research engineer · systems + ai infrastructurelocation: lagos, ng · remotestack: go · typescript · postgres · kubernetesopen source: active — agent-railsfocus: memory · authorization · observabilityresearch engineer · systems + ai infrastructurelocation: lagos, ng · remotestack: go · typescript · postgres · kubernetesopen source: active — agent-railsfocus: memory · authorization · observability

Research systems

Research prototypes, not a product catalogue.

Each system states a research question, a threat model, a hypothesis, the experiments that test it, and what is not yet known. Where evaluation is unfinished, it says so. The recurring thesis: reliability is a systems problem, not a model problem.

FlagshipDeep research questions with a full evidence layer.

Agent Guard · GovernanceExperimental

What runtime guardrails make autonomous agents safe enough to act on production infrastructure?

Giving an agent write access to cloud APIs is a structural risk, not a behavioural one. Human approval does not scale, prompt-level rules can be talked around, and pattern matching on commands fails on the first unanticipated encoding. The control has to sit in the execution path, not in the model — and it has to hold up when the model is actively lying to it, not just when it is behaving.

Preliminary resultsRead the evidence

MemKit · MemoryActive

How should long-lived agents retain useful information without memory becoming unbounded, stale, or contradictory?

Most agent 'memory' is vector search over chat history. That is context management, not memory. 'I love my job' and 'I quit' both mention the job and retrieve together on similarity alone -- a naive agent synthesizes both into an answer that's wrong the moment it's assembled. Similarity is not truth. MemKit's starting bet is that solving that problem comes before optimizing recall quality, not after -- the current build deliberately has no semantic search yet, because a fast wrong answer is worse than a slightly slower right one.

Evaluation in progressRead the evidence

Vigilo · ObservabilityActive

Can a host watch itself closely enough that an LLM analyst catches the attack before the irreversible action?

Crypto infrastructure — validators, signers, bridge nodes — has an unusual property: the damage is final the moment a key is used. Detection after the fact is not detection. Vigilo is an OS-level daemon that watches file access, process spawns, and network connections in real time, and pairs a one-second alert path with a slower LLM pass that correlates event sequences into attack patterns.

Evaluation in progressRead the evidence

Supporting infrastructureSubstrate the flagship work depends on.

Agentic Fabric · OrchestrationActive

What does an orchestration layer owe the guarantees below it?

Orchestration frameworks tend to treat memory, authorization, and telemetry as optional plugins. If routine execution can bypass them, the guarantees they provide are advisory. The fabric should make enforcement structural rather than opt-in.

Evaluation in progressRead the evidence

Conflict Lens · EvaluationExperimental

How do you surface contradictions in an agent's knowledge before they become actions?

Contradictory memories rarely announce themselves. They surface as confident, wrong behaviour. Making disagreement visible and inspectable is a prerequisite for trusting a long-lived agent's recall.

Evaluation in progressRead the evidence

Memory MCP · MemoryMaintenance

What does a memory substrate need to expose to be portable across agent runtimes?

The Model Context Protocol standardises tool discovery but says little about state, identity, or trust. A memory server is a good stress test of what the protocol leaves unspecified.

Evaluation in progressRead the evidence