geo-infer-agent

Multi-agent geospatial systems with Active Inference. Use when building spatial agents, implementing perception-action loops, managing agent telemetry, or coordinating multi-agent spatial exploration.

Best use case

geo-infer-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Multi-agent geospatial systems with Active Inference. Use when building spatial agents, implementing perception-action loops, managing agent telemetry, or coordinating multi-agent spatial exploration.

Teams using geo-infer-agent should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/GEO-INFER-AGENT/SKILL.md --create-dirs "https://raw.githubusercontent.com/ActiveInferenceInstitute/GEO-INFER/main/GEO-INFER-AGENT/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/GEO-INFER-AGENT/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How geo-infer-agent Compares

Feature / Agentgeo-infer-agentStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Multi-agent geospatial systems with Active Inference. Use when building spatial agents, implementing perception-action loops, managing agent telemetry, or coordinating multi-agent spatial exploration.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# GEO-INFER-AGENT

## Instructions

### Core Capabilities

- **Agent base**: Transport pattern for agent communication
- **Active Inference**: Agent-level free energy minimization
- **Telemetry**: JSON snapshot + per-agent metrics tracking
- **Coordination**: Message passing, shared beliefs, swarm protocols
- **Rule-based**: Decision-tree agents for simple spatial tasks

### Key Imports

```python
from geo_infer_agent.core.agent_base import GeoAgent
from geo_infer_agent.core.active_inference import ActiveInferenceAgent
from geo_infer_agent.core.telemetry import AgentTelemetry
from geo_infer_agent.models.rule_based import RuleBasedAgent
```

## Examples

```python
from geo_infer_agent.core.agent_base import GeoAgent
from geo_infer_agent.core.telemetry import AgentTelemetry

agent = GeoAgent(agent_id="explorer_01", position=(45.5, -122.6))
telemetry = AgentTelemetry(agent)

# Perception-action loop
observation = agent.perceive(environment_state)
action = agent.decide(observation)
agent.act(action)

# Snapshot telemetry as JSON
snapshot = telemetry.snapshot()
print(f"Steps: {snapshot['total_steps']}, Position: {snapshot['position']}")
```

```python
from geo_infer_agent.core.active_inference import ActiveInferenceAgent
import numpy as np

ai_agent = ActiveInferenceAgent(n_states=8, n_observations=5, n_actions=4)
obs = np.random.dirichlet(np.ones(5))
action = ai_agent.act(obs)
print(f"Selected action: {action}, Free energy: {ai_agent.free_energy:.4f}")
```

## Guidelines

- Telemetry uses JSON snapshots and per-agent metrics (not TODOs)
- Agent base uses transport pattern for communication
- Test: `uv run python -m pytest GEO-INFER-AGENT/tests/ -v`

### Integrations

- **ACT** → Active Inference agent decision-making
- **SIM** → Multi-agent simulation environments
- **ANT** → Swarm intelligence coordination
- **SPACE** → Spatial state representation for agents
- **APP** → Agent configuration and control widgets
- **OPS** → Agent telemetry monitoring

Related Skills

We are still matching the closest adjacent skills for this page. In the meantime, continue through the full directory.