#prompt-engineering

Canvas ChatNew

A branching, canvas-based chat interface for comparing responses across Claude, GPT, Gemini, and other LLMs.

RaunoNew

Ask several AI chatbots the same question at once and watch them compare notes and correct each other.

Context ModeNew

MCP server that sandboxes AI coding agents' tool output and gives them persistent, searchable memory across sessions, claiming 98% context reduction.

HeadroomNew

Open-source library that compresses tool outputs, logs, and JSON before they reach an LLM, cutting token costs 60-95% without changing the answers.

MeetlessNew

A governance layer that captures human-approved decisions and injects them into AI coding agent prompts, flagging conflicts before agents act on stale information.

UXUI Principles

A reference library of research-backed UX rules you can paste straight into Claude, Cursor, or V0 as a prompt — so the interface an AI generates for you follows real cognitive-science principles instead of just looking plausible.

Gate AI

A proxy that sits between your app and the LLM API, blocking prompt-injection attacks and stripping leaked secrets before they reach the model — with an audit trail for every request.

Memmy Agent

A free, local-first memory layer that shares your context and preferences across multiple AI coding assistants like Cursor, Claude Code, and Codex, so you stop repeating yourself.

Parea AI

A dashboard for teams building products on top of ChatGPT-like AI models, so they can test whether a change to their prompt actually made answers better or worse, and watch what the AI is doing once it's live.

SummonAI Kit

A pack of 13 ready-made AI skills that plug into Claude Code, Cursor or Codex so solo founders can also get design, marketing and product work done, not just code.

CMEM

A memory system for AI coding agents that remembers past decisions, fixes, and dead ends, and can sync that memory across different tools and devices.

Claude Reflect

A self-learning plugin for Claude Code that captures your corrections and repeated workflow patterns, then syncs them into CLAUDE.md and config files so the agent remembers them across sessions.

mcp2cli

A free open-source tool that turns any MCP server, OpenAPI spec, or GraphQL endpoint into a plain command-line tool, so an AI coding agent can call it using far fewer tokens than the usual way.

Confident AI

A dashboard that tells you whether your AI feature is actually getting worse or better over time, built on top of a popular open-source testing library instead of asking you to guess from user complaints.

PromptLayer

Collaboration platform for AI teams to manage, test and monitor the prompts that power their LLM applications.

promptfoo

Open-source LLM eval and red teaming: test prompts, compare models, catch jailbreaks and data leaks locally and in CI.