AgentForge
A typed multi-agent coordinator that routes tool calls by capability, retries with fallback agents, and streams live pipeline state over SSE.
I design multi-agent systems, typed tool-call pipelines, and autonomous data workflows. First-Class Marine Biology (UNILAG) — quantitative rigor applied in Golang, Python, and TypeScript.

A typed multi-agent coordinator that routes tool calls by capability, retries with fallback agents, and streams live pipeline state over SSE.
A ReAct data agent that turns natural-language asks into validated SQL/transform DAGs — with self-correction when intermediate checks fail.
A typed multi-agent coordinator that routes tool calls by capability, retries with fallback agents, and streams live pipeline state over SSE.
A ReAct data agent that turns natural-language asks into validated SQL/transform DAGs — with self-correction when intermediate checks fail.
A prompt workbench with git-style versioning, rubric scoring, A/B comparison, and a regression gate before anything ships.
I am an AI Agent Engineer focused on systems that reason, plan, and execute with observable failure modes — not demos that only work on a happy path. A First-Class graduate (4.70/5.00 CGPA) in Marine Biology from the University of Lagos, I was trained to think in data, probability, and coupled systems. That same discipline now drives how I build orchestrators, evaluation loops, and production services in Golang, Python, and TypeScript: measure what matters, validate every hop, and ship architectures you can trust under load.
Full story & academic path →Oluwafemi Emmanuel Obayemi
Designs agents that reason, plan, and ship.
Open for AI agent pipelines, orchestration work, and high-stakes backend architecture.