#prompt-engineering

Phoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixir

Smart git diff context for LLMs and AI agents: budgeted fragment selection, deterministic, MCP server included

Test, red-team, and deploy LLM applications with confidence. Multi-provider support (OpenAI, Anthropic, Gemini), MCP integration, self-play testing, and production SDK.

Zero-config LLM cost & quality monitoring for Ruby apps - automatically log AI API calls and collect user feedback for analysis using Coolhand.

Local proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).

👩‍💻✍️ Prompt orchestration with Vue/React components. Compatible on any Node.js/browser runtime. No more context rendering and templating

ContextGem: Effortless LLM extraction from documents

Local context engine for AI coding agents. Routes tasks to relevant files, tests, rules, and skills, supports prompt caching, and builds compact context packs for Claude Code, Codex, Cursor, MCP, and more.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Kaboom AI DevTools — Browser DevTools for AI coding assistants via MCP

Every claim machine-checked, including the artifact counts in these badges — governed skills, rules and replayable state. One contract, every host agent.

🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。

🦸 AI 编程超能力 · 中文增强版 — superpowers（116k+ ⭐）完整汉化 + 6 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI 等 16 款 AI 编程工具真正会干活

LLM prompt language based on Jinja. Banks provides tools and functions to build prompts text and chat messages from generic blueprints. It allows attaching metadata to prompts to ease their management, and versioning is first-class citizen. Banks provides ways to store prompts on disk along with their metadata.