Agent Memory
Ce contenu n’est pas encore disponible dans votre langue.
An agentic worker can remember things across turns and across
sessions. Memory has two tiers, configured in the optional memory block of the worker’s
AgentConfig:
| Tier | Scope | Backing | Runner requirement |
|---|---|---|---|
| Short-term (working memory) | Within a conversation | In-memory provider | Built in; needs a state store to run the worker at all |
| Long-term | Across conversations | Chronicle (persistent) | long-term-chronicle feature + GREENTIC_CHRONICLE_* |
"memory": { "short_term": { "enabled": true }, "long_term": { "provider": "chronicle", "credential_ref": "chronicle-main" }}Short-term (working) memory
Section titled “Short-term (working) memory”Short-term memory is the worker’s scratchpad within a conversation. It is served by an
always-on in-memory provider, so nothing extra is needed to build it — the model gets
remember / recall behaviour when memory.short_term is enabled.
Long-term memory
Section titled “Long-term memory”Long-term memory persists facts across conversations, backed by Chronicle (embedded SurrealDB by default, or an external graph store). Before each turn the worker can surface relevant long-term facts and inject them into the prompt.
Long-term memory is opt-in at the runner build: the runner must be built with the
long-term-chronicle feature, and the tier stays silently disabled unless the Chronicle
environment is configured. It never fails worker startup — an unconfigured tier is simply
inactive.
Reference
Section titled “Reference”| Variable | Purpose |
|---|---|
GREENTIC_AW_REDIS_URL | Required on a server. Conversation state store; unset → dw.agent nodes disabled. |
GREENTIC_CHRONICLE_* | Long-term memory (Chronicle) connection. Absent → long-term tier inactive. |
See also
Section titled “See also”- Agent Types — single_turn, agent_graph, deep_worker
- Agent Knowledge (RAG) — retrieval over an attached corpus