Skip to content

Release v0.0.11: Dimensional now fully Agent-native, Interactive Visualizer, Drones, Temporal Memory, Fleet control

Latest

Choose a tag to compare

@spomichter spomichter released this 12 Mar 00:26
· 2 commits to main since this release
24c6c58

banner

The Agentive Operating System for Physical Space
https://discord.gg/dimos

Highlights

82 commits, 10 contributors, 396 files changed.

Production CLI and daemon, MCP tooling, temporal-spatial memory, and first-class support for coding agents. Dask has been removed entirely. The full stack now runs from dimos run through dimos stop.

🚀 New Features

Agent-Native Development

DimOS is now built to be driven by coding agents. Point OpenClaw, Claude Code, or Cursor at AGENTS.md and they can build, run, and debug Dimensional applications using the CLI and MCP interfaces directly.

  • AGENTS.md — comprehensive onboarding doc: architecture, CLI reference, skill rules, blueprint quick-reference. Your agent reads this and starts coding. (#1495) by @spomichter

  • MCP server — all @skill methods exposed as HTTP tools. External agents call dimos mcp call relative_move --arg forward=0.5 or connect via JSON-RPC. (#1300) by @PaulNechifor

  • MCP CLI — dimos mcp list-tools, dimos mcp call, dimos mcp status, dimos mcp modules. (#1451) by @spomichter

  • Agent context logging — MCP tool calls and agent messages logged to per-run JSONL for debugging and replay. (#1499) by @spomichter

CLI & Daemon

Full process lifecycle — no more Ctrl-C in tmux.

  • Daemon mode — dimos run --daemon with health checks and run registry. dimos stop, dimos status, dimos restart. (#1436) by @spomichter

  • Structured logs — dimos log -f with per-run JSONL, follow mode, JSON output, and filtering. (#1497) by @spomichter

  • Show config — dimos show-config prints resolved GlobalConfig with source tracing.

Temporal-Spatial Memory

Robots in physical space ingest hours of video and lidar. Temporal-spatial memory gives them a human-like understanding of the world — causal object relationships, entity tracking through time and physical space, and the ability to answer complex temporal queries.

Who spends the most time in the kitchen? What time on average do I wake up? Which set of switches toggles the main lights? Who was at the office at 9am last Thursday?

Traditional frame-level embeddings (CLIP, ViT) lose temporal context and don't scale beyond a handful of frames. Video transformers are expensive and don't operate in RGB-D. Dimensional agents work with video + lidar natively, tracking entities across hours and days.

dimos --replay --replay-dir unitree_go2_office_walk2 run unitree-go2-temporal-memory

(#1511) by @spomichter

Interactive Viewer

Custom Rerun fork (dimos-viewer) is now the default. Click-to-navigate: click a point in the 3D view → PointStamped → A* planner → robot moves. (#1414, #1394) by @spomichter

Drone Support

Drone blueprints modernized to match Go2 composition pattern. drone-basic and drone-agentic work with replay, Rerun, and the full CLI. (#1520) by @spomichter

Perception

Robot Support

Installation & Platform

Core Architecture

Documentation

🐛 Bug Fixes

⚠️ Breaking Changes

  • --viewer-backend renamed to --viewer
  • Dask removed — blueprints using Dask workers need migration to native worker pool
  • Default viewer changed from rerun-web to rerun (native dimos-viewer)

What's Changed

New Contributors

Full Changelog: v0.0.10.post1...v0.0.11