llm 792 typescript 498 cli 454 agents 423 mcp 405 ai-agents 403 ai 392 anthropic 384 rag 356 llmops 345 developer-tools 330 multi-agent 307 agentic-ai 302 bun 299 agent-framework 296 compiler 292 prompt-optimization 292 code-generation 291 slack-bot 288 apache-2-0 287 testing 249 benchmark 182 agent 148 eval 134 openai 132 observability 107 claude 93 evals 90 claude-code 85 llm-evaluation 85 prompt-engineering 80 tracing 67 javascript 59 langchain 59 open-source 54 model-context-protocol 54 prompt 48 sdk 43 regression 42 nodejs 39 ci 39 codex 38 deepseek-harness 36 dsh 35 opentelemetry 34 machine-learning 33 plugin 32 metrics 31 ai-agent 30 ai-governance 29 gpt 28 mcp-server 28 gemini 28 security 27 llm-observability 27 ml 26 guardrails 25 math 25 prompt-management 24 agent-skills 24 agent-evaluation 24 performance 23 mlops 23 python 23 validation 23 expression 23 llm-as-judge 23 parser 22 monitoring 21 scoring 21 benchmarking 21 prompts 20 agentops 19 cordis 19 graph 19 audit 19 safety 19 quality 19 ai-safety 18 prompt-injection 18 skills 18 react 18 llm-eval 18 model-management 18 mathematics 18 mlflow 18 copilot 18 apache-spark 18 vitest 17 coding-agents 17 analytics 17 incremental 17 dsh-plugin 17 harness 17 playground 17 lazy 17 statistics 17 automation 17 cursor 17 llama-index 16