11 boosters for "deterministic" — open source, verified from GitHub, ready to install
Identity Graph Operator ensures all agents in a multi-agent system resolve entities to the same canonical identity deterministically, even with concurrent writes. Developers building multi-agent systems benefit from consistent entity resolution without duplication or conflicts.
A specialized AI agent that automatically detects, classifies, and fixes data anomalies in production pipelines using local SLMs and semantic clustering, with zero data loss guarantee. Data engineers and platform teams benefit most when dealing with broken pipelines that can't afford downtime.
Claw Compactor is a 6-layer token compression skill for OpenClaw agents that reduces workspace token spend by 50–97% through deterministic rules and an LLM-driven memory system called Engram. It's designed for developers building token-efficient AI agents who need automatic cost optimization at session start.
LLM-first SEO analysis skill with 16 specialized sub-skills, 10 specialist agents, and 33 scripts for website, blog, and GitHub repository optimization. For prompt reliability in Codex/agent IDEs, map common user wording to a fixed workflow: When the user requests SEO analysis, follow this routing:
A framework for transforming expert domain knowledge into production-ready AI skills by combining industry expertise with system-specific ontologies. Useful for teams building reliable, specialized AI assistants that need to work consistently across complex business processes.
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "pokemon-skills", "description": "Pokemon Gen 1 Text RPG - An experiment in controlling non-deterministic LLM deterministically through structured data and explicit rules",
"name": "agent-pragma", "owner": { "name": "Peter Wilson" }, "description": "Pragma directives for AI coding agents — deterministic linting, semantic LLM validators, and multi-LLM advisory council for Go, Python, and TypeScript"
A practical guide to writing maintainable, debuggable LLM agent code by addressing unique failure modes like non-determinism, opaque tool calls, and prompt-logic coupling. Developers building Claude-based agents will benefit from these patterns.
Create production-ready AI skills by extracting domain expertise and system ontologies, ensuring reliable performance in real-world applications. Ideal for developers building AI assistants that need deep contextual knowledge.
A multi-agent red-teaming framework that orchestrates coordinated AI security testing with an arbiter to consolidate findings and maintain an immutable audit trail. Security engineers and AI developers use it to systematically test LLM vulnerabilities with repeatable, deterministic results.
FACET is a markup language and authoring system for structured AI prompting that enables human-readable, machine-deterministic configuration across multiple AI platforms (Claude, ChatGPT, Cursor, Windsurf). It helps developers create reusable, validated prompts with strict syntax rules, type checking, and built-in transformations.
