MAXIM
An Artificial Brain from Biological Blueprints
What is Maxim?
Maxim is an agentic robotics framework that gives robots something resembling a mind. Not just reflexes. Not just if-then rules. An actual cognitive architecture inspired by how mammalian brains work, adapted for embodied AI agents that can perceive, remember, decide, and learn.
These pages are the design story — why each piece is built the way it is, what the experiments showed, and what a real robot learned. The software itself is documented at pymaxim.bio: install, CLI, configuration, and the experiment ledger that decides what Maxim is allowed to claim.
The Problem with Robot Brains
Most robots today are either brilliant or stupid, rarely anything in between. Industrial robots execute perfect movements but can't adapt. LLM-powered robots can reason but lack genuine understanding of their bodies. They don't feel where they are in space. They don't remember what worked before.
Maxim bridges this gap by stealing shamelessly from neuroscience. If evolution spent hundreds of millions of years perfecting certain cognitive architectures, why reinvent them?
The Biological Blueprint
Maxim implements computational models of several brain structures, each handling a specific cognitive function:
Hippocampus
Episodic memory. What happened, when, and what came of it.
SCN
Circadian rhythms. Temporal patterns across hours, days, weeks.
Nucleus Accumbens
Reward prediction. Learning what leads to good (or bad) outcomes.
Entorhinal Cortex
Similarity matching. Finding relevant memories for new situations.
Pain Circuits
Nociception. Detecting and learning from aversive experiences.
Attention Networks
Focus. Deciding where to look and what matters.
IPS & Angular Gyrus
Dual number system. Fast approximate and slow precise math cognition.
Anterior Temporal Lobe
Semantic memory. Lasting knowledge distilled from experience.
Communication Gateway
External messaging. Reaching users via SMS, voice, and more.
Imagination
Real-time entity design from novel percepts during low-arousal states.
Default Embodiment
Base humanoid body with 5 sensors, 8 affordances, and 3 failure modes.
Operating Modes
Maxim's behavior is controlled by two independent dimensions: a processing state (awake or asleep) and an autonomy level (planning, supervised, or autonomous), each level capping how much initiative the agent may take without a human in the loop. An earlier layer of named strategies (observe, explore, research, assist…) was removed in the 1.0 mode refactor—it was policy written by hand, and the point of the substrate is to learn that.
Sleep isn't a mode. The agent enters it by calling the sleep tool, keeps its autonomy level, and wakes when input arrives. Like biological sleep it's active maintenance: memory consolidation and pattern extraction run while the lights are off.
How It All Connects
The magic isn't in any single component. It's in how they integrate. Perception flows into memory. Memory informs attention. Attention shapes what gets remembered. Reward signals update causal models. Pain teaches avoidance.
A Concrete Example
A robot is asked to "find the coffee mug." Here's what happens:
- The Entorhinal Cortex retrieves similar past experiences (maybe "finding cups" or "kitchen tasks")
- The Hippocampus provides context: "Last time, the mug was on the counter"
- The SCN notes it's morning, when mugs are often near the coffee maker
- The Attention Network prioritizes scanning kitchen areas
- The Nucleus Accumbens predicts: "Counter search usually succeeds"
- If the robot moves too fast and jerks, Pain Detection signals discomfort
- Success or failure updates all relevant memories and predictions
Frequently Asked Questions
What is Maxim?
Maxim is an agentic robotics framework — a biologically-inspired cognitive architecture that gives robots something resembling a mind. It implements computational models of brain structures (hippocampus, entorhinal cortex, nucleus accumbens, attention networks, proprioception, and more) so embodied AI agents can perceive, remember, decide, and learn.
What is the Maxim harness?
The Maxim harness is the orchestration layer that wires the biologically-inspired components (memory systems, attention, proprioception, reward prediction, tool use) together with an LLM and an embodied platform like Reachy Mini. It coordinates perception, memory recall, attention, and action in a single agent loop.
Is Maxim open source?
Yes — Maxim is open source on GitHub at github.com/dennys246/Maxim. The repository contains the full cognitive architecture, agent harness, simulation environment, and integration code for the Reachy Mini humanoid robot.
What hardware does Maxim run on?
Maxim currently runs on the Reachy Mini humanoid robot, processing real visual input, motor commands, and human interactions. The architecture is hardware-agnostic and can be adapted to other embodied platforms via the embodiment layer.
How is Maxim different from other AI agents?
Most AI agents are pure LLM wrappers with stateless tool calls. Maxim adds a persistent bio-substrate — episodic memory (hippocampus), semantic memory (ATL), reward prediction (nucleus accumbens), circadian rhythms (SCN), and proprioception — so the agent learns from every interaction rather than starting fresh each turn.
Why This Matters
This isn't just academic curiosity. Biological inspiration provides:
- Robustness: Brains evolved to handle noisy, unpredictable environments
- Efficiency: Evolution optimized for energy constraints
- Continuous Learning: Real memory systems adapt without catastrophic forgetting
- Embodied Grounding: Cognition tied to sensorimotor experience
- Safety: Pain and fear are ancient, battle-tested harm avoidance systems
Maxim runs on the Reachy Mini humanoid robot, processing real visual input, real motor commands, real interactions with humans. It's not a simulation. It's not a thought experiment. It's a working system that learns from every interaction.