本页还没有译文
本页 12 段还没译成简体中文，下面显示的是英文原文。Middleware integrations
还没翻译译自英文（docs.langchain.com）本页 12 段都还没译
Browse available middleware for different providers or contribute your own to the ecosystem. Learn more about how middleware works in the middleware overview and how to use middleware with Deep Agents in the Deep Agents docs.
Share your middleware
Middleware enables context engineering, harness customization, and runtime safety controls. It is a useful extension point in LangChain and we love highlighting what the community builds with it:
Follow the contributing guide to build and publish a middleware package.
Open a PR to the docs repo to add your middleware to the table below.
Official integrations
| Provider | Middleware available | Source | Downloads |
|---|---|---|---|
AWS middleware | Prompt caching | langchain-ai/langchain-aws |  |
BrydgeMiddleware | Supervises an agent's tool calls with BRYDGE and checks the destination system's own records to report whether each action happened as permitted. | contactkontey-dotcom/langchain-brydge |  |
RecallMiddleware | Long-term memory for create_agent agents: adds what Recall learned about the user to the system prompt and records each exchange. | recallmem/recall |  |
RecallChatMessageHistory | Chat message history stored in a Recall session, so Recall also learns about the user from it. | recallmem/recall |  |
Anthropic | Prompt caching | langchain-ai/langchainjs | N/A |
Community integrations
Note
The community maintains these middleware integrations. They are contributed on an open-source basis and are not managed or maintained by LangChain.
| Middleware | Description | Source |
|---|---|---|
| langchain-task-steering | Implicit state-machine middleware for ordered task pipelines with per-task tool scoping, dynamic prompt injection, and composable completion validation. | edvinhallvaxhiu/langchain-task-steering |
| Nuggets Authority | Pre-execution authority enforcement for tool calls. Verifies a scoped, signed delegation before each tool runs, fails closed on deny, and emits an independently verifiable cryptographic proof of every decision. | NuggetsLtd/langchain-nuggets |
Have a middleware to share? Open a PR to add it here.