Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.

PostgreSQL MCP server, read-only by default: query, schema introspection, EXPLAIN plans, index advisor, and DBA health checks.

An instruction layer for AI coding agent

Strategic BDI reasoning engine for autonomous AI agents — goal decomposition, utility scoring, risk evaluation, and reactive replanning over PuterVision memory and world models.

Deterministic, persistent 3D/2D spatial world model for AI agents with entity tracking, object permanence, movement simulation, and expected view frustum projection.

Enables agents to optimize real-time attraction visitor dispersion and queueing wait times using queuing-theory models and dynamic heatmap routing.

High-frequency in-browser behavior tree execution engine for autonomous AI agents — 60Hz tick loops, reactive triggers, telemetry recordings, and safety guardrails.

An MCP server that lets AI agents automate Microsoft Edge, organizing sessions into labelled tab-group workspaces or separate profiles and providing tools for browser control, screenshots, extraction, and secure sign-in through Edge's password manager.

Production-ready AI agent profiles for Claude Code, Cursor, Codex, OpenClaw, and Hermes. Search, install, and contribute ForgeCat packages.

Enables LLM clients to inspect live game state and perform deterministic shop, inventory, backpack layout, and combat actions in a running game through a local bridge.

Enables an AI agent to sign, verify, encrypt, decrypt, and manage OpenPGP keys while private key material stays in gpg-agent and passphrases go only to pinentry. Adds human approval for high-risk operations, typed-fingerprint confirmation for destructive ones, and audit logging that never records plaintext.

A self-hosted MCP memory server that gives every MCP-compatible agent a shared, persistent memory layer, so preferences, project conventions, and past decisions carry across sessions and across different agents and vendors. It combines hybrid keyword-plus-vector retrieval with automatic context injection, zero-config sync, and selective injection of memories by agent and priority.

Deterministic Unit-Record Memory Engine for AI coding agents. Eliminates context-window amnesia and compaction bloat via zero-turn workspace hydration, byte-exact registers, and live context telemetry.

Enables AI agents and assistants to inspect live system telemetry, check TCP port connectivity, audit environment variables for leaked secrets, analyze and summarize log files, and list Docker containers — all with token-efficient, compressed output.

Enables AI coding agents to retrieve compact structural codebase context through repository architecture summaries, AST symbol extraction, cyclomatic complexity scoring, and TODO/FIXME hotspot search.

Enables deterministic request screening and, after native owner approval, fixed-target DeadBolt enforcement actions such as kill, deny, revoke, and evidence retrieval through local stdio MCP. Model analysis can advise but cannot approve actions.

Enables stateless, pure-visual control of Android devices and emulators through adb shell, providing screen capture, coordinate-based taps, swipes, keyboard input, and arbitrary adb command execution for agent-driven interaction.

Enables developers to register custom tool-calling functions, execute path-safe file operations within an isolated workspace, and keep in-memory memory and audit state for AI agent workflows.

Provides Model Context Protocol access to the SEAF ArchTool REST API, enabling agents to inspect sections and entities, navigate relations, query datasets, and run JSONata expressions against a SEAF portal.

Enables VS Code Copilot Chat and custom agents to perform MongoDB queries, writes, transactions, schema discovery, index and collection management, and administrative commands across multiple secure connection profiles without using mongosh or PowerShell.

Gives browser agents a reviewed map of 79 real sites — entry URLs, access verdicts, and role/accessible-name button maps for 104 screens — so an agent can find where things are and know whether it may act at all. Safety rules in code halt irreversible actions such as pay, order, submit and delete pending explicit human approval, while per-site memory recalls which routes worked last time.

Enables an AI agent to drive a remote Linux machine over the LAN through a single TCP connection, exposing tools for shell commands, jobs, interactive PTYs, file read/write/search/transfer, process and service management, networking, packages, and power control, with optional multi-host switching. Operates without SSH or any Linux-side installation beyond one stdlib-only Python daemon, using a state-free binary protocol.

Enables MCP clients to query and diagnose machine-learning training runs through read-only tools for listing experiments, reading configurations and final metrics, comparing runs, sampling metric curves, and detecting training failures.

Enables AI agents to connect to Maptek Vulcan 12 Desktop through MCP, allowing natural-language inspection of block models and triangulations, drillhole and CAD database operations, legend updates, 3D screenshots, and PyVulcan script execution.