ultracontext and OpenContext
These are complements: UltraContext provides shared infrastructure for distributing agent context across multiple tools, while OpenContext provides a local-first capture and retrieval layer that could feed context into UltraContext's distribution system.
About ultracontext
ultracontext/ultracontext
Open Source Context infrastructure for AI agents. Auto-capture and share your agents' context everywhere.
Implements a realtime context daemon that syncs agent state across multiple LLM frameworks (Claude Code, Codex, OpenClaw) via an MCP server, enabling cross-agent awareness and session continuation. Provides a git-like Context API with automatic versioning and time-travel capabilities, available as JavaScript/TypeScript and Python SDKs for framework-agnostic integration with any LLM application.
About OpenContext
0xranx/OpenContext
A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project knowledge across agents and repos.
Integrates with coding agents (Cursor, Claude Code, Codex) via MCP server and auto-generated Skills/slash commands, enabling agents to read, search, and persist project context without external subscriptions. Built on a CLI-first architecture with optional desktop and web UIs; the MCP server layer lets existing agent CLIs access a searchable knowledge base stored in a user-level `contexts/` library across all projects.
Scores updated daily from GitHub, PyPI, and npm data. How scores work