Research Automation
Agents that ingest, synthesize, and broadcast — returning human hours to judgment and care.
A Fleet domain · running on the frozen substrate
The problem it answers
Ingestion, synthesis, and reporting eat the hours that should go to judgment.
Why it matters
Automate the mechanical parts of knowledge work so human time goes to the parts that need a human.
10 Fleet Deployments
The deployments
Open on GitHub. Every system below runs on the same frozen decision substrate — this domain is one more proof that the substrate never needed editing.
objective
activeAutonomous news ingestion, claim extraction, contradiction tracking, and TTS broadcast — entirely on your laptop.
Python
github.com/kliewerdaniel/objective →objective05
activePerpetual intelligence and broadcasting platform — a long-running daemon that continuously ingests information, extracts entities and claims, detects events, narratives, and contradictions, maintains a living knowledge graph, and generates written reports and audio broadcasts.
Python
github.com/kliewerdaniel/objective05 →objective06
activeLocal-first intelligence infrastructure that continuously synthesizes a user's digital existence into a persistent, evolving cognitive model.
Python
github.com/kliewerdaniel/objective06 →synt
productionRevolutionary, air-gapped Local-First Dynamic Persona Intelligence System that transforms large, heterogeneous corpuses into grounded, attributable, and conversationally explorable intelligence using deterministic generative models.
Python
github.com/kliewerdaniel/synt →SynthInt
productionDynamic Persona Intelligence System that transforms large, heterogeneous corpuses into grounded, attributable, and conversationally explorable intelligence.
Python
github.com/kliewerdaniel/SynthInt →dynamic_persona_moe_rag
activeDynamic graph-based Mixture-of-Experts RAG system using persona JSON files and a local Ollama model.
Python
github.com/kliewerdaniel/dynamic_persona_moe_rag →AMIS
activeAutonomous Marketing Intelligence System — turns a corpus of Markdown blog posts into an autonomous marketing knowledge graph that plans, ranks, recommends, and generates campaigns.
Python
github.com/kliewerdaniel/amis →ConCreat
experimentalModern web application for creating and managing multimedia content, featuring AI-powered text-to-speech capabilities using Chatterbox.
TypeScript
github.com/kliewerdaniel/ConCreat →autoblog01
activeInvestigates whether local LLMs can drive a complete content generation pipeline. RSS ingestion, RAG-based writing, and automated publishing on local hardware.
Python
github.com/kliewerdaniel/autoblog01 →RedDiss
experimentalExplores the practical limits of local LLMs for content analysis. Built during the Loco Local LocalLLaMa Hackathon.
Python
github.com/kliewerdaniel/RedDiss →