Skip to content

Releases: OpenMind/OM1

v1.0.2-beta.1

14 Apr 00:44
@openminddev openminddev
v1.0.2-beta.1
410a127
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.2-beta.1 Latest
Latest

🚀 What’s New

  • Introduce MCP (Model Context Protocol) tools with reference configs and documentation
  • Add cron job scheduling feature
  • Add G1 arm action support for improved manipulation capabilities
  • Add alternative ASR language support and upgrade ASR modules
  • Add Chirp 3 (V2) ASR documentation with VAD support
  • Introduce auto done_payment handling in ARM zenoh connector

⚙️ Improvements

  • Upgrade runtime to Python 3.12 with updated dependency requirements
  • Refactor LLM action naming and connector configs for consistency
  • Set default knowledge base to om
  • Use environment variables for model IDs
  • Improve code formatting and line length standards
  • Enhance documentation coverage with NumPy-style docstrings and general improvements
  • Update release notes structure and documentation links
  • Lazy-load FAISS and improve dependency handling
  • Upgrade Coinbase plugin

🐛 Bug Fixes

  • Fix ASR prompt format alignment in TTS conversation storage
  • Fix schema script issues
  • Correct turn angle comments (90° → 30°) in zenoh.py
  • Fix GitBook configuration and documentation mappings

📦 Dependency Updates

  • Upgrade core dependencies including:
    • torch, fastapi, aiohttp, requests
    • cryptography, pyjwt, pillow, cbor2, pygments
  • Update development tooling:
    • black formatter
  • Refresh lockfiles and dependency versions across the stack

🧹 Cleanup

  • Remove deprecated LLM plugins and introduce parallel stubs
  • General codebase cleanup and consistency improvements

💼 What's Changed

🙌 New Contributors

** 🔗 Full Changelog**: v1.0.1...v1.0.2-beta.1

Contributors

AlexWUrobot, dependabot, and 7 other contributors
Assets 2
Loading

v1.0.1

15 Mar 19:36
@openminddev openminddev
v1.0.1
664654b
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.1

This new release unifies single and multi modes and improves the stability of mode switching.

What's Changed

Read more

Contributors

flykye, nan1888, and 79 other contributors
Loading

v1.0.1-beta.3

12 Mar 20:20
@openminddev openminddev
v1.0.1-beta.3
b210d35
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.1-beta.3

This new release introduces several new features and fixes various issues.

  • The single mode has been migrated to multi-mode. The same Cortex runtime now supports both single and multiple modes.
  • Fix a bug where the previous LLM could persist when switching between modes.
  • Fix a bug in the callback handling for Riva and Google ASR.
  • Improve the TTS duration calculation for the greeting mode.

What's Changed

New Contributors

Full Changelog: v1.0.1-beta.2...v1.0.1-beta.3

Contributors

nan1888, Farukest, and 20 other contributors
Loading

v1.0.1-beta.2

13 Feb 02:16
@Prachi1615 Prachi1615
v1.0.1-beta.2
071fe75
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.1-beta.2

v1.0.1-beta.2

What's new in this release

  • A huge performance improvement has been added.
  • Standardized the codebase to only support multimode configuration, removing the separate single-mode structure and related folders. Single-mode setups are still supported and are now automatically converted to multimode via the new runtime infrastructure.
  • Added support for monitoring and reporting the charging status of the Unitree Go2 robot.
  • Standardized generic sensor input types with robot-specific variants. New separate background processes added for Unitree G1, Go2 and Turtlebot4.
  • Docker now accepts OM_COMMAND to switch config.
  • Refactored ApproachingPerson background plugin to use Zenoh for person-approaching events.
  • Updated the ElevenLabs TTS integration to reduce latency by switching from JSON/base64 audio responses to a live audio streaming output, and changes the default ElevenLabs output format to PCM at 16kHz.
  • OM1 now supports Isaac Sim.
  • Improved test coverage across plugins.

What's Changed

  • chore(deps): bump protobuf from 5.29.5 to 5.29.6 by @dependabot[bot] in #2134
  • Split odom and rplidar for different robots and add support for G1 by @openminddev in #2136
  • Gitbook migration by @Prachi1615 in #2146
  • Update slogan by @openminddev in #2147
  • fix: correct log messages in KokoroTTSProvider from ElevenLabs to Kokoro by @giwaov in #2151
  • feature/add-unitree-go2-odom-provider-tests by @Wanbogang in #2161
  • fix(logging): preserve exception tracebacks in critical runtime paths by @MuhamadRifansyah in #2149
  • fix: resolve code quality and consistency issues in Kokoro TTS connector by @Wanbogang in #2142
  • fix: properly filter blanked RPLidar angles using any() in _path_processor by @Ridwannurudeen in #2141
  • test(actions): add unit tests for gps action by @LupaFlex in #2133
  • test(actions): add unit tests for face action by @LupaFlex in #2132
  • fix: typo and copy-paste fixes in src/ and config/ by @0xbyt4 in #2127
  • Implement tests for singleton decorator by @kivancbeser in #2107
  • Fix duplicate 'the' typo in UBTECH Yanshee documentation by @erenyegit in #2105
  • docs: fix typos, grammar, and deprecated packages across documentation by @0xbyt4 in #2099
  • refactor: remove unnecessary pass statement in Sensor.init by @eren-karakus0 in #2086
  • fix: remove debug code that randomly inflates ETH balance in production by @letmehateu in #2071
  • Add ApproachingPerson background with Zenoh integration by @openminddev in #2070
  • test: add error handling and edge case tests for DualLLM by @goblin0xcrypto in #2019
  • Fix and update unit tests for OpenAI LLM plugin by @Wanbogang in #2044
  • Add unit tests for zenoh session module by @Wanbogang in #2038
  • fix: ensure timestamp default values match str type annotations in TeleOps dataclasses by @wtoqxy0000 in #2035
  • test: add unit tests for llm output_model module by @Wanbogang in #2005
  • fix(docs): incorrect type hint in battery_turtlebot4 by @windlgrass in #2004
  • fix(docs): incorrect class name in AMCLLocalizationInput docstring by @windlgrass in #2003
  • fix(docs): Optional[Callable] type hints in callback methods by @windlgrass in #2002
  • fix: make SerialReader serial port configurable via config by @MuhamadRifansyah in #1986
  • docs: fix CLI command inconsistency in Installation Guide by @0xEdmundo in #1984
  • test: add unit tests for runtime logging module by @Wanbogang in #1977
  • Add serial connection cleanup to RtkProvider.stop by @aydnOktay in #1955
  • docs(unitree): clarify Linux-only support for realsense provider by @MuhamadRifansyah in #1936
  • fix: add null guard for cortex_loop_task in CancelledError handler by @0xbyt4 in #1913
  • add ChargingStatus and ChargingStatusUnitreeGo2 components for monit… by @jerinpeter in #1807
  • fix: replace blocking requests with async aiohttp in Tesla connector by @0xbyt4 in #1806
  • fix: restore .env.example filename to original convention by @0xbyt4 in #1797
  • docs: fix docstring issues across codebase by @0xbyt4 in #1796
  • docs: fix article usage in llm plugin docstrings by @Katewxp in #1791
  • docs(AvatarProvider): add missing parameter description in send_avatar_command by @s3328537 in #1787
  • Remove duplicate entries in .dockerignore by @AyazKaan in #1785
  • fix: replace blocking requests.post with aiohttp in fabric_closest_peer by @0xbyt4 in #1775
  • fix: add missing separator in resolution format string by @wtoqxy0000 in #1722
  • fix: correct latency calculation using fuser_start_time by @0xbyt4 in #1800
  • fix: add VideoCapture release to prevent resource leak in VLM_Local_YOLO by @0xbyt4 in #1521
  • fix: rename unused loop variables with underscore prefix (B007) by @0xbyt4 in #1450
  • fix: use unique temp file name to prevent race condition by @0xbyt4 in #1801
  • Fix test: expect 'om/' prefix for charging topic by @openminddev in #2167
  • Docs update by @Prachi1615 in #2180
  • update docker file to use OM1_COMMAND from env file by @YuchengZhou821 in #2183
  • fix: initialize dev_jwt and dimo attributes to prevent AttributeError by @0xbyt4 in #2172
  • fix: add missing environment variables to env.example by @DasRasyo in #2153
  • Isaac sim docs by @Prachi1615 in #2205
  • chore(deps): bump pillow from 11.1.0 to 12.1.1 by @dependabot[bot] in #2223
  • Abandon single mode by @YuchengZhou821 in #2204
  • test: add unit tests for 14 missing action connectors by @0xbyt4 in #2206
  • Add error handling to ZenohListenerProvider.stop by @aydnOktay in #2006
  • test: add unit tests for 14 background plugins by @0xbyt4 in #2232
  • Change elevenlabs to use audio output live stream by @shicaih in #2225
  • Restructure docs by @Prachi1615 in #2224
  • Mode docs update by @Prachi1615 in #2237
  • refactor: update configuration and improve ASR message handling across plugins by @openminddev in #2236
  • test: add unit tests for 7 remaining action connectors by @0xbyt4 in #2227

New Contributors

Full Changelog: v1.0.1-beta.1...v1.0.1-beta.2

Contributors

kivancbeser, dependabot, and 23 other contributors
Loading

v1.0.1-beta.1

05 Feb 19:43
@Prachi1615 Prachi1615
v1.0.1-beta.1
699818b
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.1-beta.1

v1.0.1-beta.1

What's new in this release

  • Added support for LimX TRON
  • Ollama support added for local inference
  • Latest config version is now upgraded to v1.0.2
  • Documentation updates
    • We've updated the full autonomy documentation for G1 and Go2
    • Added documentation for Gazebo setup
    • Fixed typos and broken links across documentation
    • Refreshed docstrings throughout the codebase
    • Updated API endpoint documentation
    • Updated API pricing documentation and information regarding the new subscription plans
  • Introduced support for 'concurrent', 'sequential', and 'dependencies' action execution modes in orchestrator and configuration schemas
  • Added greeting conversation mode and state management
  • Added local support for Koroko and Riva model
  • Added person following mode
  • Improved unit test coverage for provider and input plugins

What's Changed

Read more

Contributors

flykye, nan1888, and 61 other contributors
Loading

v1.0.0

17 Dec 21:05
@Prachi1615 Prachi1615
v1.0.0
b564bd6
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.0

What's new in this release?

  • Development Section
    Added a dedicated section to help developers quickly get started with setup, building, and testing.
  • Gazebo
    We now have full simulation support on gazebo with slam, naviation, auto charging for unitree Go2. This leverages users to test OM1 on a simulator without a need to have a physical hardware with them.
  • Config version management
    Updated configuration file to add a new field version. This field ensures that configuration files remain compatible as the runtime evolves.
  • Unitree G1 Full Autonomy
    We now support full autonomy for Unitree G1. It supports Facial detection and anonymisation, 3D SLAM map generation, Navigation.
  • Hot Reload
    Added hot reload support to speed up development by automatically reusing resolved dependencies after the first run. Runtime configuration is persisted via .runtime.json5, enabling seamless restarts and agent switching without full reinitialization.
  • OTA
    Introduced full support for over-the-air updates, enabling users to seamlessly upgrade to the latest runtime versions. Configurations now allow smooth version management and automated deployment of updates.
  • Modes and Lifecycle Documentation
    We have added detailed guidelines in our docs for different modes supported and lifecycle management.
  • Local LLM support for Thor
    Added support for local large language models (LLMs) on Thor with a 3.2-second timeout. When both cloud and local responses are available, the local LLM determines which response to proceed with.
  • Context aware mode transition
    OM1 now supports context-aware mode transitions, allowing autonomous mode switching without human intervention.
  • LiDAR Localization
    Improved localization accuracy using LiDAR sensors.
  • ML Stack Migration
    Moved the machine learning stack to Thor (running on Jetson 7.0). AGX is still supported but with limited capabilities.
  • Runtime version
    Upgraded to the latest runtime version for improved performance and stability.
  • Documentation Fixes
    Corrected typos and improved clarity across the documentation.
  • Introducesd pydantic config
    Refactored the action connector architecture to improve type safety, extensibility, and maintainability by introducing Pydantic-based configurations and stronger generic typing. Added connector-specific config models and enhanced documentation with detailed docstrings for improved clarity and validation.

What's Changed

New Contributors

Read more

Contributors

ShaohongZ, jerinpeter, and 19 other contributors
Loading

v1.0.0-beta.4

24 Oct 22:59
@Prachi1615 Prachi1615
v1.0.0-beta.4
2757b6f

Choose a tag to compare

View all tags
v1.0.0-beta.4

What's new in this release

  • Openrouter support for LLama and Anthropic: Added compatibility with OpenRouter API, enabling seamless access to more AI providers, including Meta’s LLaMA and Anthropic Claude models.
    This allows flexible model selection for natural language processing, reasoning, and control tasks depending on performance or cost preferences.
  • Support multiple modes: We now support 5 different modes with Unitree Go2 full autonomy.
    • Welcome mode - Initial greeting and user information gathering
    • Conversation - Focused conversation and social interaction mode
    • Slam - Autonomous navigation and mapping mode
    • Navigation - Autonomous navigation mode
    • Guard - Patrol and security monitoring mode
  • Support face blurring and detection: The OpenMind Privacy System is a real-time, on-device face detection and blurring module designed to protect personal identity during video capture and streaming.
    It runs entirely on the Unitree Go2 robot’s edge device, requiring no cloud or network connectivity.
    All frame processing happens locally — raw frames never leave the device. Only the processed, blurred output is stored or streamed.
    The module operates offline and maintains low latency suitable for real-time applications
  • Support multiple RTSP inputs: The OpenMind RTSP Ingest Pipeline manages multiple RTSP inputs, supporting three camera feeds and one microphone input for synchronized streaming. The top camera feed is processed through the OpenMind face recognition module for detection, overlay, and FPS monitoring, while the microphone (default_mic_aec) handles audio capture and streaming. All processed video and audio streams are ingested through the OpenMind API RTSP endpoint, enabling multi-source real-time data flow within the system.
  • Support echo cancellation and remote video streaming: Use our portal to remotely display your face in our dog backpack and talk to people directly.
  • Support navigation and mapping: The Navigation and Mapping enables OM1 to move intelligently within its environment using two core modes: Navigation Mode and Slam Mode.
    In Slam Mode, the robot explores its surroundings autonomously, using onboard sensors to build and continuously update internal maps for spatial awareness and future navigation. This mode is typically used during initial setup or when operating in new or changing environments.
    In Navigation Mode, the robot travels between predefined points within an existing mapped area, leveraging maps generated in Slam Mode for path planning, obstacle avoidance, and safe movement to target locations.
  • Refactor AI control messaging: We now use function calls for taking actions.
    Here's our new flow - Actions -> Function calls params -> LLM -> Function calls -> Json Structure (CortexOutputModel).
  • Support Nvidia Thor: We now support Nvidia Thor for Unitree Go2 full autonomy.
  • Added release notes to our docs: The official documentation now includes a dedicated Release Notes section, making it easier to track feature updates, improvements, and bug fixes over time. This also improves transparency for developers and users integrating new releases.
  • Introducing Lifecycle
    Each operational mode in OM1 follows a defined lifecycle, representing the complete process from entry to exit of that mode. A mode lifecycle ensures predictable behavior, safe transitions, and consistent data handling across all system states.

What's Changed

New Contributors

Full Changelog: v1.0.0-beta.3...v1.0.0-beta.4

Contributors

jerinpeter, Prachi1615, and 5 other contributors
Loading

v1.0.0-beta.3

20 Sep 20:59
@Prachi1615 Prachi1615
v1.0.0-beta.3
1cde70f
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.0-beta.3

What's new in this release

  • Downgraded Python to 3.10 for better Jetson support.
  • Integrated Nav2 for state feedback and target publishing, with auto AI-mode disable after localization.
  • Zenoh configs/sessions moved to zenoh_msgs, now preferring local network before multicast.
  • Added avatar background server to communicate with the OM1-avatar
  • Improved avatar animation with thinking behavior and ASR response injection into prompts.
  • Added support for long range control of humanoids and quadrupeds using the TBS_TANGO2 radios.
  • Added sleep mode for ASR, if there's no voice input for 5 min, it goes to sleep.

Docker

📦 openmindagi/om1:v1.0.0-beta.3

What's Changed

Full Changelog: v1.0.0-beta.2...v1.0.0-beta.3

Contributors

Prachi1615, TangmereCottage, and openminddev
Loading

v1.0.0-beta.2

06 Sep 23:02
@openminddev openminddev
v1.0.0-beta.2
c65712e

Choose a tag to compare

View all tags
v1.0.0-beta.2

v1.0.0-beta.2

This release adds support for custom camera indices and enables both microphone and speaker functionality in Docker.

Docker

📦 openmindagi/om1:v1.0.0-beta.2

What's Changed

Full Changelog: v1.0.0-beta.1...v1.0.0-beta.2

Contributors

openminddev
Loading

v1.0.0-beta.1

05 Sep 21:47
@openminddev openminddev
v1.0.0-beta.1
effa68f
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
v1.0.0-beta.1

Overview

First Beta release for OM1
We’re excited to announce the first beta release of OM1, an open-source, modular, and agentic OS for robots. OM1 is hardware-agnostic, enabling developers to prototype, test, and deploy robotics applications without being tied to a specific platform.

Features

  • Multiple LLM provider integrations(OpenAI, Gemini, Deepseek, xAI).
  • GoogleASR model for speech to text.
  • Riva and Eleven Labs for TTS.
  • Preconfigured agents for Unitree Go2, G1, TurtleBot, Ubtech Yanshee.
  • Full autonomy for Go2 with Real-time SLAM, support for RPLiDAR A1/A2/A3 series sensors, Nav2 for autonomous navigation, automatic handling of coordinate frame transforms.
  • Simulator support with Gazebo for Go2.
  • Multi-arch support - AMD64 and ARM64

Docker Image

To initiate the complete setup, start the following docker images (more technical details can be found in our documentation)

📦 openmindagi/om1:v1.0.0-beta.1

What's Changed

Read more

Contributors

bobjiang, ohharsen, and 21 other contributors
Loading