Cascade starts with the last decision
Windsurf rules tell the agent how to behave; they do not tell it what already happened. Awareness records decisions and pitfalls as you work, then recalls them before Cascade plans the next change.
Memory for Windsurf
Give Windsurf persistent memory across Cascade sessions: local Markdown, structured knowledge, and shared context with every other IDE. Free, no account.
Install locally
npx @awareness.market/setup --ide windsurfLocal-first. No account required. The setup CLI writes the rules and MCP config for this IDE.
The problem
Windsurf rules tell the agent how to behave; they do not tell it what already happened. Awareness records decisions and pitfalls as you work, then recalls them before Cascade plans the next change.
The injected rules make the agent load recent decisions and constraints at session start, so it does not re-derive what the last session already settled.
Memory lives in Markdown and SQLite under your project. No account, no API key, and nothing leaves the machine unless you opt into cloud sync.
The same daemon serves every editor and agent. A decision recorded in one tool is available in the next, with project isolation by directory.
How it works
Run the setup CLI. It detects the IDE, writes the MCP config, and injects the workflow rules that make the agent recall before it plans.
No new commands to remember. The agent initializes memory at session start and records decisions as it works.
Open the same project in another editor. The task board and memory are already there.
Awareness injects workflow rules into Windsurf's configuration, so the agent initializes memory at session start, recalls before work, and records decisions after every change. Retrieval runs on local SQLite with hybrid semantic + full-text search; it makes zero LLM calls.
What gets remembered
Compare
Static files someone has to maintain. Awareness is written by the agent as it works, and recall is automatic.
Managed and remote. Awareness is local-first by default: Markdown + SQLite on your machine, no account.
Locked to one tool and one session. Awareness is shared across IDEs and survives restarts.
Yes. The setup CLI writes the MCP config and injects workflow rules, so Cascade initializes memory at session start and records decisions as it works.
By default, yes: Markdown and SQLite under your project. Cloud sync is optional.
Yes. Both point at the same local daemon and the same project directory, so context carries across IDEs.
No. Local-first memory is free forever and needs no account or API key. Cloud sync and team features are optional.
In a .awareness/ directory inside your project: Markdown files plus a SQLite index. It is portable and git-friendly.
A rules file is static. Awareness records what actually happened — decisions, pitfalls, open questions — and the agent recalls it before planning.
Local-first, no account, no credit card. Start in 30 seconds and keep the data on your machine.