As workplace knowledge spreads across chats, AI firms are building systems that can structure, retrieve and preserve it over time.
Updated
May 11, 2026 5:24 PM
A messaging app on a phone. PHOTO: ADOBE STOCK
Votee AI, an enterprise AI company headquartered in Hong Kong, has partnered with its Toronto-based research lab Beever AI to launch Beever Atlas. The new platform is designed to turn workplace chats into searchable knowledge that AI systems can retrieve and understand.
The release focuses on a growing issue inside organisations. Much of today’s workplace knowledge now exists inside chat platforms such as Slack, Microsoft Teams, Discord and Telegram. Important discussions, project decisions and technical information often disappear into long message histories that are difficult to search later.
Beever AI developed the platform to organise those conversations into a structured system for AI assistants. The software connects with Telegram, Discord, Mattermost, Microsoft Teams and Slack, then converts conversations into linked records of people, projects, files and decisions.
The collaboration combines Votee AI’s enterprise infrastructure work with Beever AI’s research around AI memory systems. The companies are releasing two versions of the product. The open-source edition is aimed at individual developers, researchers and creators. The enterprise edition is designed for banks, government agencies and larger organisations with stricter security requirements.
The release also reflects a broader shift happening across the AI industry. Companies are increasingly looking at how AI systems store and retrieve long-term knowledge, rather than relying solely on large context windows or search-based retrieval.
Earlier this year, OpenAI founding member and former director of AI at Tesla Andrej Karpathy discussed the growing need for what he described as “LLM Knowledge Bases.” He argued that AI systems need structured and evolving memory rather than depending only on context windows and vector search.
Beever Atlas approaches that problem through workplace communication. Instead of focusing mainly on uploaded files, the system is designed around conversations that happen daily across team chat platforms. It can also process images, PDFs, voice notes and video files within the same searchable system.
The companies say the software is designed to work directly with AI assistants and coding tools such as Cursor, AWS Kiro and Qwen Code. Integrations for OpenClaw and Hermes Agent are expected later in 2026.
Pak-Sun Ting, Co-Founder and CEO of Votee AI said: "Hong Kong has always been known for property and finance. Beever Atlas is proof that world-class AI infrastructure can emerge from an HK-headquartered company and be shared openly with the world. Every growing organization faces the same silent liability: conversational knowledge loss. Beever Atlas turns this perishable resource into a compounding organizational asset."
A large part of the enterprise version focuses on privacy and access control. The system mirrors permissions from Slack and Microsoft Teams so users can only retrieve information they are already authorised to access. Permission updates are reflected automatically when access changes inside company systems.
The enterprise edition also includes audit logs, encryption controls and data retention settings for organisations handling sensitive internal data. Companies can run the software entirely inside their own infrastructure using Docker and connect it to their preferred AI models through LiteLLM.
The companies argue that organising information is more useful than simply storing chat archives. Jacky Chan Co-Founder and CTO of Votee AI said: "The key technical decision was to treat agent memory as a knowledge engineering problem, not a retrieval problem. Structure beats similarity — a typed graph of who works on what is more useful to an AI than vector search over a Slack archive."
The software also includes protections against prompt injection attacks and systems designed to reduce hallucinated responses. According to the companies, the AI is designed to return “I don't know” with citations when confidence is low instead of generating unsupported answers.
As workplace communication becomes increasingly fragmented across chat platforms, companies are beginning to treat internal conversations as information that AI systems can organise, retrieve and build on. Beever Atlas reflects a broader push to turn everyday workplace communication into long-term organisational memory.
Keep Reading
CES 2026 and the move toward wearable robots you don’t wear all day.
Updated
January 28, 2026 5:53 PM
The π6 exoskeleton from VIGX. PHOTO: VIGX
CES 2026 highlighted how robotics is taking many different forms. VIGX, a wearable robotics company, used the event to introduce the π6, a portable exoskeleton robot designed to be carried and worn only when needed. Unveiled in Las Vegas, the device reflects a broader shift at CES toward robotics that move with people rather than staying fixed in industrial or clinical settings.
Exoskeletons have existed for years, most commonly in controlled environments such as factories, rehabilitation facilities and specialised research settings. In these contexts, they have tended to be large, fixed systems intended for long sessions of supervised use rather than something a person could deploy on their own.
Against that backdrop, the π6 explores a more personal and flexible approach to assistance. Instead of treating an exoskeleton as permanent equipment, it is designed to be something users carry with them and wear only when a task or situation calls for extra support.
The π6 weighs 1.9 kilograms and folds down to a size that fits into a bag. When worn, it sits around the waist and legs, providing mechanical assistance during activities such as walking, climbing or extended movement. Rather than altering how people move, the system adds controlled rotational force at key joints to reduce physical strain over time.
According to the company, the device delivers up to 800 watts of peak power and 16 Nm of rotational force. In practical terms, this means the system is designed to help users sustain effort for longer periods, especially during physically demanding activities_ by easing the body's load rather than pushing it beyond normal limits.
The π6 is designed to support users weighing between 45 kilograms and 120 kilograms and is intended for intermittent use. This reinforces its role as a wearable companion — something taken out when needed and set aside when not — rather than a device meant to be worn continuously.
Another aspect of the system is how it responds to different environments. Using onboard sensors and processing, the exoskeleton can detect changes such as slopes or uneven ground and adjust the level of assistance accordingly. This reduces the need for manual adjustments and helps maintain a consistent walking experience across varied terrain, with software fine-tuning how assistance is applied rather than directing movement itself.
The hardware design follows a similar logic. The power belt contains a detachable battery, allowing users to remove or swap it without handling the entire system. This keeps the wearable components lighter and makes the exoskeleton easier to transport. The battery can also be used as a general power source for small electronic devices, adding a layer of practicality beyond the exoskeleton’s core function.
VIGX frames its work around accessibility rather than industrial automation. “To empower ordinary people,” said founder Bob Yu, explaining why the company chose to focus on exoskeleton robotics. “VIGX is dedicated to expanding the physical limits of humans, enabling deeper outdoor adventures, making running and cycling easier and more enjoyable and allowing people to sustain their outdoor pursuits regardless of age.”
Placed within the wider context of CES, the π6 sits alongside a growing number of portable robots and wearable systems that prioritise convenience, mobility and personal use. By reducing the physical and practical barriers to wearing an exoskeleton, VIGX is testing whether assistive robotics can move beyond niche environments and into everyday life. If that experiment succeeds, wearable robots may become less about dramatic augmentation and more about quiet support — present when needed and easy to put away when not.