confident-ai/deepeval
github.com

A testing framework for evaluating the behaviour and quality of applications powered by language models.
Gemt
Lignende links

Ship AI-generated code with confidence
A software-quality platform that coordinates specialised AI agents for testing and governance.
Fælles emne: Kunstig intelligens, Udvikling

Models - TypeSafe AI
Reference information for TypeSafe's Jev models, their API identifiers and operating limits.
Fælles emne: Kunstig intelligens, Udvikling

Introducing System One Models & Jev - TypeSafe AI Blog
TypeSafe introduces Jev and its approach to models that produce structured decisions for software automation.
Fælles emne: Kunstig intelligens, Udvikling

Introduction - TypeSafe AI
An introduction to TypeSafe models that evaluate supplied context and return typed answers for applications.
Fælles emne: Kunstig intelligens, Udvikling

How we built our multi-agent research system
Anthropic describes the architecture, tool design and lessons from building its multi-agent research system.
Fælles emne: Kunstig intelligens, Udvikling

mastra-ai/mastra
A TypeScript framework for developing applications that use AI agents and related workflows.
Fælles emne: Kunstig intelligens, Udvikling
Flere links fra github.com

Job Search MCP
An open-source MCP server that connects AI clients to Hidden Jobs for remote job search. Its documented workflows cover CV comparison, application drafts, interview preparation and application tracking.

dimensional-drawing
To agent-skills til at omsætte UI-komponenter til tekniske tegninger med mål for afstande, hjørner, lag og placering. Den ene skill tegner et specifikationsark; den anden kan animere det.

Reylo
A TypeScript tool for importing SQL files with full type inference and no generated code.

PGX - Lightweight Postgres for AI agents
A Rust database runtime for short-lived, isolated Postgres-compatible databases used by agents, CI and previews. The project describes one process hosting many databases and publishes its own memory and cloning benchmarks. It is marked beta and intended for disposable development databases.

Dialogic
A Godot plugin for conversations, characters, visual novels and story-driven games.

Claude Code Game Studios
A coordinated collection of specialized agents and workflows for game programming, design, art and testing.