How Volary works
Volary is a memory system for your AI agents.
It lets them automatically learn from past experience and recall that knowledge in future sessions, so they pick up where they left off.
The memory system
Reflections
Volary extracts different kinds of learned knowledge from agent conversations, such as:
- Factual – Concrete facts that the agent had to learn during the conversation, which it will be able to recall next time, e.g.
- “Unit tests are co-located with source files in this repo”
- “Users prefer it when I return them direct links to documentation rather than waiting for them to ask”
- Procedural – Tactical advice to advise the agent how to make more strategic choices in future, e.g.
- “When searching for specific vulnerabilities, I should use a language-specific search engine when available (such as https://pkg.go.dev/vuln) rather than Google”
Learning
After each conversation, Volary analyses the exchange for exploration patterns, errors, and corrections. It extracts reflections automatically, with no manual tagging or configuration needed.
Integration
You can configure Volary as a backend for your agent, simply by changing its API URL. No code changes are needed, and Volary will start reflecting on your conversations immediately. Volary supports sending requests to all major AI backends.
You can also use Volary as an MCP server to integrate into your agent. This lets your agent choose when to recall memories & add them to its context.
Get started
What are you working on?