self-improving agent
Advanced prompt injection defense system for AI agents. Multi-language detection, severity scoring, and security auditing.
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.
🏛️ Hermes Gate — Terminal TUI for managing remote Hermes Agent sessions with auto-reconnect, detach support, and zero config
An OpenClaw skill that uses faster-whisper (a faster implementation of the Whisper transcription model) to transcribe audio, with additional features such as speaker diarization
Complete alignment and safety architecture for autonomous AI agents. Membrane security, continuous trust verification, epistemic hygiene, emergence protocols, and defence tools. 30 years of cybernetic research — deployable today.
Autonomous AI Agent for Windows - Your intelligent, always-on AI assistant with screen understanding and task automation.
🐙 Stronger isolation alternative to OpenClaw (formerly Moltbot / Clawdbot). tmux-based multi-agent system with native CLI orchestration. ☀️🌙
Automated domain intelligence pipeline. You define the domain; Pulsar runs the engine — any LLM · any RSS · self-evolving beliefs.
CyBroLog: executable compact accountability language for multi-agent coordination
To associate your repository with the moltbot topic, visit your repo's landing page and select "manage topics."