Juriquants/jq-ai

Self-hosted, open-source legal intelligence for the African continent. # JQ.AI **Self-hosted, open-source legal intelligence for the African continent.** Bring your own keys. Run it where you want. Own your data. **License:** Apache 2.0 **Project Status:** Active development — M1 Foundation in progress **Community:** JuriQuants --- ## What is JQ.AI? JQ.AI is a self‑hosted AI platform purpose‑built for African legal teams. It delivers conversational chat with persistent history, matter‑scoped projects, character‑verifiable citations against source documents, and reusable workflow skills authored in the open `agentskills.io` format. It runs on a laptop, an internal server, or a cloud VM, against your choice of model — Anthropic, OpenAI, Azure OpenAI, or local Ollama — with zero license fees. **The reason JQ.AI exists is simple:** legal teams should not have to choose between AI assistance and data sovereignty. Every other capable tool in this category is a closed‑source SaaS that requires sending privileged information to a third‑party vendor. JQ.AI runs in your environment, with your keys, against your choice of model — including fully air‑gapped deployments using local inference. --- ## Why this project exists Commercial in‑house legal AI products treat their prompt engineering as a proprietary moat. The skills, playbooks, citation logic, and verification heuristics that shape what the user sees are hidden inside closed‑source applications, presented as "AI" but functionally indistinguishable from a hidden system prompt. Customers pay significant per‑seat fees for software whose only real innovation is a hidden prompt — without any way to see, debug, or improve it. JQ.AI inverts this. Every artifact that shapes the user's experience is visible work product. The skills are open source. The playbooks are open source. The citation engine's verification logic is open source. When a user clicks "view this skill" on any active skill, they see the actual skill definition and supporting files, formatted for human reading, with pro …