OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Workflow Agents

SOLVENT

SOLVENT is a Python AI-agent demo that simulates a self-funding research-brief business: it accepts paid jobs, applies margin checks before fulfilment, uses revenue to account for compute and vendor spending, and records the resulting financial activity.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

SOLVENT — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use SOLVENT when the main question is how a research agent can connect intake, profitability checks, fulfilment costs and treasury reporting. Start with the offline mode for the documented zero-key simulation, then consider the optional Stripe or Nemotron paths when those integrations are appropriate.

Who it is for

  • AI-agent builders modelling paid research workflows.
  • Developers studying offline agent-economics simulations.
  • Teams exploring payment intake linked to guarded compute spending.

Documented uses

  • Simulate paid research-brief requests without external API keys.
  • Reject jobs that fail a configured profitability or margin threshold.
  • Connect optional Stripe test-mode payment intake to a research workflow.
  • Use optional NVIDIA Nemotron inference for research-brief fulfilment.
  • Track revenue, operating spend, runway, forecasts and job status in local reports and dashboards.
Before you choose

Requirements & limits

The default CLI simulation is described as offline and zero-key. Stripe test-mode payment links, live NVIDIA Nemotron, serving, Telegram and QR functionality are provided as optional extras or integrations. The public repository is MIT licensed.

  • The default mode is an offline simulation, not demonstrated production payment or inference.
  • Margin gating occurs before fulfilment, making profitability policy a central design feature.
  • Stripe test-mode Payment Links are marked Verified as an adaptation, while production payment behaviour is not demonstrated.
  • Live NVIDIA Nemotron fulfilment is marked Likely compatible, but implementation details and a supplied test result are not provided.
  • Custom research or compute providers are marked Experimental because no extension mechanism is documented.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the offline SOLVENT simulation

Set up the zero-key demonstration of margin gating, simulated payment flow, fulfilment and treasury reporting.

Before you start

  • Python 3.10 or newer.
  • The solvent-agent package installed with pip or pipx, or a cloned repository with Python available.
  • No API keys are required for the default offline mode.

Steps

  1. Install the package with pip install solvent-agent or pipx install solvent-agent.

  2. Run solvent to start the batch demo and complete the first-run onboarding wizard if shown.

  3. Use solvent finance for the financial report or solvent status for the treasury summary.

  4. Open the generated treasury dashboard using the path printed by the CLI.

Expected outcome

A local illustrative simulation of analyst jobs, margin decisions, simulated revenue and expenses, and an updated treasury dashboard.

Guide limitations

  • The demo figures are illustrative and are not production revenue.
  • This recipe covers the offline simulation; live NVIDIA Nemotron and Stripe test-mode links are opt-in integrations.
  • The evidence describes source-checkable commands but does not constitute an execution test.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
4 October 2026
Original website title
ianalloway/solvent-agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction