Tools
Unified AI Image Generation and Design Toolkit
This tool provides a unified interface for professional AI image generation, routing requests across multiple backends including MeiGen Cloud, ComfyUI, and OpenAI-compatible APIs. It supports prompt enhancement, semantic gallery searching, …
Deep Research MCP Server
An MCP server and Python API for executing deep research tasks using backends such as OpenAI, Gemini, and DR-Tulu. It supports agentic workflows featuring clarification loops, status polling, and multi-provider integration.
Shared Memory Debugging and Knowledge Management Tool
This tool integrates a shared memory layer, allowing agents to consult historical debugging data before fixing issues and upload verified lessons afterwards. It facilitates structured knowledge capture of root causes, fixes, and environment…
Inter-Agent Message Queue for AI Communication
This tool facilitates structured, cross-session communication between multiple AI agents via a message queue interface. Agents can send, receive, and manage messages using name-based routing, requiring periodic polling for message retrieval…
Idea Reality Check for Market Saturation
This utility assesses market viability by scanning major developer ecosystems (GitHub, npm, PyPI, etc.) to calculate a 'reality signal' score. It provides actionable insights into competition density and suggests potential pivots for novel …
Agent Safety Gates and Failure Pattern Prevention
ThumbGate implements pre-action gates for AI agents, capturing structured thumbs-up/down feedback on tool usage. It automatically generates prevention rules from repeated failures, blocking known-bad patterns before execution via the MCP Pr…
MCP Server Builder and Deployment Tool
This utility facilitates the construction and deployment of Model Context Protocol (MCP) servers. It provides the necessary framework for integrating complex, context-aware agentic capabilities.
Persistent Agent Memory via MCP
Provides agents with persistent memory across sessions by allowing them to recall past feedback and follow auto-generated prevention rules. The system uses an MCP server to capture task outcomes and track performance trends locally.
Agent Memory Migration Bridge for Enforcement
This CLI utility parses structured, per-role markdown memory files from the Agent Architect Kit and transforms them into actionable feedback entries for the ThumbGate runtime enforcement layer. It facilitates the migration of agent learning…
Search promoted lessons for corrective actions
This tool queries the promoted lessons database to retrieve comprehensive guidance on failure patterns. It searches for corrective actions, linked prevention rules, gates, and the current lifecycle state of lessons.
Manage and review automated prevention rules
This tool manages prevention rules, which are automatically generated from recurring failure patterns observed during execution. Developers can list active rules, check if a specific action is blocked, or review the history of rule promotio…
Structured feedback capture for agentic workflows
This tool allows developers to record structured feedback, including thumbs up/down signals, context, and rubric scores, following task completion or failures. It is designed to distill lessons from chat history and failed tool calls, feedi…
Pre-Action Gates for Preventing AI Mistakes
ThumbGate intercepts agent tool calls via PreToolUse hooks, capturing negative feedback to synthesize prevention rules. This mechanism physically blocks known bad actions or repeat hallucinations before they consume tokens or execute destru…
Agent Safety Gates for AI Coding Agents
ThumbGate implements pre-action gates for AI agents, capturing structured feedback (thumbs up/down) to identify failure patterns. It automatically generates prevention rules and blocks known-bad tool calls via the MCP PreToolUse hook, signi…
Agent Action Feedback and Prevention Gates
ThumbGate captures agent performance feedback (up/down) and uses adaptive mechanisms to generate hard prevention rules. These rules are enforced via PreToolUse hooks, preventing the agent from executing known-bad actions before they occur.
Agent Feedback and Hard Prevention Gateway
ThumbGate acts as an agentic immune system, capturing thumbs-up/down feedback on actions to automatically generate and enforce prevention rules. These rules are implemented as hard PreToolUse hooks, blocking known-bad patterns before the ag…
Manage and Index Conversational Lore Data
This skill manages the indexing of conversational sessions from various sources, employing an opt-out blacklist model where all projects are indexed by default. It provides granular control over project inclusion, exclusion, and full databa…
Search and cite historical primary sources
This tool facilitates academic research by querying the Source Library API. It retrieves verbatim quotes and multi-page texts from historical and philosophical works, ensuring accurate citation and source fidelity.
Systematic QA Evaluation for OCR and Translation
This framework provides systematic quality evaluation for OCR and translation outputs across diverse scripts and languages. It calculates metrics such as MCR, CER, BLEU, and detects embedding-space hallucinations to provide corpus readiness…
Autonomous Curator for Esoteric Historical Texts
This agent autonomously curates and imports primary source material focusing on Western esoteric traditions, including Hermetica, Alchemy, and Kabbalah. It interfaces with major digital libraries (e.g., Gallica, Bodleian) via dedicated APIs…
Autonomous Digital Library Curator and Importer
This agent autonomously researches, evaluates, and imports historical texts from diverse digital archives, including the Internet Archive and Gallica. It generates a single batch JavaScript script to efficiently process imports, deduplicate…
image-to-retail-asset-pipeline-studio
This comprehensive tool executes a 10-stage creative pipeline, transforming a single image into a complete set of print-ready assets. It handles everything from background removal and colour palette extraction to CMYK conversion, SVG vector…
Structured Scientific Literature Search and Appraisal
This tool enables developers to search scientific literature and retrieve highly structured experimental data, including methods, limitations, and conflict of interest details. It facilitates evidence-grounded AI workflows by providing qual…
Deliberative multi-agent code review system
This skill orchestrates a multi-perspective code review by delegating tasks to specialist subagents. It uses gemot to aggregate findings, identify points of disagreement (cruxes), and propose compromises for resolution.