Radar check
What we found when we opened it. Every bar is one fact, with its date.
Last code pushed 30 Sep 2026, 25 days before this check.
Latest release v0.1.0 on 26 Sep 2026.
Public since September 2026, 1 months.
0 stars and 0 forks.
217 commits and 38 new issues in the last 90 days.
1 contributor. 46 pull requests merged in 90 days. A small team carries it.
No security policy file says how to report a problem. No published security advisories.
How the bars are scored
- Alive. Days since the last code push: a week or less 100, a month 90, three months 70, six months 50, a year 30, eighteen months 15, older 0.
- Releases. Age of the latest GitHub release, on a similar scale; no bar when the project publishes no releases.
- Maturity. Age of the project: eight years 100, five 90, three 70, two 55, one 40, six months 25, younger 10.
- Adoption. Stars on a log scale: 100,000 stars is 100, 10,000 is 80, 1,000 is 60, 100 is 40.
- Activity. Commits in the last 90 days: 300 or more 100, 100 85, 30 65, 10 45, any 25.
- Community. People who have contributed: 100 or more 100, 30 80, 10 60, 5 40, 2 25, one 10.
- Security. A published security policy 80, none 40; published advisories are listed, not scored.
Checked by Repo Radar on 26 Oct 2026 from the repository on GitHub.
In simple English
This project is a legal research assistant for Ontario personal-injury law. It searches statutes and court decisions to answer questions in plain words. Every quoted sentence is checked by code against the official text. No answer is shown to a user until a human reviewer approves it. You need technical tools like Docker and a Google Cloud account to run it yourself.
What it is
A self-hosted research system built with Python, FastAPI, PostgreSQL, and a Next.js interface. It uses hybrid search and language models to find laws and draft grounded summaries.
What it is good for
Law students, paralegals, and developers who want to study legal engineering or build a verifiable search system over official documents.
- Every quote is verified against official text by code before review.
- Built-in review queue stops unverified answers from reaching users.
- Includes automated tests, end-to-end browser checks, and evaluation scripts.
- Requires a Google Cloud project with Vertex AI access and billing.
- Setting up the local development environment needs several external command-line tools.
- Model generation times are slow, with answers taking over ten seconds to draft.
manual keyword search across fragmented legal databases
Next.js
- langchain-ai/rag-from-scratch9.5k stars
Educational code for building grounded retrieval systems from scratch in Python.
- docusealco/docuseal19k stars
Document signing you run yourself, with a record of who signed and when.
- Future-Scholars/paperlib2.3k stars
A desktop library for research papers that fills in the details itself.
- mozilla/pdf.js54k stars
A PDF reader written in JavaScript that renders documents inside a web page with no plugin.
gcloud auth application-default login gcloud auth application-default set-quota-project <your-project> uv sync && npm ci --prefix web make db uv run -m scripts.check_vertex