Capability statement · CHYNJ / Kaptain · July 2026
Kaptain reduces the operating cost of agentic AI
Kaptain is CHYNJ's model-agnostic Agentic Ecosystem OS: local-first, remotely accessible, licensed, auth-gated, and built for cost control, workflow visibility, and scalable agent operations.
Executive brief
AI agents create recurring operating cost. They repeat context-heavy work, overuse premium models, and turn long workflows into unpredictable token bills.
Kaptain is CHYNJ's paid coordination layer for agentic work: local runtime, trusted remote access, model choice, Krew tools, KodeGraph context, licensing, and workflow visibility in one operating environment.
The product thesis is simple: keep frontier-model reasoning available when it changes the outcome, while routine evidence work, tool calls, local execution, and code-context preparation move through cheaper and more controlled routes.
Market pain
Token spend is becoming operating spend. Agentic systems do not answer once; they search, retry, route, summarize, and keep context alive. That changes AI cost from a prompt-level issue into a persistent workflow-level issue.
Benchmark evidence
The benchmark claims below are tied to Kaptain documentation and internal benchmark artifacts. Lower token counts are cited where recall is comparable, with the clean June 25 benchmark as the primary evidence standard.
Fewer Codex tokens
June 25 exact lookup: 11,438 total Codex tokens with Kaptain + KodeGraph versus 52,241 for Direct Codex, with 1.000 gold-file recall in both runs.
Fewer than a graph-MCP surface — and 10.0% fewer than Direct Codex on the same July 5 run (159,203 vs 176,861), at 1.000 recall on all three
July 5 Go KodeGraph average: 159,203 total tokens versus 322,911 for an external graph MCP baseline, with 1.000 average recall.
Clean June 25 benchmark result
Same exact lookup, same 1.000 gold-file recall: Direct Codex used 52,241 total tokens; Kaptain + KodeGraph used 11,438 total tokens. Kaptain also reduced uncached input tokens, output tokens, tool calls, and wall time in that clean row.
| Metric | Direct Codex | Kaptain + KodeGraph | Result |
|---|---|---|---|
| Gold-file recall | 1.000 | 1.000 | Same answer quality |
| Total Codex tokens | 52,241 | 11,438 | 78.1% lower |
| Uncached input tokens | 19,444 | 9,377 | 10,067 fewer |
| Output tokens | 413 | 141 | 272 fewer |
| Codex tool calls | 2 | 0 | Kaptain supplied context up front |
Current Capability and Next Steps
Impact
Kaptain is designed to reduce unnecessary premium-model usage while keeping frontier reasoning available for planning, synthesis, and high-value decisions.
The impact case is operating leverage: lower AI spend, fewer avoidable cloud-model workloads, better use of local compute, stronger workflow control, and support for sensitive workflows that should remain local and private.
Current measurements in selected benchmark rows show material token reduction, including the 78.1% comparison (a single exact-lookup task, n=1, on the pre-Go codebase) and the July 5 pair above — 50.7% under a graph-MCP surface and 10.0% under Direct Codex on the same run. Kaptain creates this advantage by preparing context earlier and routing suitable work through deterministic flows, local runtimes, and cheaper or local models where appropriate.
Support requested
CHYNJ is seeking mentorship, technical feedback, early users, capital support for broader benchmark infrastructure, and introductions to teams experiencing AI cost pressure in agentic development workflows.
The goal is to move Kaptain from working MVP and early measurements into a disciplined launch: stronger benchmark coverage, reliable onboarding, and a credible path from individual builders to team adoption.