zirkelc/ai-resumable-stream

Essential utilities for building production-ready AI applications with Vercel AI SDK. State management, debugging, structured streaming, intelligent agents, and caching.

Eager tool dispatch for streaming LLM agents — dispatch tools the moment their JSON block seals, not after the message ends.

A library + API spec for easily streaming generative AI output to your chat applications.

Automatically resume the exact same conversation in the Codex desktop app on Windows after usage-limit resets, rate limits, or temporary failures.

TypeScript SDK for building AI agents with automatic, scoped, persistent memory. `agent-memory` wraps model calls with memory recall and learning so apps can keep useful user, thread, and operation context without manually stuffing long chat histories into every prompt.

OpenCode stops working if a model goes in timeout or there are errors, this plugin fixes those issues

Documentation and examples around LangChain's streaming capabilities.

A tiny Claude Code skill that keeps your prompt cache warm during idle sessions, so your next message reads from cache instead of paying full price.

Fragment-Based Memory MCP Server — AI 중장기 기억 시스템 (구 Memento-mcp)