Skip to main content
Glama

ARV — research with an evidence graph

CI

Русский

ARV (Assumption–Research–Verification) helps an AI agent build a working picture from incomplete data and keep the grounds behind its conclusions inspectable. It bundles a research skill with a local MCP server and a persistent SQLite graph.

The agent reads sources, proposes hypotheses and judges their meaning. ARV stores the source trail, combines distinct grounds and revisits dependent conclusions when a premise changes.

Observation → hypothesis → new grounds or counterfacts → revised working model

If you find ARV useful, consider giving it a star on GitHub. Thanks for checking it out!

Technical quickstart

Targets Windows, macOS and Linux with Python 3.13 and uv. Use PowerShell on Windows or your terminal on macOS/Linux; the commands are the same. Run these commands from the extracted repository folder. The first command downloads Python 3.13 if needed and installs the locked dependencies.

uv sync --frozen
uv run --frozen --offline python examples/quickstart/run.py

No external source account or model API key is needed for the quickstart. It drives the actual stdio MCP server with scripted calls and writes a new, separate demo graph on every run. It does not exercise autonomous model reasoning.

What happens

What you can inspect

Two synthetic recordings suggest a shared signal

One hypothesis gains a second distinct observation

The same record is copied and summarised

Its observation count stays at two

A task convention interprets a raw unit as centimetres

The rule remains visible as an assumption

A calibration record supplies a different scale

The old length and its dependent conclusion lose support

The server restarts

The revised working model and history remain available

This fixture checks software behaviour, not comparative research quality. The command prints the output folder. Open its walkthrough.md, snapshots.json, model.json and trace.json. See the technical example.

Related MCP server: chronomem

Use with Codex

The repository includes a local plugin marketplace, portable plugin.json and mcp.json, plus the Codex compatibility manifests. Run uv sync --frozen first; the MCP launch uses cached dependencies in offline mode.

codex plugin marketplace add .
codex plugin add assumption-research-verification@arv-public

Alternatively, open the desktop Plugins Directory, select the ARV marketplace and install the plugin there. Start a new local chat and invoke $assumption-research-verification with your question and authorised sources. See installation, data location and troubleshooting.

What ARV adds

  • Observations retain source identity, locator, date and scope.

  • Hypotheses can accumulate new grounds and preserve actual counterfacts.

  • Copies, derived summaries and repeated inference paths share their original roots.

  • User conventions and ordinary domain defaults remain distinguishable from facts.

  • Revisions retain history; new material data reopens a saved conclusion.

  • Equivalent meanings can be reused or merged explicitly by the agent.

Support is ordinal bookkeeping, not a calibrated probability. The agent still judges source quality, semantic identity and which explanation makes sense. ARV does not certify factual truth or guarantee better answers than a plain agent. See the method and its limits.

Data and access

The graph server runs locally and has no source adapters, model credentials or telemetry. Source access comes from the host's separately authorised tools. Source passages sent to ARV are stored in its graph. A connected AI host may process tool calls and results under that host's own data policies.

The SQLite file is single-user storage, not a tenant isolation boundary. Use a separate graph when a project needs separate data. Details.

Development

uv run --frozen --offline python -m unittest discover -s tests -v
uv run --frozen --offline python scripts/package_release.py

The release builder uses an explicit file list and excludes databases, dependency environments and generated demo output. Contributing · Changes · Verification scope · Release preparation.

ARV 0.4.2 is distributed under the MIT licence. Source and releases.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents and MCP clients to store, retrieve, and manage bi-temporal, graph-aware facts in an embedded SQLite memory engine with token-budgeted recall and contradiction tracking.
      6
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides local, evidence-aware research memory with human review, revision history, and an inspector, allowing assistants to preserve source reports, inferences, assumptions, and evidence across sessions.
      MIT