langchain-truthbear
LangChain tools for Truth Bear GAUGE, a pay-per-call source of official-record signals (US federal agencies and named registries) with Bitcoin-anchored receipts.
Installation
pip install langchain-truthbear
No API key, no account, no signup for the free tools.
Tools
| Tool | Cost | Purpose |
|---|---|---|
TruthBearPreview |
free | Quick fact-check: look up one data point from 180+ official sources — returns signal, value, source URL, record hash, freshness |
GaugeCoverage |
free | Does a signal line exist, how many objects, how fresh, is the source agency on schedule |
GaugeCatalog |
free | Which entity ids are valid for a signal line — filter by signal_id or industry (one required) |
GaugeRecord |
paid (x402) | Requests one official record; returns the HTTP 402 payment challenge untouched |
Quick start
from langchain_truthbear import TruthBearPreview
tool = TruthBearPreview()
print(tool.invoke({"query": "US unemployment rate"}))
# Signal: macro.unemployment
# Value: 3.7%
# Source: https://fred.stlouisfed.org/series/UNRATE
# Record Hash: a1b2c3...
# Freshness: 2026-08-30T12:00:00Z
With an agent
from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_truthbear import TruthBearPreview, GaugeCoverage, GaugeCatalog
tools = [TruthBearPreview(), GaugeCoverage(), GaugeCatalog()]
# ... set up your agent with these tools
Design notes
- Standard library only — no dependency beyond
langchain-core. - No money moves here.
GaugeRecordreturns 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_idnorindustryis rejected. - A miss is not an error. An unknown
signal_idreturns{"found": false}rather than raising. - Every paid record ships a canonical sha256
record_hashthat can be recomputed offline. - Screening-level only — not decision-grade verification.
Metadata
Release files for langchain-truthbear 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| langchain_truthbear-0.1.1.tar.gz | 5.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langchain_truthbear-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 13.0 kB
Release files / langchain_truthbear-0.1.1.tar.gz
| Download URL | langchain_truthbear-0.1.1.tar.gz |
|---|---|
| Size | 5.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
3d75a9e967a3dd3a403712d3490a5dc48a1855a20c85fde9d012b250e2392f35
|
|
BLAKE2b-256 checksum How to use checksums |
9e5f63eca8869cc1419b8d137d92a25d9076c03b238e036139f5afa75c7e547b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|
Release files / langchain_truthbear-0.1.1-py3-none-any.whl
| Download URL | langchain_truthbear-0.1.1-py3-none-any.whl |
|---|---|
| Size | 7.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
69ca79eefcb4d7e1a644a765918be302c2582b0fb13bfc58f77f9c9354d094f8
|
|
BLAKE2b-256 checksum How to use checksums |
b265ec2e7d260168961ada3fe71d28e0ff671fc4ff3379955977ed5dca28f76a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.10
|