Determinism ends up mattering more than intelligence once agents touch real systems. While building GTWY, we saw that making execution paths inspectable reduced failures far more than swapping models.
I've spent the last few months building Lár (Irish for "core"). It's a Python framework for building AI agents, but heavily inspired by the philosophy of "Glass Box" engineering rather than magical "Black Boxes".
The Problem:
Most agent frameworks today (LangChain, AutoGen) feel like magic. They hide the prompt chains, the state transitions, and the retry logic. When they break in production, debugging is a nightmare.
The Solution:
Lár is designed to be the "PyTorch for Agents". It uses a "Define-by-Run" architecture where:
1. Agents are just directed graphs (Nodes + Edges).
2. Every state transition is immutable and logged.
3. The engine produces a JSON "Flight Log" that makes the agent 100% auditable (useful for 21 CFR Part 11 compliance in healthcare/finance).
Tech Stack:
- IDE Friendly: Clone, `pip install`, and run. Build an agent in minutes.
- Zero Friction Models: Switch from Cloud to Local in 1 line. Just change `"gpt-4"` to `"ollama/phi4"`. No code refactoring.
- Hybrid Architecture: We proved that using code for logic (instead of LLMs) makes Lár 60x cheaper and significantly faster than standard "Chain" frameworks.
- Enterprise Patterns: Includes 18 Core Patterns out of the box (e.g., A/B Testing, Resumable Graphs, Security Firewalls).
- Just-in-Time Integrations: Don't wait for API wrappers. Drag our "Integration Builder" prompt into your IDE and get a type-safe tool in 30 seconds.
- Air-Gap Capable: No telemetry, no hidden clouds. Run entirely offline.
It’s open source (Apache 2.0). I’d love to hear what you think about the "Audit-first" approach vs the current "Chat-first" trend.
Determinism ends up mattering more than intelligence once agents touch real systems. While building GTWY, we saw that making execution paths inspectable reduced failures far more than swapping models.
Hey HN,
I've spent the last few months building Lár (Irish for "core"). It's a Python framework for building AI agents, but heavily inspired by the philosophy of "Glass Box" engineering rather than magical "Black Boxes".
The Problem: Most agent frameworks today (LangChain, AutoGen) feel like magic. They hide the prompt chains, the state transitions, and the retry logic. When they break in production, debugging is a nightmare.
The Solution: Lár is designed to be the "PyTorch for Agents". It uses a "Define-by-Run" architecture where: 1. Agents are just directed graphs (Nodes + Edges). 2. Every state transition is immutable and logged. 3. The engine produces a JSON "Flight Log" that makes the agent 100% auditable (useful for 21 CFR Part 11 compliance in healthcare/finance).
Tech Stack: - IDE Friendly: Clone, `pip install`, and run. Build an agent in minutes. - Zero Friction Models: Switch from Cloud to Local in 1 line. Just change `"gpt-4"` to `"ollama/phi4"`. No code refactoring. - Hybrid Architecture: We proved that using code for logic (instead of LLMs) makes Lár 60x cheaper and significantly faster than standard "Chain" frameworks. - Enterprise Patterns: Includes 18 Core Patterns out of the box (e.g., A/B Testing, Resumable Graphs, Security Firewalls). - Just-in-Time Integrations: Don't wait for API wrappers. Drag our "Integration Builder" prompt into your IDE and get a type-safe tool in 30 seconds. - Air-Gap Capable: No telemetry, no hidden clouds. Run entirely offline.
It’s open source (Apache 2.0). I’d love to hear what you think about the "Audit-first" approach vs the current "Chat-first" trend.
Website: https://snath.ai Docs: https://docs.snath.ai Repo: https://github.com/snath-ai/lar
3 Killer Demos:
1. Self-Healing Code Agent: https://github.com/snath-ai/code-repair-demo 2. Glass Box RAG: https://github.com/snath-ai/rag-demo 3. Customer Support Swarm: https://github.com/snath-ai/customer-support-demo