dimensionalOS / dimensionalOS/dimos
Agentic Task Wishlist
Open
Nobody has claimed this yet.
spec
- Dominant language
- Python
- Stars
- 4.5k
- Forks
- 808
- Avg merge
- 3d 5h
- Merged PRs (30d)
- 233
Description
explore the apartment, sit in the corner of the living room, let me know if you see someone, I'll be in the bedroom
- agent runs explore
- agent navigates to living room
- TODO how does agent know where the corner is, turn towards the rest of the room? need costmap understanding
- agent somehow hooks into recongitions? idk
- agent is called by a detector
- navigates to bedroom using semantic map or costamp understanding
- uses speak() skill
drone follow the next white car that passes the intersection
robot is navigating to the kitchen, but on the way to the kitchen, half of the house explodes
- camera image available, periodic calls to agent?
- agent cancels the navigation, calls police or idk instead
alternatively, you tell "hey robot plz stop" and it stops
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files or tests are named. Start by locating the explore and navigation entry points, the detector integration, semantic or costmap handling, and the speak() skill. Define one scenario's expected behavior and identify how completion, interruption, and recognition would be verified.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, robotics
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100