Hera Agent Unity
Verified · 6 days agoControl and verify a live Unity Editor through a local, low-token MCP server.
Control and verify a live Unity Editor through a local, low-token MCP server.
Shared, persistent memory for AI agents, with semantic recall and live updates.
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
Run Claude, Codex, Gemini, Forge, and OpenCode CLIs through MCP with background jobs
Persistent memory MCP server. 28 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.
Pre-action gates that block AI agents from repeating known mistakes.
Pass the baton between coding agents: convert sessions across Claude Code, OpenCode, Codex & more.
Structural code-quality tools for AI coding agents.
Create, run, and analyze NetLogo agent-based models through natural conversation
Security scanner for AI Agent skills, plugins, and MCP servers with A-F grading.
Search arXiv by topic, author, title or date, read paper details, and export BibTeX or PDFs.
Causal graph memory engine for AI agents with scoring, activation, and forgetting
Publish agent output to permanent versioned URLs, read review comments back, and revise.
Pre-action gates that block AI agents from repeating known mistakes.
Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
Manage Marzban panels through the Model Context Protocol.
Control Classic Mac OS (System 7-9) from AI agents via shared folder protocol.
Drive KittyClaw, a self-hosted agent-fleet kanban, from any MCP client (embedded /mcp endpoint).
Rails development skills, docs, and workflows exposed through MCP stdio.
Cross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCP