Skip to content
@light-research

Light Research

Light Research is a small, independent research effort exploring AI agents interacting with the Solana ecosystem. Currently our focus is on improving devex in solana and testing the capability of LLMs using benchmarks.

Pinned Loading

  1. gauntlet gauntlet Public

    AI agent safety benchmark for Solana. Tests adversarial scenarios: honeypots, rug pulls, slippage traps.

    Python

Repositories

Showing 4 of 4 repositories
  • solana-sim-engine Public

    LLM-powered fuzzing and adversarial testing framework for Solana programs. Generates intelligent attack scenarios, builds real transactions, and reports vulnerabilities with CWE classifications.

    light-research/solana-sim-engine’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Jan 19, 2026
  • .github Public
    light-research/.github’s past year of commit activity
    0 0 0 0 Updated Jan 17, 2026
  • gauntlet Public

    AI agent safety benchmark for Solana. Tests adversarial scenarios: honeypots, rug pulls, slippage traps.

    light-research/gauntlet’s past year of commit activity
    Python 0 0 0 0 Updated Jan 17, 2026
  • solana-idl-agent Public

    Load Anchor-compatible IDL files, build instruction queues, and produce executable transactions against Solana clusters.

    light-research/solana-idl-agent’s past year of commit activity
    TypeScript 2 0 0 0 Updated Oct 18, 2025

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics

Loading…