@evezart

evez-skill-vetter performs static security analysis on openclaw skills, checking permissions, suspicious code patterns, dependencies, and secret exposure with a 0-100 risk scoring model.

evez-debate-framework orchestrates multi-agent adversarial reasoning through configurable debate rounds, stance types, and judge-based evaluation. designed for consensus-building and argument quality improvement in multi-agent systems.

semantic-code-search indexes codebases by parsing AST and generating embeddings to enable natural language queries and similarity detection across implementations, but lacks specifics on accuracy, performance constraints, and failure modes.

agent-safety-monitor provides real-time behavior tracking and constraint enforcement for autonomous ai systems via rule engines and anomaly detection, but lacks procedural depth and concrete decision logic.

evez-backup-sync automates backup and sync for ai agent workspaces via git, supabase, and mem0 with 5-minute commit intervals and 15-minute state snapshots.

evez-oracle-bridge routes llm calls through vultr instances with four model variants and openai-compatible endpoints. includes circuit integration for knowledge graph and debate workflows at zero cost.

evez-api-gateway routes openai-compatible llm calls to the evez platform for cost reduction. supports four model variants (smart, code, fast, vision) with free and paid tier access, but lacks integration guidance beyond environment setup.

Analyze LLM API usage logs and suggest cost optimizations. Use when you need to reduce LLM spending, compare model costs, find downgrade opportunities, detec...

Build, test, and deploy MCP (Model Context Protocol) tools for developer workflows. Use when creating MCP servers, adding tool definitions, integrating with...

Visual workflow builder for orchestrating multi-agent systems with branching, parallel execution, error handling, and retry logic. Use when building agent pi...

Scalable memory system for AI agents with short-term, long-term, and episodic memory. Use when building agent memory persistence, conversation context manage...

Prediction market that trades the gap between perception depths. Shadow prices reflect what autonomous agents at different recursion depths can see — the 72%...