llama-index-tools-truth-bear-gauge

LlamaIndex tool spec for Truth Bear GAUGE, a pay-per-call source of official-record signals (US federal agencies and named registries).

Installation

pip install llama-index-tools-truth-bear-gauge

No API key, no account, no signup for the two free tools.

Tools

Quick start

from llama_index.tools.truth_bear_gauge import TruthBearGaugeToolSpec

spec = TruthBearGaugeToolSpec()
tools = spec.to_tool_list()

# Use directly
print(spec.coverage_check(signal_id="hydrology.river-level"))
print(spec.catalog_lookup(signal_id="hydrology.river-level"))

With an agent

from llama_index.core.agent import ReActAgent
from llama_index.tools.truth_bear_gauge import TruthBearGaugeToolSpec

tools = TruthBearGaugeToolSpec().to_tool_list()
agent = ReActAgent.from_tools(tools, llm=your_llm, verbose=True)
agent.chat("Is the hydrology.river-level signal line on schedule?")

Design notes

• Standard library only — no dependency beyond llama-index-core.
• No money moves here. record_request returns the x402 challenge untouched; settling it is the caller's own wallet's job.
• The catalog filter is required. The unfiltered response is ~1.5 MB — too large for an agent's context — so a call with neither signal_id nor industry returns an error.
• A miss is not an error. An unknown signal_id returns {"found": false} rather than raising.
• Every paid record ships a canonical sha256 record_hash that can be recomputed offline.