Open-source maintainers
Carry decisions, release context, and review notes forward without adding a hosted account dependency.
Local-first memory for agent-managed workspaces
Agent work, remembered in your workspace.
OpenDream turns local agent activity into reusable memory, then shows what the next agent will receive before it acts.
Agent platform builders
Give cloud co-work, OpenClaw-style loops, and operator handoffs one inspectable memory trail.
Knowledge-base users
Keep notes, research, and vault-style work tied to source material agents should cite later.
Interface surface
See memory behavior before it becomes hidden context.
The browser UI is a readable control room for local memory: runs, retrievals, source links, evals, reviews, and workspace catalog all in one place.
Memory in the workspace
Activate OpenDream inside the workspace you already use. Canonical state stays local, under the workspace folder, without forcing a hosted memory service into the loop.
Readable observability
Inspect recent runs, selected memories, prompt context, review decisions, and workspace health without reading raw JSON first.
Sleep-time maintenance
Dream runs turn agent and operator history into durable, source-linked context so future sessions can recover what mattered.
Skeptical by design
Source links, abstention paths, evaluation reports, and review queues make memory quality inspectable before you trust it.
Memory surface
Health, contested state, type mix, and recent durable memory highlights.
Retrieval log
Prompt-context assembly with query history and selected source links.
Prompt context
The exact context package a later session can inspect before model handoff.
Session timeline
Agent activity, context counts, and event trails stay available after the chat.
Run diff
Memory changes are shown as inspectable diffs before you treat them as truth.
Review queue
Recommended memory decisions before questionable context becomes trusted.
Relationship graph
Use the graph as a quick map of records, runs, retrievals, and context-use links.
Selection loop
Know what shaped the next prompt.
OpenDream shows which memories were selected, why they matched, and which items stayed out of the handoff.
+Selected memories stay linked to their source rows.
+Context use is visible before it becomes agent behavior.
+Safety checks flag stale, low-confidence, or contaminated memory.
Demo videos
Watch the memory loop move.
Current demo clips show the browser UI, local transcript import, and the local memory loop without making the reader infer behavior from still images alone.
Workspace overview
Current workspace overview
Machine-local by default
Built for workspaces that need local truth.
Workspace state remains the source of truth. OpenDream indexes the local memory store you point it at, then helps later sessions pick up context without sending your workspace through a managed memory black box.
Install where work happens
Use the CLI in each workspace, then browse the memory loop locally.
Keep claims inspectable
Reports link memories, prompt context, source events, and eval signals.
Workflow
A short loop for long-lived context.
1
Capture
Agent activity lands as local events, transcripts, and source-linked project notes.
2
Dream
Maintenance turns noisy history into durable, inspectable memory.
3
Retrieve
Task context pulls only memories that fit the current prompt or handoff.
4
Verify
Reports show selected source links, exclusions, and safety checks.
Launch list
Tell us where OpenDream should fit first.
Join the pre-launch list and tell us whether you are interested in OpenDream for an individual workspace, a pro workflow, or enterprise deployment.
First run
Start with one workspace. See what changes.
Install, activate, run the UI, then check the generated memory with the included showcase and release checks.