The Library

Every architecture. From "Hello World" to Predictive World Models.
100% Python. No Magic.

Showcase Projects

Full Repositories

The Nervous System

The industry is building the Brain. We are building the Nervous System. Three repos. One cognitive architecture.

🌐

Lár-JEPA: Route Any Model — Not Just LLMs

Every framework assumes one model type. When a JEPA world model outputs a 768-dimensional latent tensor, those frameworks crash — there is no signal type for it. Lár-JEPA routes anything. LLMs, JEPAs, diffusion models, SSMs, GNNs — as first-class nodes in the same deterministic graph.

# LLM → JEPA: decide then simulate
LLMNode(output_key="action_spec")
→ JEPANode(output_key="predicted_state")
# Monte Carlo search in latent space
BatchNode([
JEPANode(action="ACCELERATE"),
JEPANode(action="BRAKE"),
JEPANode(action="TURN")
]) → ReduceNode(output_key="best_action")
# Heterogeneous swarm — any mix
BatchNode([LLMNode(...), JEPANode(...), GNNNode(...)])

Adaptive Execution

examples/adaptive/

Runtime-Adaptive Graphs

You pre-define the tools. At runtime, AdaptiveNode asks an LLM to design the graph — how many nodes, which tools, in what order — based on the actual input. A simple NDA gets 1 review node. A complex multi-party software license gets 3 parallel specialists: legal terms, financial liability, GDPR compliance. You don't hardcode both paths. The agent decides.

The graph shape changes at runtime. The compliance guarantees don't. TopologyValidator (pure Python, not an LLM) enforces the tool allowlist and rejects cycles before a single node executes. Every generated spec is logged to the HMAC-signed Causal Trace. All 13 compliance primitives work inside generated subgraphs exactly as they do in static ones. In fractal agents (parallel specialists), BranchTriageNode ensures the human jury sees per-branch findings — not just a rolled-up score. How it works → Fractal agents →

Compliance & EU AI Act

13 Primitives · 24 Examples

High-Stakes & Regulated Environments

Production-ready compliance architecture. Every structural requirement in Nannini et al. (2026) is covered. EU AI Act enforcement: August 2026. EU AI Act Deep Dive → Auditor Guide →

Core Compliance Primitives

Reasoning Models & Comparisons

System 2 Thinking & The Black Box Evidence

Native support for DeepSeek R1, OpenAI o1, and Liquid. Plus — the proofs of why other frameworks fail. Reasoning Models Docs →

Reasoning Models (examples/reasoning_models/)

The Evidence (examples/comparisons/) · Red Teaming Case Study →

Scale & Advanced

Massive Parallelism & World Models

High Scale (examples/scale/)

Advanced (examples/advanced/)

Core Patterns (examples/patterns/)

Cognitive Architectures

Resumable Graphs

No other framework can do this

Every crash is a resumption point.

Other frameworks re-send the full conversation history on retry. Lár's routers are pure Python — same state in, same decision out, deterministically. When Lár resumes at Step 47, it takes exactly the path Step 47 would have taken. Every causal trace entry is a resumption checkpoint. Resumable Graphs Docs → Continuously Running Agents →

$9.48
saved per day
At 10,000 runs/day with 40% transient failure rate. 302 tokens (Lár resume) vs ~776 tokens (competitor retry). Pure cost arithmetic.
🔬
Time-Travel Debugging

If your agent produces a wrong output at Step 5, load the state from Step 4, modify the prompt, and run Step 5 alone — repeatedly, cheaply. In a black-box framework you re-run the whole pipeline and hope the LLM reproduces the same path. In Lár you rewind to the exact state that produced the bad output.

Getting Started (examples/basic/)

The Essentials