emberdesire

Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.

Local retrieval-augmented generation system for AI agents using ChromaDB and sentence-transformers, supporting multi-agent shared memory and privacy controls.

Inference-based intrusion detection for AI agents. Pattern matching + LLM analysis for jailbreaks, prompt injection, credential theft, social engineering. 108 detection patterns, OpenClaw plugin, auto

Safely apply OpenClaw config changes with backup, automatic rollback on failure, health checks, and commands for patching, restoring, listing, diffing, valid...