Connectors

Add persistent memory where agents already run

Use Wolbarg Workspace for coding agents (Cursor, Claude Code, Codex). Use AI SDK adapters when you are building a custom agent.

Coding agents

Wolbarg Workspace

Shared project truth for Cursor, Claude Code, and Codex. One CLI installs MCP + host rules — no hand-edited JSON.

Productv0.1.0 on npm

Wolbarg Workspace

@wolbarg/workspace

Shared, reconciled project truth for Cursor, Claude Code, and Codex. Agents stop re-explaining the codebase every session.

$ npx @wolbarg/workspace init

What you get

  • Shared across hosts

    Cursor, Claude Code, and Codex read and write the same project truth.

  • Reconciled, not appended

    Updates replace stale facts instead of piling up notes.

  • Evidence-backed

    Decisions and discoveries stay tied to files, tests, and docs.

  • One CLI

    init, connect, doctor, status, review — no hand-edited MCP JSON.

Connect with connect cursor, connect claude, or connect codex.

Cursor

npx @wolbarg/workspace connect cursor

Claude Code

npx @wolbarg/workspace connect claude

Codex

npx @wolbarg/workspace connect codex

Custom agents

AI SDK adapters

Thin adapters for popular agent frameworks. Your stack runs; Wolbarg owns durable shared memory.

AI SDKv1.0.0

Vercel AI SDK

@wolbarg/vercel-ai

Automatic recall into the system prompt and remember after generations with the AI SDK.

AI SDKv1.0.0

OpenAI Agents

@wolbarg/openai

Wire Wolbarg shared memory into OpenAI Agents as persist / recall tools.

AI SDKv1.0.0

LangChain

@wolbarg/langchain

Shared semantic memory as a LangChain store and agent tools.

AI SDKv1.0.0

LlamaIndex

@wolbarg/llamaindex

Drop Wolbarg into createMemory({ memoryBlocks }) as a long-term memory block.

AI SDKv1.0.0

Mastra

@wolbarg/mastra

Use Wolbarg as the durable shared memory backend inside Mastra.

New to Wolbarg?

Start with Workspace for coding agents, or the SDK Quick Start if you are wiring memory into a custom agent loop.