Prompts, structured output and evals for projects built with AI agents
Prompt management, structured output, tokenizers, evals. 4 tools ranked by how many of 12,697 public projects built with AI coding agents use them, with downloads and GitHub stars. Updated Oct 10, 2026.
| Tool | Used in agent projects | Downloads / wk | GitHub stars | License |
|---|---|---|---|---|
| Ultracite npm AI-ready code formatter that helps write and generate code faster. |
69 (0.5%) | 1.2M | 3,317 | MIT |
| tiktoken pypi Fast BPE tokenizer for OpenAI models enabling accurate token counting and text splitting. |
60 (0.5%) | 46.1M | 19.4K | — |
| tokenizers pypi Fast NLP tokenizer library by Hugging Face for text processing. |
32 (0.3%) | 43.7M | 11.2K | — |
| LangSmith pypi Platform client for monitoring, evaluating and debugging LLM applications. |
23 (0.2%) | 19.3M | 1,072 | MIT |
Nothing here matches. Search all tools →
Other categories
Web frameworks UI components and icons Styling and CSS Animation and motion 3D and graphics Charts and data visualisation Forms, validation and schemas State and data fetching Markdown, editors and content Desktop and mobile apps Utilities Model SDKs Agent, MCP and tool libraries ML and data science Databases, ORMs and clients SDKs for hosted services Auth and security libraries Jobs, queues and workflows Files, images and media Scraping, browsers and parsing HTTP servers and APIs HTTP clients and networking Testing Linting and formatting Languages, types and runtimes Build tools and bundlers Dev workflow and config Logging, monitoring and analytics Crypto and web3 Game development