Lár: The PyTorch for Agents — The First EU AI Act-Ready Agent Execution Engine Lár — The First EU AI Act-Ready Agent Execution Engine The EU AI Act enforcement deadline is August 2026. Teams building AI agents in finance, healthcare, legal, and enterprise need to prove to regulators exactly what their agent did, why, and what it cost — on every run. Existing frameworks cannot do this. Lár can. Lár is a ground-up agent execution engine where auditability is structural, not an add-on. Every design decision — deterministic graphs, step-level state diffs, cryptographic
| Stars | 13 |
| Forks | 3 |
| Language | Python |
| Category | AI 工具 |
| License | Apache-2.0 |
| Quality Score | 49.68/100 |
| Open Issues | 1 |
| Last Updated | 2026-06-15 |
| Created | 2025-11-09 |
| Platforms | claude-code, gemini, python |
| Est. Tokens | ~22k |
These tools work well together with lar for enhanced workflows:
Explore other popular ai 工具 tools:
lar is Glass-box agent execution engine. Deterministic, forensic audit trails, EU AI Act compliant. The PyTorch for Agents.. It is categorized as a AI 工具 with 13 GitHub stars.
lar is primarily written in Python. It covers topics such as agentic, agentic-ai, agentic-framework.
You can find installation instructions and usage details in the lar GitHub repository at github.com/snath-ai/lar. The project has 13 stars and 3 forks, indicating an active community.
lar is released under the Apache-2.0 license, making it free to use and modify according to the license terms.