dimensionalOS / dimensionalOS/dimos

Memory questions

Open
#1,418 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

research
Dominant language
Python
Stars
4.5k
Forks
808
Avg merge
3d 5h
Merged PRs (30d)
233

Description

1. "where was I when this log line was added?"
  • pose lookup from a timestamp
2. "how long have I been observing the red socks currently in view?"
  • how many times did I see them before?
  • temporal duration tracking + observation frequency
3. "how many people did I see during last week?"
  • assume we are generating a facial recognition db — is this matching a face detection stream, then embeddings? then we are searching over that stream?
4. "where did you see red socks during last week?"
  • we query for red socks embedding similarity, then feed this data into a VLM that further filters for socks
  • is this data output into some table? is it like an ObservationSet again?
  • then we can create a map (costmap) of red socks?
5. "did anyone ever open this door? at what times did I see this door open? who opened it?"
  • event detection + temporal querying of state changes
6. "I have a transcription log (STT) and voice embeddings, how do I figure out who is saying what?"
  • cross-stream correlation: audio → identity
7. "I have parallel voice and facial recognition streams, how do I correlate voice to people?"
  • I don't see all people speaking at all times
  • multi-modal fusion with incomplete overlap
8. "what's different in this room compared to yesterday?"
  • comparing scene snapshots across time, diffing object sets
  • requires baseline modeling / temporal comparison
9. "show me everywhere the cat went today"
  • continuous spatial tracking over time, not point queries
  • dense pose-stream retrieval + path aggregation
10. "what happened in the 30 seconds before the vase fell?"
  • event-anchored temporal window across all streams
  • multi-stream temporal slicing relative to a detected event
11. "when was the last time I did NOT see the cat in the apartment?"
  • finding gaps in an observation stream
12. "what time does the mailman usually come?"
  • aggregation across days, extracting temporal regularity from sparse events
  • cross-session pattern extraction
13. "what did robot-2 observe in the warehouse that I missed?"
  • cross-agent memory diff
  • session/robot-scoped queries and set difference across streams
14. "how far did I travel while carrying an object?"
  • only accumulate distance when a parallel detection stream has a positive signal, or between log entries?
  • cross-stream conditional joins

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No files, tests, or entry points are named in the issue; begin by locating the project's existing memory, observation, and stream-query components. The issue lists many open-ended capabilities rather than one bounded change, so completion criteria must be defined before implementation can begin.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, data
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.