Back to browse
GitHub Repository

Jo Secure Programming Language

7 starsScala

Jo – AI-native language to catch prompt injection at compile-time

by kiru_io·Jun 5, 2026·7 points·3 comments

AI Analysis

●●SolidBig BrainBold Bet

Compiler-enforced capabilities catch prompt injection before AI-generated code ever runs.

Strengths
  • Transitive capability tracking through entire call graph with clear error traces
  • Compiles to Ruby and Python for pragmatic adoption in existing AI agent workflows
  • Explicit capability declarations prevent network, filesystem, and data access by default
Weaknesses
  • Early stage with 7 stars and v0.10.0 — APIs still changing, not production-ready
  • Capability-based security exists in Pony and Rust, limiting architectural novelty
Target Audience

Developers building AI agent platforms, security-conscious teams running untrusted code

Similar To

Pony · WASI · Rust

Similar Projects

Developer Tools●●Solid

Lumina – a statically typed web-native language for JavaScript and WASM

Built-in reactive runtime and dual JS/WASM targets challenge React and TypeScript dominance.

WizardryBold Bet
light_ideas
202mo ago
Security●●Solid

PromptSonar – Static analysis for LLM prompt security

Static scanner catches prompt injections in code before runtime, unlike runtime guards.

Solve My ProblemShip It
meghal86
102mo ago