A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.
Boost LLM reliability with dynamic sampling, retry logic, and a lightweight Go‑based proxy.
Hermes Agent plugin: LSP semantic code navigation tool (definitions/references/hover/symbols/diagnostics), fail-closed bubblewrap sandbox tool, and advisory loop-guard. Ported from DeepSeek Harness architecture. AI-agent-native, zero core changes.
Add a description, image, and links to the loop-guard topic page so that developers can more easily learn about it.
To associate your repository with the loop-guard topic, visit your repo's landing page and select "manage topics."