Promptfoo

Programming — not prompting — LLMs

Declarative framework from Stanford University for programming language models rather than prompting them. DSPy treats LLM interactions as programmable modules with input-output signatures and uses optimization algorithms to automatically compile these modules into effective prompts or fine-tuned weights, replacing brittle prompt strings with structured, modular AI software.

Type-safe LLM function builder

BAML is a domain-specific language by BoundaryML for building reliable AI workflows and agents through schema engineering. It turns prompt engineering into a structured, type-safe discipline by letting developers declaratively define function schemas, validate LLM responses, and version prompts without fragile JSON parsing or boilerplate. BAML reframes prompt engineering as schema definition, making AI workflows testable and maintainable across models.

Structured LLM outputs with validation

Instructor is the most popular Python library for extracting structured, validated data from large language models, with over 3 million monthly downloads and ports across Python, TypeScript, Go, Ruby, Elixir, and Rust. It uses Pydantic models to define output schemas and automatically handles validation, retries, and error correction when the LLM output does not match. Instructor patches existing client libraries instead of replacing them, preserving full access to the underlying API.

Open-source LLMOps platform for prompt management and evaluation

Agenta is an open-source LLMOps platform that combines prompt engineering playgrounds, prompt version management, LLM evaluation, and observability in a unified interface. It supports 50+ LLM models with side-by-side prompt comparison, A/B testing, human evaluation workflows, and OpenTelemetry-native tracing. Self-hostable with 4,000+ GitHub stars.

Open standard for portable skills across AI agents

Agent Skills is the open SKILL.md folder specification for packaging reusable instructions, scripts, references, and assets that compatible AI agents load through progressive disclosure. Originally developed by Anthropic and released as an open standard, it defines the portable format itself—not an example library, marketplace, or hosted agent product.

Test and debug MCP servers before they ship

Open-source platform for inspecting, debugging and regression-testing MCP servers, MCP Apps and ChatGPT apps, with OAuth and protocol conformance for local and CI workflows.

Open-source MCP bridge between AI assistants and the Unity Editor

MCP for Unity is CoplayDev’s MIT-licensed bridge between MCP-compatible AI assistants and the Unity Editor. It exposes tools for assets, scenes, GameObjects, scripts, tests, profiling, and build-oriented workflows. The community project supports Unity 2021.3 LTS through 6.x and is explicitly not affiliated with Unity Technologies.

Sentry-maintained MCP server and CLI for Xcode builds, simulators, and tests

XcodeBuildMCP is a Sentry-maintained, MIT-licensed MCP server and CLI for agent-assisted iOS and macOS development. It lets MCP-compatible coding agents run Xcode build and test workflows, manage simulators, inspect failures, and work through Homebrew, npm, or on-demand client configuration, with documented Sentry telemetry controls for teams that need an opt-out.

Open-source diagnostic for AI operational misalignment

iFixAi is an Apache-2.0 diagnostic tool for scoring AI agents and models against operational-misalignment risks such as hallucination, manipulation, sabotage, sandbagging, and oversight evasion.

UK AI Security Institute framework for LLM safety evaluations

Inspect AI is an MIT-licensed framework from the UK AI Security Institute for running large language model evaluations, including tool use, multi-turn dialogue, model-graded scoring, and reusable evaluation tasks.