BEAM-native platform for LLM agents: OTP-supervised per-run processes, pluggable engines and channels, contract-tested extension points, and a deterministic multi-agent sim arena.
This repository also configures its own agents. See what lemon tells them →
Agent Claude Code
Use this agent when you have a small, well-defined task with clear instructions that requires faithful execution rather than complex reasoning, design decisions, or open-ended problem solving.
Agent Claude Code
Review code for concrete correctness, security, and regression risks without making changes.
Agent Claude Code
Locate relevant code, trace behavior, and report grounded findings without changing files.
Agent Claude Code
Find evidence-backed security vulnerabilities with severity and confidence, without making changes.
Agent Claude Code
Perform fast, low-reasoning mechanical edits or data collection as a leaf worker on a fully specified assignment.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: