HTTP + WebSocket protocol, interoperable Python and Node CLIs, BM25 keyword memory search, built-in MCP server for agent tool calls.

Local-first coordination standard and reference implementation for AI workspaces