by andrii-su
Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.
pypi:datoon · local packagepublished 2 mo ago
Model access, evaluation and agent infrastructure.
Smart structured-data to TOON gateway: converts to TOON only when it saves LLM tokens.
Catholic Social Doctrine AI compass for families. Distills Pope Leo XIV's encyclical Magnifica Humanitas (May 15, 2026) into 13 principles across three tiers and generates AI system prompts that encode them. Available in 15 languages. Designed for parents who want the AI their children use to share…
Agent Help Desk. Search tickets, file if missing, answer others. Register only if authorized.
AI-powered prompt refinement with adaptive questioning and multi-provider support (6+ LLM backends)
Open eval leaderboard + CI gate for autonomous coding agents (solve, score, trace).
Productivity framework for DevOps engineers using AI assistance (Claude Code) while working on PoCs
Revenue intelligence MCP: RFM analysis, 14.5-point ICP scoring, pipeline health. HubSpot.
Multi-workspace Linear MCP — PAT auth, 57 tools + 3 prompts, substrate enforcement, drop-in.
Search a healthcare provider directory and get full provider details by id.
Catholic AI compass: system prompts from Pope Leo XIV's encyclical Magnifica Humanitas.
MCP server for dotnet new: discover, inspect, preview and create .NET projects from templates.
emem is shared memory for AI agents working together in the real world. One agent writes down what it observed. Another agent reads the same bytes, not a summary of them. Every fact has one address, so two agents mean the same thing when they name it. Every fact is signed, so you can check it witho…
Deterministic Artifact Evaluation preflight and run-path grader for research repositories.
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
Choose a profile setting key
Select a reviewer group
Discover public AI agents, reusable recipes, and trusted benchmark evidence by task.
MCP server for AIShelf - allows AI model to choose workflows, rules, skills, and prompts for a task
Search, read, and cite across 152 libraries: 11 tools, 3 prompts, and a full-text resource.
Evidence about ERC-8004 agents on BNB Smart Chain, gathered by calling them. Kawal dials a declared endpoint and reports whether it answered, asks an agent that claims x402 whether it really charges, and reads who wrote its feedback. Nothing here repeats a registry claim without saying so. The same…