Use case · Long-term memory
Agents that remember across sessions.
Store what an agent learns as typed memories and recall only what's relevant, so context stays small and nothing is lost between runs.
How it fits
Built from the primitives you already get.
Typed memories
Episodic for what happened, semantic for facts, procedural for how to do things. Each memory has an owner and tags.
Hybrid recall
memory_recall ranks by keyword match, plus vector similarity when you connect an embeddings provider, and filters by kind and tags.
Supersede, keep history
When a fact changes, supersede the old memory instead of overwriting it, so the history stays available.
Roll back bad memories
Snapshot a memory before a long run and restore it if the agent learned the wrong thing.
Build
Local-first development.
Build and test on your machine with the open-source engine. No cloud account needed: every primitive runs locally, with the same API as the cloud.
Install the CLI, then run primitives dev. Quickstart
Open source
Built in the open. Contribute freely.
The SDKs, the MCP server and the single-node engine are open source and actively maintained. Submit PRs, report issues, improve docs, or just star the repo to show support.
useprimitives/primitivesFork, star, or open a pull request