DariuszNewecki/CORE
Governance runtime enforcing immutable constitutional rules on AI coding agents
Enforces machine-readable constitutional rules across workflow phases (interpret → plan → generate → validate → style check → execute) using seven specialized enforcement engines (AST, glob, intent, knowledge, workflow, regex, LLM gates) that deterministically block violations before execution. Integrates with Python codebases via PostgreSQL + Qdrant for knowledge storage, providing audit trails and automated remediation through declarative workflows rather than agent-level constraints.
Stars
24
Forks
6
Language
Python
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/DariuszNewecki/CORE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
whataboutyou-ai/eunomia
Eunomia is the open-source authorization layer for AI Agents
rafapra3008/cervellaswarm
Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent...
OrchardHarmonics/orchard-kit
Complete alignment and safety architecture for autonomous AI agents. Membrane security,...
rokabytedev/proofrun
Teach your coding agent to prove its own work — evidence, not claims
imran-siddique/agent-os
[DEPRECATED] Moved to microsoft/agent-governance-toolkit