Nubaeon/empirica
Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and grounded calibration for Claude Code and beyond
Empirica implements a 4-layer memory system that persists findings and learnings across sessions, preventing repeated investigation of the same codebase patterns. It uses a noetic-praxic transaction architecture where AI investigates first (measuring understanding via 13 epistemic vectors), then passes through a Sentinel gate before acting—blocking edits until confidence thresholds from calibration data are met. The system integrates with Claude Code via MCP hooks and system prompt injection, automatically surfacing relevant historical patterns through semantic search over project artifacts while tracking live epistemic state via terminal statusline.
187 stars.
Stars
187
Forks
22
Language
Python
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/Nubaeon/empirica"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
petterjuan/agentic-reliability-framework
ARF is an agentic reliability intelligence platform that separates decision intelligence (OSS)...
sarkar-ai-taken/riva
Local-first observability and control plane for AI agents.
relai-ai/relai-sdk
A platform for building reliable AI agents
soumendrak/ragwatch
An SDK for Python AI Agents. Under heavy development.
imtt-dev/steer
The Active Reliability Layer for AI Agents. Catch failures, teach fixes, and automate reliability