memco journal

Memory, measured.

Research, engineering practice and field notes on how agents learn from real work — and how that learning becomes reusable company memory.

FeaturedResearchAug 14, 20264 min readLearning on the Job, Batteries IncludedAn agent learns a business's unwritten rules and compliance climbs from 20% to 64%. The harness behind our Learning on the Job paper is now open source, so you can reproduce that curve for about $3.Valentin TablanRead article →

Latest writing.

ResearchAug 14, 20264 min readValentin TablanLearning on the Job, Batteries IncludedAn agent learns a business's unwritten rules and compliance climbs from 20% to 64%. The harness behind our Learning on the Job paper is now open source, so you can reproduce that curve for about $3.
CompanyAug 3, 20265 min readValentin TablanMemory for Knowledge WorkYour teams correct AI assistants every day, but that knowledge disappears with the session. Spark's new Knowledge Work domain turns those corrections into governed organisational memory every assistant can reuse.
EnterpriseJul 29, 20266 min readValentin TablanSovereign AI Needs Sovereign MemorySovereign AI is more than controlling where the model runs. New research shows why organisations should also own the governed, portable memory that gives agents their operational knowledge.
ResearchJul 27, 20265 min readValentin TablanLearning on the Job: Agents Can Learn from the Feedback They Already GetEvery business has feedback its AI agents can learn from. New research shows that external memory turns routine corrections into portable, compounding operational knowledge.
EngineeringJul 2, 20266 min readScott TaylorCoding agents are the wedge. Organizational memory is the prize.Coding agents are the cleanest place to see the agent-memory problem: every run creates evidence, but without trusted organizational memory the next agent starts cold.
EngineeringMay 20, 20266 min readValentin TablanKnowledge Management Systems Are Always Obsolete. Agents Can Fix ThatEvery enterprise knows its knowledge base is out of date. AI agents can finally fix that, but only if the memory infrastructure meets enterprise requirements. We walk through what it takes: identity and access control, knowledge scoping, human oversight, provenance, and data residency.
Agent memoryMay 4, 20264 min readValentin TablanWhy Active Agentic Memory is the Next ShiftHuman-crafted knowledge works perfectly fine, until data-driven learning surpasses it. Explore the historical "Zig and Zag" of AI, and why I believe shared agentic memory is the infrastructure required for the next era of autonomous learning.
EngineeringMay 1, 20266 min readValentin TablanYour Team Knows More Than Anyone On ItMost AI memory tools give back what you put in. With Knowledge Abstraction, Spark derives principles your team never stated, and helps agents avoid problems nobody has encountered yet.
EngineeringApr 17, 20264 min readValentin TablanYour Agent's Memory Is a Markdown File. That's a Problem.Files are the most popular form of agent memory. Here are four things they structurally cannot do.
EngineeringApr 7, 20264 min readValentin TablanYour Coding Agent Remembers Everything, Until It Doesn'tContext windows can retrieve facts with remarkable accuracy, until compaction silently erases the project rules and conventions your team depends on.
EnterpriseApr 5, 20267 min readScott TaylorContinual Learning for Enterprise AI Needs a Memory LayerMost enterprise AI systems do not fail because the model is incapable. They fail because the system cannot retain, refine, and reuse what the organization has already learned.
Agent memoryMar 26, 202613 min readValentin TablanMaking Sense of Agentic Memory: A Map of the Design SpaceThe term 'memory' is used to describe wildly different systems. We map out the design space and explain the choices behind Spark's shared memory architecture.
ResearchMar 16, 20264 min readScott TaylorIf Your Coding Agents Don't Share Memory, You're Burning MoneyMost 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%.
ResearchMar 2, 20264 min readValentin TablanWhat Happens When Your AI Agent Fails?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%.
EngineeringFeb 17, 20264 min readScott TaylorAgents need knowledge they can't generate themselvesA 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.
ResearchFeb 4, 20263 min readValentin TablanAI-Generated Code Might Be More Maintainable Than You ThinkA 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.
ResearchJan 30, 20263 min readValentin TablanWhy Shared Memory Matters Even for "Solved" ProblemsWhen 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.
EngineeringJan 27, 20263 min readValentin TablanWhy AI Struggles with Your Legacy CodeThe 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.
Agent memoryNov 27, 20253 min readValentin TablanBeyond the Human CeilingAI is surpassing human performance in specialized domains. In software development, agentic knowledge-sharing infrastructure like Spark can outperform the human forums it replaces.
ResearchNov 12, 20252 min readValentin TablanSmarter Together: Our New Paper Shows How Shared Memory Lifts All ModelsOur 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.
EnterpriseNov 2, 20257 min readScott TaylorThe Collective Intelligence GapWe're building an agentic workforce. Now we need to build the infrastructure for collective intelligence.
CompanyOct 28, 20254 min readScott TaylorThe Wedge and the Vision: Code to Agentic InfrastructureLLMs 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.
ResearchOct 26, 20253 min readScott Taylor79% of Enterprises Are Deploying AI Agents. Only One Thing Is Missing.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.
EngineeringOct 24, 20253 min readScott TaylorWhat Developers Actually Want From AI Memory: Lessons from 230+ HN CommentsThe 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.
Agent memoryOct 21, 20253 min readValentin TablanKarpathy is Talking About Cognitive Core, We're Building the Memory for ItAndrej 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.
Agent memoryOct 21, 20255 min readScott TaylorMemory Incentives and ArchitecturesAs 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.
Agent memoryOct 14, 20254 min readValentin TablanNature's Blueprint: What Human Memory Teaches Us About Building Smarter AI AgentsBy studying biological memory, we can design more effective memory systems for AI agents that learn, generalize, and strategically forget
ResearchOct 8, 20255 min readValentin TablanReinforcement Learning For AI Agents: Learning on the Job with Active MemoryHow an active memory system enables runtime reinforcement learning, transforming AI agents from static tools into dynamic partners that learn from experience
Agent memorySep 20, 20253 min readValentin TablanThe Art of Forgetting: Why True Memory is the Next Frontier for Autonomous AI AgentsBuilding truly autonomous agents requires moving beyond simple retrieval to design active memory systems that can learn, generalise, and strategically forget
CompanySep 12, 20253 min readScott TaylorIntroducing Memco: the shared memory layer for AI agentsEvery day, thousands of developers and their AI agents solve the same problems—then forget the solutions. We're building Memco to fix that.
Agent memoryJul 18, 20257 min readGabriele FareiAgents That LearnWhy collective learning and shared memory are the missing pieces for AI agents
EnterpriseMay 1, 20256 min readGabriele FareiYour Next User Is Not HumanThe Developer Flywheel is Broken. How AI agents are replacing humans as the primary consumers of developer tools and documentation.

32 of 32 essays · complete archive

The research behind the writing

Papers & benchmarks Methodology The field guide Videos

the loop

benchmarks · product · research

A short dispatch on shared memory for AI agents — the numbers behind the product, what we're shipping, and the research we're reading. No filler.