FlashFeed

Full text

The competitive edge in enterprise AI is shifting to context: which platform can give an agent the right memory, the right retrieval and the right data at the moment of decision.

Couchbase on Tuesday announced its AI Data Plane, combining persistent agent memory, real-time context retrieval and an enterprise-managed MCP server in a single operational platform.

Couchbase's roots are in caching and high-transaction databases — an architecture the company argues makes it better suited for agent memory than vendors that came to the problem from search or analytics. The AI Data Plane runs identically across cloud, on-premises and disconnected edge environments, extending agent memory and local vector search to devices with no network connection.

"How do you make sure that the intelligence that you get out of these models are the ones that databases specialize in?" Gopi Duddi, CTO at Couchbase, told VentureBeat. "How can you get that value out of storage systems, which are still going to be databases?"

What the AI Data Plane delivers

The AI Data Plane packages three components designed to replace the fragmented stacks most enterprises are currently running.

Agent memory: A unified persistence layer for conversational context, structured operational data and vector embeddings. Couchbase says the guardrails are what distinguish it from standalone memory services: token constraints per session, time-to-live limits on stored memories and metering controls that cap compute consumption per agent session.

Enterprise MCP server: An enterprise-supported self-managed server for standardized model-context protocol integration, shipping as part of the platform rather than requiring a separate service.

Agent catalog: A function-level catalog of discoverable agent tooling built by Couchbase. Duddi distinguished it from metadata catalogs like Databricks Unity or AWS Glue — describing it, in his words, as closer to a glorified MCP that surfaces agent functions as callable tools within the platform.

Memory-first architecture takes agent context to the disconnected edge

The lineage of Couchbase and its core architectural foundation is what Duddi says gives it an edge when it comes to context.

"We were a cache before we became a database," Duddi said.

Writing to memory is 10x faster than writing to disk, Duddi said — a speed advantage he argues separates Couchbase from NoSQL databases that layer memory workloads on top of disk-based storage.

Couchbase isn't the only data technology that has its roots in a caching layer. Redis similarly is rooted in cache and also recently announced an agentic AI context layer. Duddi argued that Couchbase is different in that it maintains an ACID (Atomicity, Consistency, Isolation, and Durability) compliant database which matters for transactional workloads. Couchbase also has a long history across multiple deployment modalities.

That architecture extends to the edge through Couchbase Lite, the platform's on-device runtime. It runs SQL, full-text search and vector search locally without a network connection, using a proprietary sync mechanism to replicate bidirectionally back to cloud or between edge nodes when connectivity returns. The target environments are retail floor operations, field service, industrial deployments and regulated settings where agent data cannot leave the device.

Duddi cited hotel reservations as an early example: multiple agents serving customers concurrently, each pulling local context and running vector search on-device, with shared session memory synchronizing centrally. The practical benefit is token efficiency. Rather than every agent independently retrieving and processing the same data, the platform caches shared context so concurrent sessions draw on it without burning tokens repeatedly.

Agora's view from production

Agora, a platform that helps developers embed real-time voice, video and conversational AI into enterprise applications, has run Couchbase in production since February 2024.

The initial use case was its Signaling product, managing channel setup and state synchronization for live calls. Expanding into conversational AI agents brought stricter requirements: memory-first architecture, full JSON support for storage and query, cross-datacenter replication for high availability and enterprise-grade vendor support.

"Couchbase was the best fit based on these criteria," Patrick Ferriter, SVP of Product at Agora, told VentureBeat.

Agora is now extending that relationship to support context retrieval for conversational AI agents.

"This will simplify the architecture and deliver enterprise grade RAG with predictable lower latency required for conversational AI use cases," Ferriter said.

For data professionals trying to figure out the best approach to context, there is no one answer. On platform selection, Ferriter was direct.

"It depends on the preference and goals of the organization, including timing," Ferriter said. "If they want something enterprise grade and optimal for immediate production and scale vs. having to optimize and maintain an open-source solution with community support. We wanted the former and that is why we looked at an expanded partnership with Couchbase."

Competitive context: following the right trend

The context layer has become a crowded space in 2025.

Oracle put a memory core in its database back in March providing a context layer. Redis added a context layer in May as did vector-native database vendor Pinecone .

"Couchbase is following this trend, not setting it, but it's the right one to follow," Devin Pratt, Research Director for AI, Automation, Data and Analytics at IDC, told VentureBeat. "Its real edge is reach, running the same platform from cloud to edge to mobile, which is how enterprises actually operate. The test now is to scale against bigger names."

For teams navigating the vendor landscape, Pratt's framing is direct. "Match the tool to the workload. Consolidate where it makes sense, use a specialized engine like a graph database where relationship-heavy reasoning earns it, and let governance drive the call rather than treating memory as plumbing," Pratt said.

Full text

BOULDER, Colorado — After Earth's moon and Mars, where could humans plant their footprints?

The "Humans to Titan Summit 2026" was held here on June 11 and June 12 to explore the concept of Titan , the largest moon of Saturn , as the next human exploration destination, post-Mars.

Researchers looked into how demanding such a trek could be and what would be required to make it, along with next steps to further that ambitious goal.

A NASA image of Saturn's largest moon, Titan. (Image credit: NASA/JPL-Caltech) Normalizing the idea

As a first-of-its-kind gathering of experts, the Humans to Titan Summit 2026 was invigorating, taking seriously the prospect of one day sending humans to Titan , said Amanda Hendrix, director of the Planetary Science Institute, which is headquartered in Tucson, Arizona.

Hendrix is also president of the advocacy group Explore Titan and co-author of "Beyond Earth: Our Path to a New Home in the Planets" (Pantheon Books, 2016).

"Everyone recognizes that the reality of this is a long way off," Hendrix told Space.com, "but normalizing the idea   — that Titan is actually a very reasonable destination for humans  — is important."

Taking this goal seriously means that "we can have a next destination in our minds, after Mars ," she added. "That keeps the momentum going."

Dense atmosphere

The assembly of experts explored an array of Titan topics, from spacesuits and modes of transportation, habitat designs and airlock concepts to light levels and possible encounters with monsoons and floods on the frigid, exotic moon, which has a weather system based on hydrocarbons rather than water.

Additionally, making use of Titan as a hub for launching sample-return missions to other moons within the Saturn system, like Enceladus , was viewed as a big plus.

So too was utilizing the moon's rich bounty of resources — like methane, nitrogen and oxygen — to fuel expansive, far-deeper exploration beyond Titan itself.

"We've got a lot of planning to do," said Hendrix, "but we have time!"

A top priority is figuring out how to either shorten the trip time to Titan or accommodate it and mitigate the negative effects on astronauts, Hendrix said.

"The top reason in my mind that Titan is such a good spot for humans is the dense atmosphere," Hendrix said. That nitrogen-dominated atmosphere provides natural shielding from harmful radiation of many types.

The first "Humans to Titan Summit" drew a unique cadre of experts. (Image credit: Explore Titan) Precursor missions

Appreciation of what human visitors will face on the moon was boosted by the European Space Agency's robotic Huygens probe , which touched down on Titan on Jan. 14, 2005 as part of the NASA-ESA Cassini-Huygens mission to Saturn.

Next up for setting down on Titan is NASA's nuclear-powered Dragonfly , now projected to launch no earlier than 2028 for a six-year voyage to the faraway moon.

During its over three-year surface mission, Dragonfly's rotors will carry it for miles across Titan's surface, auto-piloting its way to a variety of areas. The vehicle is designed to snag samples of surface material for analysis inside the rotorcraft by scientific instruments.

Amanda Hendrix, director of the Planetary Science Institute and president of Explore Titan, an advocacy group. (Image credit: Barbara David/Future) Extraordinarily ambitious

Taking part in the two-day gathering was Scot Rafkin, director of the Department of Space Studies at the Southwest Research Institute (SwRI) and a planetary and atmospheric scientist. The summit was held at SwRI's Solar System Science & Exploration Division facilities.

"Everyone recognized that sending humans to Titan is extraordinarily ambitious. But history shows that the greatest achievements in exploration begin when people are willing to pursue goals that seem beyond reach," said Rafkin. Sharing with Space.com his own personal thoughts, he said the summit marked "the beginning of a long-term effort to imagine and ultimately achieve something transformative."

Titan is one of the most compelling worlds in the solar system , Rafkin said; it's a place with rivers, lakes, weather, dunes and complex chemistry unlike anywhere else we know of. Pursuing human exploration of Titan, he said, creates a long-term framework and provides a scientific purpose that transcends the moon and Mars.

What the best-dressed Titan explorer may wear. (Image credit: Dijoux and Lee) 'Not a question of physics'

Rafkin said that targeting Titan will also accelerate technologies needed not only for exploring that moon but for voyaging throughout the solar system.

"Human exploration of Titan is not a question of physics," said Rafkin. "It is a question of time, technology, and commitment. We understand most of the major challenges. We know many of the critical science and engineering gaps that remain."

Every advance in propulsion, power systems, manufacturing, robotics, computing, life support and communications, Rafkin said, brings Titan closer while simultaneously enabling exploration throughout the solar system.

Not every solution exists today, Rafkin continued, but the path forward is increasingly clear.

Artistic view of Titan, the largest moon of Saturn. (Image credit: ©Michael Carroll; used with permission) Starting a movement

"Some steps can be taken now, such as sending an orbiter to better characterize the Titan system," said Rafkin. "Other capabilities will require decades or even generations of development. The challenge is immense, but it is achievable."

Rafkin said that the summit was not about planning a mission.

"It was about starting a movement. If space exploration has taught us anything, it is that ambitious goals accelerate innovation in ways we cannot fully predict. The destination is Titan, but the investment is in ourselves," Rafkin concluded.

A second Humans to Titan Summit, said Hendrix, is slated around the launch date in 2028 of the NASA Dragonfly mission.

Full text

Mary Beard has spent 50 years with the ancient Greeks and Romans, but can’t say with certainty who wrote the Odyssey, or what its most famous adjective for Odysseus actually means.

Beard also makes the case for why the Odyssey deserves a serious readership right now, ahead of Christopher Nolan’s upcoming film. She argues no translation should be treated as definitive: every version is an interpretation, shaped by the era that produced it, and the smartest way to read the Odyssey is to read several against each other.

This video Mary Beard: Why no film has ever cracked The Odyssey is featured on Big Think .