Persistent Memory AI for Applications and Agents

Give your AI true long-term memory. Squish delivers durable context that survives session restarts with semantic search, belief extraction, and automatic memory decay.

What is Persistent Memory for AI?

Persistent memory gives AI agents the ability to remember past interactions, decisions, and user preferences across sessions. Without it, every session starts from scratch.

Belief Extraction and Memory Decay

Squish derives beliefs (decisions, constraints, preferences) from raw observations automatically. Memory decay archives stale context so relevant memories stay visible.

Performance at Scale

39 ops/sec throughput, 6.6ms embedding, 6.1ms semantic search. All running locally with SQLite — zero external dependencies required.

Frequently Asked Questions

What makes Squish different from a vector database for AI memory?

Vector databases store raw embeddings. Squish is a memory runtime that adds belief extraction, memory decay, semantic search, and structured recall on top of local storage.

Is persistent memory AI free?

Yes. The self-hosted Squish runtime is free and open-source under MIT. Squish Cloud adds sync and team features starting at $9/mo.

Can I use persistent memory with multiple AI tools?

Yes. Squish works across Claude Code, Cursor, Codex, ChatGPT, OpenCode, and any MCP-compatible client from a single runtime.

Does persistent memory work offline?

Yes. All core operations — remember, recall, context — work fully offline with the local SQLite database.

Get Started Free

Squish documentation