Ideas, experiments,
and findings.

Technical articles and accessible explanations from across our five research domains.

Formal Optimisation

compere: Multi-Armed Bandit Ranking with Fewer Comparisons

How compere uses bandit algorithms to rank items with minimal pairwise comparisons — applications in search evaluation, recommendation, and tournament design, vs Bradley-Terry and TrueSkill.

multi-armed-banditMABBradley-Terry
Safe Computing

embedcache vs Redis vs GPTCache: Caching for Embedding Computations

A practical comparison of embedcache, Redis vector cache, and GPTCache for eliminating redundant embedding recomputation in RAG pipelines.

cachingembeddingsRedis
LLM Cognition

l0l1 vs Text2SQL Tools: A Privacy-Preserving SQL Co-Pilot for Your Own Database

A practical comparison of l0l1 with generic Text2SQL tools — when the privacy guarantee matters, when the learning from query patterns matters, and when a vanilla LLM SQL bridge is enough.

SQLText2SQLcopilot
Edge Intelligence

llamafu vs llama.rn vs flutter_llama_cpp: On-Device LLM for Flutter in 2026

A practical comparison of llamafu, llama.rn, and flutter_llama_cpp for running LLMs on Flutter — what each does well, what each doesn't, and which to pick.

on-devicellama.cppFlutter
Safe Computing

memista vs Pinecone vs Qdrant vs Chroma: Do You Need a Vector Database?

A practical comparison of memista, Pinecone, Qdrant, Weaviate, Milvus, and Chroma for vector search — and why the answer is usually 'no, you need SQLite'.

vector-searchPineconeQdrant
LLM Cognition

mullama vs Ollama vs vLLM: Choosing a Local LLM Server in 2026

A practical comparison of mullama, Ollama, vLLM, LocalAI, and LM Studio for local LLM serving — when to use which, and why you might pick the research-instrumented option.

OllamavLLMLocalAI
LLM Cognition

perishable vs Cloudflare API Gateway vs HashiCorp Vault: Short-Lived Credentials for LLMs

A practical comparison of perishable, Cloudflare API Gateway, and HashiCorp Vault for ephemeral LLM API credentials — when zero-trust LLM access needs its own purpose-built tooling, and when a general-purpose solution is enough.

zero-trustephemeral-credentialsCloudflare
Safe Computing

polymathy vs Haystack vs LangChain: Building RAG Pipelines in Rust

A practical comparison of polymathy, Haystack, and LangChain for building RAG pipelines — when you want a Rust-native async chunking + embedding service, and when the Python frameworks are still the right answer.

RAGHaystackLangChain
LLM Cognition

route-switch vs LiteLLM vs Portkey vs OpenRouter: LLM Routing in 2026

A practical comparison of route-switch, LiteLLM, Portkey, and OpenRouter for LLM routing — when you need a gateway, when you need a learned router, and when you need both.

LLM routingLiteLLMPortkey
Formal Optimisation

savanty: Bridging Natural Language and Mathematical Solvers in 2026

How savanty turns English problem descriptions into mathematically guaranteed solutions. The case for LLM-to-formal-solver pipelines over pure LLM output.

constraint-satisfactionSMT solverZ3
Cross-Cutting

Skelf Research: The Independent Lab That Ships Research as Code

How Skelf Research compares to Big Tech AI labs, AI startups, and individual researchers — what 'independent AI research lab publishing open-source software' means in 2026, and why the methodology is the moat.

AI research labopen sourceopen science
Edge Intelligence

slorg vs Algolia vs Meilisearch vs Typesense: Deliberative vs Traditional Search

A practical comparison of slorg, Algolia, Meilisearch, and Typesense for search — when deliberative search (reasoning before retrieval) is the right answer, and when traditional search is still the right answer.

searchAlgoliaMeilisearch
Edge Intelligence

ukkin vs ChatGPT Operator vs Anthropic Computer Use: On-Device vs Cloud AI Agents

A practical comparison of ukkin, ChatGPT Operator, and Anthropic Computer Use for autonomous mobile and desktop AI agents — privacy, autonomy, and the on-device vs cloud trade-off.

agentsmobileautonomy
Robotics

waremax: Deterministic Warehouse-Robotics Simulation for RL Research

How waremax gives warehouse-robotics research a deterministic simulator, a Gymnasium RL interface, and instrumented delay attribution. Why deterministic beats plausible for reproducible research.

warehouse-roboticsRMFSAMR
Safe Computing

zviz vs gVisor vs Firecracker: Choosing a Sandbox for AI-Generated Code

A practical comparison of zviz, gVisor, and Firecracker for sandboxing untrusted AI-generated code — performance, security, and operational trade-offs.

sandboxinggVisorFirecracker
LLM Cognition

memorg vs Mem0: Structured Memory vs Vector Memory for LLM Agents

A practical comparison of memorg and Mem0 for agent memory — when structured schemas beat vector recall, when they don't, and how to combine them.

memoryagentsMem0
LLM Cognition

mpl vs MCP: A Compliance and Audit Layer on Top of the Agent Protocol

MCP defines how agents talk. mpl defines what correct looks like. Why production agentic systems need both — and how to compose them.

MCPA2Aagent-protocol
LLM Cognition

promptel vs DSPy: Declarative Specification vs Programmatic Compilation

A practical comparison of promptel and DSPy for prompt engineering — when to use a declarative specification language, when to use a programmatic compiler, and how they compose.

promptsDSPydeclarative
Safe Computing

Programmable Databases: Why We Built liath Twice

The story of building a Lua-native database in Lua, then rewriting it in Rust with RocksDB — and what the performance tells us.

databaseluarust
Edge Intelligence

Deliberative Search: When the Engine Reasons Before It Retrieves

Why traditional search retrieves first and ranks later — and how slorg inverts this by understanding intent before fetching results.

searchSvelteKitreasoning
LLM Cognition

Persistent Memory for Long-Running Agents

What happens when LLM agents need to remember across sessions — structured memory schemas, retrieval strategies, and the memory-context distinction.

memoryagentsretrieval
Safe Computing

Vector Search Without the Cloud: memista's SQLite-Backed ANN

Building approximate nearest-neighbour search on SQLite in pure Rust — and why you might not need a dedicated vector database.

vector-searchSQLiteANN
Cross-Cutting

Ephemeral Credentials and Zero-Trust AI: Rethinking API Security

Why AI agents need scoped, time-limited credentials — and how perishable implements zero-trust patterns for LLM API access.

securityzero-trustcredentials
LLM Cognition

Prompt Lifecycle Management: From Extraction to Deployment

A practical framework for managing prompts as versioned dependencies — tackling drift, regression, and reproducibility.

promptsversioningdevops
Formal Optimisation

Better Rankings with Fewer Comparisons: Multi-Armed Bandits for Efficient Ordering

How compere uses MAB algorithms to rank items effectively with minimal pairwise feedback — applications in search and recommendation.

MABrankingbandits
LLM Cognition

Formalising Prompts as First-Class Research Objects

Why treating prompts as typed, portable artefacts changes how we reason about LLM behaviour — and how promptel implements this idea.

promptsformal-methodsspecification
Formal Optimisation

From English to Optimal: How savanty Bridges Natural Language and Constraint Solvers

Describe optimisation problems in plain English and receive mathematically guaranteed solutions — no PhD required.

NLPconstraint-satisfactionsolvers
LLM Cognition

Intelligent LLM Routing: Spending Compute Where It Matters

How route-switch uses MIPROv2 to automatically select the right model for each query — balancing cost, quality, and latency.

routingMIPROv2cost-optimisation
Edge Intelligence

Autonomous Mobile Agents: ukkin's Architecture for On-Device AI

Building AI agents that browse, observe, and automate tasks entirely on-device — the autonomy-safety spectrum on mobile.

agentsmobileautonomy
LLM Cognition

Building mullama: What We Learned Replacing Ollama from Scratch

A post-mortem on building a local LLM serving layer — llama.cpp integration, model management, and where existing tools constrain research.

llama.cppinferencelocal-llm
Edge Intelligence

Running Language Models on Your Phone: The llamafu Experiment

What happens when you run a full LLM on mobile hardware with zero cloud dependency — memory, latency, and model quality on consumer devices.

mobilellama.cppflutter
Safe Computing

Sandboxing Untrusted Code in Zig: The zviz Architecture

How zviz uses Zig's comptime capabilities to build gVisor-inspired sandboxing with near-zero runtime cost.

zigsandboxinggVisor
Safe Computing

Why We Write AI Infrastructure in Rust (and Zig, and Go)

Language choice as research methodology — how memory-safe, deterministic-performance languages produce falsifiable systems claims.

rustziggo
Formal Optimisation

Compiling Trading Signals: sigc and the Quantitative Hypothesis Pipeline

From visual signal specification to verified Rust executable — how sigc turns alpha hypotheses into production-ready code in minutes.

quantsignalscompiler
Cross-Cutting

Open Science in AI: Why We Publish Everything

The case for radical openness in AI research — reproducibility, falsifiability, and community trust through 25 open-source projects.

open-scienceopen-sourcereproducibility