Posts tagged #harness

2 posts

All agent-architecture agent-harness agent-orchestration agent-safety agentic-ai agentic-coding agentic-engineering agentic-memory agentic-systems agents ai ai-agents ai-arbitrage ai-compiler ai-cost-optimization ai-economics ai-engineering ai-reasoning architecture automation cctoggle claude-code clother cloudflare compute-graph context-engineering dns email embodied-ai gonka gpu graph-rag graphify harness hermes-agent inference infrastructure karpathy kimi kimi-k3 knowledge-compilation knowledge-graph knowledge-graphs kv-cache langchain langgraph life-harness llm llm-inference llm-math mcp mixture-of-experts model-routing moonshot-ai multi-agent-systems muxy neurosymbolic-ai notebooklm open-source open-weights openclaude opencode openrouter optimization opus-4.7 orchestration paged-attention plugins productivity providers proxy resend self-improving-ai software-3 terminal tokens tool-calling tooling vibe-graphing vibecoding video vllm youtube

Jul 13, 2026

Teaching Kimi to Speak Claude Code: A Field Guide to Tool-Format Translation

Every utility that translates tool-calling formats between LLM providers — LiteLLM, Bifrost, Portkey, claude-code-router, Vercel AI SDK, first-party /anthropic endpoints — what each one actually does, and the three failure classes none of them have solved. Plus the conclusion I arrived at: stop adapting context downward to each model, and build a harness that orchestrates harnesses instead.

llmclaude-codetool-calling

Jul 10, 2026

The Harness, Not the Model: Why the Same LLM Burns 4× the Tokens Without the Right Scaffolding

A token-efficiency reading of the 'harness > model' thesis: the same model solved 6.7% of tasks bare vs 68% with the right harness — at 4× fewer tokens. What a harness is, why it's where the token bill actually lives, and what the Life-Harness and Meta-Harness papers prove. Plus how your Claude Code stack (subagents, skills, hooks, graphs) already is a harness.

harnessclaude-codetokens