AI Engineering

RAG Onboard Context probes the indexed knowledge base at the start of a session or after a topic shift. It checks index stats, categories, and a few sample searches so the agent knows what content is available before answering.

RAG Security First routes security questions through the local corpus before external threat-intel lookups. Use it for incident response, MITRE mapping, CVE analysis, detections, and red/blue team research grounded in local playbooks.

Rag Troubleshoot searches the knowledge corpus for prior errors, fixes, runbooks, and incidents before general debugging. Use it when a user reports a bug, exception, stack trace, failed CI run, or unexpected behavior.

RAG Web Fallback forces an agent to search the local knowledge base before using external web tools. It is used when a question might be answered from indexed docs and the agent must explain why it escalated if local coverage is missing.

Agents Md Sync prunes and routes AGENTS.md guidance so inherited context stays small, durable, and useful. Use it when nested agent instructions have drifted, duplicated, or become too broad.

Dreaming maintains Signet's ontology and memory substrate from transcripts, memory artifacts, source artifacts, notes, summaries, and imported records. Use it when bulk evidence needs to be turned into entities, links, claims, and provenance-tracked maintenance output.

Dreaming Development helps preserve Signet's current Dreaming architecture while making changes. Use it when inspecting source, semantic memory, retrieval, and inference paths to avoid duplicate modules and ad-hoc providers.

Improve surveys a codebase and writes prioritized, self-contained implementation plans for another agent to execute. It is read-only on source code and is used for audits, bug triage, roadmap planning, and handoff plans.

MemoryBench Integration benchmarks your custom memory system against tools like Supermemory, Mem0, and Zep. Use it to compare accuracy, latency, features, and cost on standard or custom datasets.

Prompt Injection Defender scans tool outputs for indirect prompt injection attempts and warns Claude about suspicious instructions. Use it when you want to detect override, role-playing, encoding, or context-manipulation patterns in files, web pages, and command results.

Signet AI installs a persistent memory and secrets layer for AI tools. Use it when you need to set up the Signet daemon, dashboard, and connectors for a supported agent platform.

Signet Ontology helps you navigate reviewed structured facts, claim history, entity dependencies, and graph hygiene from Codex. Use it when working with Signet knowledge graph state and treating raw memory files as evidence.