Skip to content

Client Setup

Tenure works with any OpenAI-compatible client. Point it at http://localhost:5757/v1 with your bearer token and it routes through Tenure automatically.

Docker networking note: If your client runs in Docker, localhost won’t resolve to your host machine. Use http://host.docker.internal:5757/v1 instead (Docker Desktop on Mac/Windows) or your host’s LAN IP on Linux.

Chat interfaces are where Tenure does its best work. Brainstorming, deciding, refining; the reasoning that happens here builds your belief store over time.

ClientIntegrationStatus
Open WebUIPoint and shootSupported
LibreChatPoint and shootComing soon
OnyxPoint and shootComing soon

Point and shoot setup: In your client’s API settings, set the base URL to http://localhost:5757/v1 and paste your bearer token. Select any model and start chatting.

IDE clients receive a memory-informed context on every request. Your preferences, decisions, and project conventions are injected automatically without extra setup.

The VS Code extension adds real-time workspace scope resolution, so Tenure knows which project you’re working in before your first message is sent. It covers any IDE built on VS Code.

ClientIntegrationStatus
VS CodeNative extensionSupported
CursorNative extensionSupported
WindsurfNative extensionSupported
ClineNative extensionSupported
ContinueNative extensionSupported
Claude CodePoint and shootComing soon

Point and shoot setup: In your IDE’s AI settings, replace the base URL with http://localhost:5757/v1 and add your bearer token.

Agent integrations run Tenure as a plugin inside the agent framework itself, with automatic per-agent memory isolation. Memory written in one agent never surfaces in another.

ClientIntegrationStatus
OpenClawNative pluginSupported

If you prefer to manage your belief store by hand, extraction can be disabled entirely. Tenure still injects whatever you have authored into every session.

To disable extraction globally: Admin Panel > Settings > Extraction > Enabled: off

To disable per-session, add a request header: X-Tenure-No-Extract: true

Or type !extract off directly in your chat session.