# ShinMegamiBoson/OpenPlanter

Repository: https://github.com/ShinMegamiBoson/OpenPlanter
Canonical: https://ross.abutalabs.com/products/openplanter
Language: Python
License: MIT
License Family: permissive
Last push: 2026-03-06T00:30:14+00:00

## Health v2 (maintenance only)
Score: 48/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 70, release rhythm 41, longevity 13
- inputs: {"age_days": 195, "days_push": 181, "days_rel": 181, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2434, forks 366 (observed 2026-08-28T04:06:51.341401+00:00)

## What it is
OpenPlanter is a recursive-language-model investigation agent that ingests heterogeneous datasets (corporate registries, campaign finance, lobbying disclosures, government contracts), resolves entities across them, and surfaces connections via evidence-backed analysis. It ships as a Tauri 2 desktop app with a live knowledge graph and wiki viewer, plus an independent Python CLI/TUI agent with file, shell, web search, and sub-agent delegation capabilities.

## Use cases
- cross-reference vendor payments against lobbying disclosures
- resolve entities across corporate registries and campaign finance records
- visualize connections between companies and government contracts as a knowledge graph
- run autonomous research agents with web search and shell access
- build a cross-linked wiki of investigation findings
- investigate sanctions and lobbying overlaps locally with Ollama

## When to choose
- you need to link entities across multiple public datasets with evidence-backed output
- you want an autonomous agent desktop app with an interactive knowledge graph
- you prefer multi-provider LLM support including local models via Ollama
- you want both a GUI and a scriptable headless CLI for investigations

## When to avoid
- you need a simple one-shot LLM chat app without agentic tool use
- you require guaranteed factual accuracy without verifying agent findings
- you need a hosted multi-user service rather than a local desktop/CLI tool
- your datasets are small and don't need entity resolution or graph analysis

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, search-engine, data-visualization, cli, gui, llm-inference, web-scraping
- domain: osint, artificial-intelligence, data-science, developer-tools
- platform: windows, cli, python, rust
- tags: recursive-language-model, knowledge-graph, entity-resolution, investigation-agent, wiki-generation, cytoscape, multi-provider-llm, tauri-desktop, campaign-finance, corporate-registry, ai-agents, investigative-research, macos, linux, desktop, tauri, docker

## Member repositories
- ShinMegamiBoson/OpenPlanter (main) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:51.341401+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:31:07.869873+00:00, confidence not recorded.
  - readme: https://github.com/ShinMegamiBoson/OpenPlanter (fetched 2026-08-28T04:06:51.341401+00:00, sha 25028152e782)
- Data as of 2026-08-30T08:39:29.467469+00:00.