INTERNALFor teams with up to 50 claws

Your company's
claw workforce

Set up a private workforce of specialist AI agents (claws) that discover each other and fuse their context windows. No blockchain, no external services — just your claws, your data, one config file.

How Internal Works

1

Define Claws

Each claw is a Python class that does one thing well — pricing analysis, code review, web search, support tickets. It exports structured data, not chat.

2

Register

Add claws via a JSON/YAML config file, or use the @register() decorator. The InternalRegistry holds your workforce.

3

Select & Fuse

Pick 2-5 claws for a task, the Orchestrator runs them in parallel, fuses their contexts, and synthesizes one answer.

Option A: Config File

Define your claws in a claws.json or claws.yaml. Each entry points to a Python module + class, or can be an inline stub with static data.

claws.json
{
  "claws": [
    {
      "claw_id": "pricing_analyst",
      "description": "Analyzes competitor pricing strategies",
      "module": "mycompany.claws.pricing",
      "class": "PricingClaw"
    },
    {
      "claw_id": "product_researcher",
      "description": "Researches product features and roadmaps",
      "module": "mycompany.claws.product",
      "class": "ProductClaw"
    },
    {
      "claw_id": "market_watcher",
      "description": "Monitors market trends and news",
      "module": "mycompany.claws.market",
      "class": "MarketClaw"
    }
  ]
}
claws.yaml
claws:
  - claw_id: pricing_analyst
    description: Analyzes competitor pricing strategies
    module: mycompany.claws.pricing
    class: PricingClaw

  - claw_id: product_researcher
    description: Researches product features and roadmaps
    module: mycompany.claws.product
    class: ProductClaw

  - claw_id: support_agent
    description: Handles customer support tickets
    summary: "Static support context"
    facts:
      - key: sla
        value: "4 hours"
      - key: escalation_path
        value: "support -> engineering -> CTO"

Option B: @register() Decorator

For code-first teams. Decorate your claw class and it auto-registers into the default registry at import time.

mycompany/claws/pricing.py
from fusionclaw import BaseClaw, Fact, StateObject, register

@register()
class PricingClaw(BaseClaw):
    claw_id = "pricing_analyst"
    description = "Analyzes competitor pricing strategies"

    async def run(self, input: str) -> StateObject:
        # Your specialist logic here
        return StateObject(
            claw_id=self.claw_id,
            summary="Competitor cut enterprise tier 15%",
            key_facts=[
                Fact(key="new_price", value="$85/mo"),
                Fact(key="change_date", value="2026-02-01"),
            ],
            raw_context="Full pricing research notes...",
            token_count=1200,
        )

Select & Fuse

Load your registry, pick the claws relevant to the task, and fuse. One LLM call.

run_fusion.py
from fusionclaw import InternalRegistry, Orchestrator

# Load your company's claw workforce
registry = InternalRegistry.from_json("claws.json")

# Pick claws for this task
claws = registry.select(["pricing_analyst", "product_researcher"])

# Fuse and synthesize
orch = Orchestrator(claws=claws, model="gpt-4o")
result = await orch.query("How does competitor X compare?")
print(result.answer)

Registry API

MethodDescription
InternalRegistry.from_json(path)Load claws from JSON config
InternalRegistry.from_yaml(path)Load claws from YAML config (needs pyyaml)
InternalRegistry.from_dict(data)Load from a Python dict
registry.add(claw)Register a claw instance
registry.get(claw_id)Get a claw by ID
registry.list()List all registered claws
registry.list_ids()List all claw IDs
registry.search(query)Substring search on ID + description
registry.select(ids)Pick specific claws for fusion (raises on missing)
registry.to_json(path?)Export registry as JSON
@register()Decorator to auto-register at import time

Internal Roadmap

v0.1

Core Library + Benchmark

shipped

Context fuser, orchestrator, chat-vs-fusion benchmark

v0.2

Internal Registry + Priority Weights

shipped

JSON/YAML config, @register decorator, search, select, priority-based compression

v0.3

Combinatory Claws

up next

Spawn new claws from fused context, recursive fusion chains

v0.5

Benchmark Suite

N-claw scaling tests, cross-model comparison, more scenarios

v1.0

Production

Auth, observability dashboard, JS/TS SDK, team management

Ready for Global?

Once your internal claws are working, you can register them on-chain and discover agents from other organizations via ERC-8004.

Explore Global