Insights & Updates

Most teams running AI coding agents pay for the same knowledge over and over. We ran 200+ evaluation runs to show how shared memory cuts token usage up to 87% and lifts pass rates from 70% to 100%.

What happens when an agent fails? We analyzed the ROI of Spark shared memory and discovered that costs decrease by 40% on average. The pleasant surprise was the 'fail cheap': even unsolved tasks see a cost reduction of 34%.

A new paper confirms what we've been building toward: curated procedural knowledge improves agent performance by 16%, but agents can't write it themselves. Static skill files don't scale. Shared memory does.

A preprint on AI and software maintainability finds no significant difference in downstream maintainability—and habitual AI users may produce slightly cleaner code. Caveats and takeaways.

When an agent already solves a task 100% of the time, does memory help? Our experiment with bug-fixing in Go shows Spark cuts cost and variance in half—even on the easy problems.

The gap between AI demos and real engineering teams: legacy code, internal APIs, and tech debt. How a shared agentic memory closes that gap with collective continual learning.

AI is surpassing human performance in specialized domains. In software development, agentic knowledge-sharing infrastructure like Spark can outperform the human forums it replaces.

Our first evaluation paper demonstrates that access to Spark's shared, active memory benefits AI coding agents of all sizes—from smaller open-weights models to the largest commercial models.

We're building an agentic workforce. Now we need to build the infrastructure for collective intelligence.

LLMs broke software's most powerful feedback loop — learning from distributed experience. Shared memory can fix it. Our path from code agents to the runtime for agentic systems.

Enterprises succeeding with AI aren't the ones with the most powerful models. They're the ones that figured out how to make organizational knowledge compound through private shared memory networks.

The Hacker News response to Claude's Memory launch reveals a sharp divide: sophisticated users want sovereignty, control, and learning - not accumulation. Here's what the community is demanding.

Andrej Karpathy's vision of separating intelligence from knowledge aligns with our R&D at Memco. Our Spark memory layer enables smaller models to achieve state-of-the-art performance by externalizing specialized knowledge.

As AI performance gains slow, memory becomes the new battleground. We explore service-provider, portable, and community memory architectures, and how they incentivize learning and ownership.

By studying biological memory, we can design more effective memory systems for AI agents that learn, generalize, and strategically forget

How an active memory system enables runtime reinforcement learning, transforming AI agents from static tools into dynamic partners that learn from experience

Building truly autonomous agents requires moving beyond simple retrieval to design active memory systems that can learn, generalise, and strategically forget

Every day, thousands of developers and their AI agents solve the same problems—then forget the solutions. We're building Memco to fix that.

Why collective learning and shared memory are the missing pieces for AI agents

The Developer Flywheel is Broken. How AI agents are replacing humans as the primary consumers of developer tools and documentation.