Results for “model-optimization”
8 skillsteamwork
Creates and manages AI agent teams for complex engineering tasks, with model routing, cost optimization, and performance evaluation.
10
model-router
Routes AI model requests to the optimal provider based on task, cost, latency, and capability requirements, managing multi-provider LLM deployments.
10
efficient-frontier
Orchestrate expensive frontier models as reviewers and cheaper subagents for bounded, token-heavy work to optimize cost and quality.
3.4k · bundle
More results
model-route
Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.
0
tokenwise
Auto-routes Claude Code subtasks to the cheapest capable model (Haiku/Sonnet/Opus), logs token costs, and A/B tests tiers to validate savings against real workloads.
42.4k
llm-models
Access 100+ LLMs including Claude, Gemini, Kimi, and GLM via the inference.sh CLI with automatic fallback and cost optimization.
584
ai-md
Convert human-written CLAUDE.md files into a structured label format that AI models follow more reliably using fewer tokens.
42.4k
tilegym-cutile-python
Write high-performance GPU kernels using cuTile's tile-based programming model with validation and optimization, including deep agent orchestration for complex multi-kernel tasks.
2.2k · bundle