llm 807 typescript 506 cli 460 agents 428 mcp 416 ai-agents 410 ai 399 anthropic 386 rag 362 llmops 346 developer-tools 330 multi-agent 307 agentic-ai 306 bun 299 agent-framework 296 compiler 292 prompt-optimization 292 code-generation 291 slack-bot 288 apache-2-0 287 testing 254 benchmark 191 agent 153 eval 136 openai 133 observability 109 claude 96 evals 94 claude-code 91 llm-evaluation 87 prompt-engineering 82 tracing 68 javascript 61 langchain 59 model-context-protocol 56 open-source 55 prompt 52 regression 49 codex 44 sdk 43 opentelemetry 43 nodejs 42 deepseek-harness 42 dsh 41 ci 40 machine-learning 33 plugin 33 ai-agent 31 metrics 31 ai-governance 30 security 28 gpt 28 mcp-server 28 gemini 28 llm-observability 27 guardrails 27 ml 27 cursor 26 prompt-management 25 python 25 llm-as-judge 25 ai-safety 25 agent-evaluation 24 mlops 24 math 24 agent-skills 24 performance 23 validation 23 dsh-plugin 23 expression 22 benchmarking 21 scoring 21 coding-agents 21 statistics 21 memory 21 monitoring 21 parser 21 audit 20 graph 20 prompts 20 skills 19 agentops 19 safety 19 cordis 19 quality 19 apache-spark 18 prompt-injection 18 mlflow 18 llm-eval 18 model-management 18 copilot 18 react 18 mathematics 18 vitest 17 playground 17 lazy 17 harness 17 incremental 17 analytics 17 automation 17