DSPy

An AI prompt optimizer that searches the prompt space against benchmark labels and revises instructions using failure feedback. In the described workflow, it searches for shorter instructions while preserving the application's interface and scoring contract; candidate prompts still require quality testing because benchmark-specific optimization can fail on unfamiliar inputs.

effortless is an MIT-licensed Claude Code plugin that automatically selects the reasoning effort for each prompt using a judge model, so simple prompts can use lower effort while harder tasks use higher effort. It uses Haiku 5.5 by default, with optional Jev judging through TypeSafe, and keeps short follow-ups at the previously selected effort. A status bar shows the selected effort and model, context usage, prompt-cache time, judge explanation, usage warnings, and controls for compaction or handing a session off to a fresh chat. Handoff creates a summary and continues in a new chat; compaction uses Haiku 5.5 by default and falls back to Claude Code's normal compaction if needed. An experimental setting can route simple prompts to a cheaper model, but it is disabled by default because switching models can require rebuilding the prompt cache. The plugin runs locally as Claude Code hooks, provides commands for settings, benchmarking, diagnostics, statistics, handoff, and updates, and can be installed through Claude Code's plugin marketplace.

Procedura is an open-source agentic 3D-modeling tool from SpatiaOS that converts text prompts into editable procedural assemblies rather than point clouds or triangle meshes. It generates OpenSCAD source with named parts and typed mates, plans and builds parts incrementally, and can use reference images and optional Blender render feedback during refinement. Optional passes assign per-part PBR materials and plan articulation, exporting motion to OpenUSD and URDF with Isaac-based validation. It runs locally as a Bun/TypeScript pipeline using a configurable OpenAI-compatible, Gemini, or local model endpoint; it does not provide hosted inference or API keys. The pipeline uses a Manifold-capable OpenSCAD build to compile the generated programs and Blender for renders, and includes a web Studio for composing runs and inspecting intermediate artifacts. The repository is MIT-licensed.

Promptfoo is an AI application security and evaluation platform for testing prompts, RAG systems, agents, models, and guardrails. It can run evaluation tests with LLM-judge scoring against defined criteria and verify citations against source documents; in the described payment-rules assistant, it was used to assess answer quality and investigate apparent regressions against the underlying evidence. Its security workflows simulate context-aware attacks, including prompt injection, jailbreaks, data leaks, business-rule violations, insecure agent tool use, and toxic-content generation, and can run in development and CI/CD workflows. Promptfoo also provides automated red teaming, code scanning, MCP security testing, remediation guidance, and continuous monitoring, with integrations for AI applications, agent frameworks, CI/CD systems, and on-premises or cloud deployments.

Simulan is an open-source, JavaScript-based language from Simular for writing deterministic, replayable computer-automation workflows. It provides a symbolic automation layer for computer use, analogous to Playwright for browser automation, and can be used from the terminal or written through coding agents such as Claude Code. Workflows can be saved as reusable skills and replayed; when the environment changes or a fixed step fails, model-driven exploration can help recover before execution continues.