Memory

Dawn has three memory mechanisms. Choose by who owns the data and how it should be read; route state and checkpoints preserve workflow execution, but they are not a fourth memory mechanism.

Start with prompt files for small, reviewed context. When records need a schema, governance, retention, or retrieval, the smallest useful memory.ts is:

import { defineMemory } from "@dawn-ai/sdk"
import { z } from "zod"
 
export default defineMemory({
  kind: "semantic",
  scope: ["workspace", "route"],
  schema: z.object({
    subject: z.string(),
    predicate: z.string(),
    value: z.string(),
  }),
})

From this typed collection, continue with Long-term Memory, Recall and Retrieval, Episodes, Distillation, or Browse and Manage Memory, depending on the task.

Workspace profile (AGENTS.md)

If workspace/AGENTS.md exists and has content, Dawn injects it under # Memory on every model turn. It is shared by every consuming agent route and subagent using the same app root; raw graph, workflow, and chain routes do not consume it.

# Workspace Memory
 
- Use pnpm for package commands.
- Prefer short, direct customer replies.
- Escalate billing exceptions to the finance queue.

The default local app root makes this a shared host prompt source. A per-thread sandbox does not isolate that host file automatically. Use separate app roots or trust domains for tenants, constrain untrusted writes, and review seeded content. The Workspace Filesystem guide explains the file tools and backend boundary.

Updating it

See Workspace Filesystem for controlled writeFile access and backend behavior.

Route memory (memory.md)

For stable context that applies to one agent route, place memory.md beside its index.ts:

src/app/research/
  index.ts
  memory.md

# Research Route Memory
 
- Every claim in a report must carry an inline citation to a source you read.
- Prefer primary sources; flag anything you could not verify.

Dawn trims and injects the file under # Route Memory, after workspace/AGENTS.md, on every model turn. Presence is the opt-in: there is no import or registration call. It is a versioned prompt fragment, not a store, and the agent does not write it automatically. Empty files contribute nothing; files larger than 32 KiB are skipped and produce a prompt note.

Long-term collection (memory.ts)

Schemas and write lifecycle: Long-term Memory.

Generated tools

Generated tool contract: Long-term Memory.

How recall ranks

Ranking stages: Recall and Retrieval.

Semantic recall (opt-in)

Embedding-based recall: Recall and Retrieval.

Postgres backend (pgvector)

Shared vector storage: Recall and Retrieval.

The injected index

Prompt index behavior: Recall and Retrieval.

Episodic memory

Run-event concepts: Episodes.

Enabling the run recorder

Recorder setup: Episodes.

What gets recorded

Record shape: Episodes.

Retention

Expiry and caps: Episodes.

Time-windowed recall

Window filters: Episodes.

Governance

Write policy: Episodes.

Agent-authored episodes

Agent-written events: Episodes.

Distillation

Pass selection: Distillation.

Consolidation

Compaction details: Distillation.

Reflection

Insight derivation: Distillation.

Distilled records are found by keyword

Keyword reachability: Distillation.

Provenance

Source provenance: Distillation.

Cost

Cost controls: Distillation.

Running it on a schedule

Scheduling guidance: Distillation.

Distillation configuration

Configuration options: Distillation.

Write governance

Write modes: Long-term Memory.

ask mode

Supervision behavior: Long-term Memory.

Reviewing candidates

Candidate operations: Long-term Memory.

Configuration

Store settings: Long-term Memory.

Testing

Deterministic setup: Long-term Memory.

Verifying against a real model

Live verification: Long-term Memory.

What's deferred

Current limits: Long-term Memory.

Related