A decision brain for agentic systems: perceive context, compare options, and control execution.
-
Updated
Jun 19, 2026 - Python
#
decision-layer
Here are 11 public repositories matching this topic...
An AI decision assistant that helps you think, decide, and act — powered by Spice.
-
Updated
Apr 10, 2026 - Python
Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.
nodejs open-source mcp developer-tools hermes replay receipts omp codex fail-open agent-harness system-1 decision-routing decision-layer portable-agent
-
Updated
Oct 15, 2026 - JavaScript
Operating framework for AI-assisted work with decision, governance, validation, and learnings before execution.
framework typescript ai artificial-intelligence developer-tools workflows ai-framework governance ai-safety assisted-workflow decision-maker ai-systems design-engineering ai-development ai-developer-tools agentic-systems context-engineering decision-layer
-
Updated
Sep 28, 2026 - TypeScript
The decision layer for AI — typed decisions with confidence before your agent runs. Templates, Decision Schemas and API examples (cURL, Node.js, Python).
-
Updated
Oct 6, 2026 - Python
Emotion understanding system with decision and guidance layer
nlp text-classification feature-engineering emotion-detection error-analysis regression-modelling decision-layer
-
Updated
Mar 20, 2026 - Jupyter Notebook
Jev (TypeSafe System One) sebagai partner keputusan untuk AI agent - agent skill lintas SDK + MCP server + implementasi terukur. Dokumentasi Bahasa Indonesia.
typesafe ai-agents llm copilot-cli mcp-server agent-skills claude-code decision-layer jev system-one
-
Updated
Sep 24, 2026 - Python
A Jev-compatible decision layer as an MCP server: typed noul/choice/score questions with probability distributions and confidence. Pluggable backends (local needle/laya models or any OpenAI-compatible endpoint), calibration tracking, conditions v1, eval harness.
-
Updated
Oct 7, 2026 - JavaScript
A local decision layer for agents and workflows. You hand it a STATE (text or JSON) and a SCHEMA of named questions, each with a fixed list of allowed answers.
-
Updated
Sep 25, 2026 - TypeScript
A2A (AI-to-AI) as a transaction structure shift and executable decision-layer prototype.
-
Updated
Apr 16, 2026 - Python
Add this topic to your repo
To associate your repository with the decision-layer topic, visit your repo's landing page and select "manage topics."