Portfolio

Past deployments

Every deployment below ships with a full case study: the operating problem, the technical approach, results you can inspect in public, and the claim boundaries that say exactly what is not being claimed. Each one also names the research pillar it advanced.

Labor market intelligenceLive deployment

KAR

A full-stack labor market intelligence application that connects public economic data with model-assisted analysis.

Results you can inspect

  • The public repository documents a runnable full-stack implementation and production build path.
  • The application exposes macro readings, occupation exploration, scoring, forecasting, and an AI query surface.
  • A live project URL is published from the repository for direct inspection.
ReactTypeScriptTanStack StartTailwind CSSBLS APIGenAI

Research agenda

Read the case study Source
Open-source intelligenceLive deployment

Third Eye

A self-hostable geospatial intelligence interface that brings multiple public data feeds into one analyst workspace.

Results you can inspect

  • The public repository includes runnable local, Docker, and prebuilt-image setup paths.
  • The documented interface unifies multiple intelligence domains and a RECON toolkit in one codebase.
  • The optional Smart System is explicitly feature-flagged, decision-support only, and Human-in-the-loop.
Next.jsTypeScriptMapLibre GLWebGLDockerPublic data APIs

Research agenda

Read the case study Source
Local-first coding agent

Godcoder

A native desktop coding agent with a Rust core, local control, extensible tools, and optional graph-aware retrieval.

Results you can inspect

  • A tagged release provides installable artifacts for Windows and Linux plus a benchmark runner.
  • The architecture documentation separates the reusable Rust agent core from desktop and retrieval adapters.
  • The repository includes a reproducible benchmark workflow rather than relying only on interactive demonstrations.
RustTauriReactTypeScripttree-sitterQdrantFalkorDBBM25

Research agenda

Read the case study Source
AI research automation

ResearchSwarm

An extension of karpathy/autoresearch that adds task routing, bounded execution, and persistent operational memory.

Results you can inspect

  • The repository exposes a runnable CLI for classification, planning, execution, and Human handoff generation.
  • The project structure includes a task classifier, router, persistent memory, tests, and analysis notebook.
  • Public commit history documents ELI Labz updates to the README and changelog for the extension.
PythonPyTorchSQLiteCLI workflowsTask routingEvaluation loops

Research agenda

Read the case study Source
Capability taxonomy

Cognitive Core Skills

A machine-readable taxonomy for reasoning, memory, planning, action, verification, learning, and governance capabilities.

Results you can inspect

  • The repository documents 159 generated skill cards across 13 domains in taxonomy version 1.0.0.
  • Machine-readable artifacts, schemas, benchmark fixtures, and generated documentation are available together.
  • The repository includes a repeatable local validation command and CI workflow.
PythonJSON SchemaYAMLpytestGitHub ActionsGenerated documentation

Research agenda

Read the case study Source
The thread through all of it

Every deployment feeds the research agenda

These are not one-off builds. Each deployment is a public artifact inside the ELI Labz research and development agenda, and the agenda page shows where every pillar stands today.

Read the research agenda Browse all builds
Work with ELI Labz

Hire a Forward Deployed Engineer

Bring one workflow that cannot stay a demo. ELI Labz embeds with your Crew, builds the Intelligent Machine System around it, and proves it with records you can check.

Advisory from $250 per hour (2-hour minimum) • Deployment sprints from $18,000 • Embedded from $32,000 per month • Retainer from $16,000 per month

See services and pricing Generate an engagement brief

Prefer email? dmesa@e-l-i.net