#agentic-ai

Macvis

MacVis — open-source local-first AI agent for macOS. Multi-provider (Claude, GPT, Gemini, Ollama). Full Mac access via MCP. BYOK, no backend...

Claude Profiles

Profile switcher for Claude Code — swap settings, hooks, MCP servers, and commands between configurations

Ledgermind

​LedgerMind — an autonomous living memory for AI agents. It self-heals, resolves conflicts, distills experience into rules, and evolves with...

Aiterm MCP

One persistent MCP terminal your AI drives — and launches other coding agents (Codex/Grok/Composer) into. SSH, containers, and REPLs nest as...

Schemabrain

The trust and intelligence layer between AI agents and your database. Read-only by architecture, semantic knowledge graph + audit log, MCP-n...

Code Brain

Persistent memory, BM25 code search, MCP tools, and hook guardrails for AI coding agents — Claude Code, Codex CLI & Antigravity. One local-f...

GitIntel MCP Server

A Git intelligence MCP server built with Node.js and TypeScript that analyzes local Git repositories to surface insights like hotspots, chur...

Five MCP

160,000 deductively-derived JSON constraints that eliminate LLM persona drift. Measured: 0 breaks in a 120-turn pressure test (plain prompt:...

Loop Engineering

MCP server for self-verifying AI agent loops: schedules, independent checker gates, stop rules, worktree isolation & durable state. Built fo...

Agentic Swmm Workflow

Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM...

Prompt Shield

Prompt-injection firewall for LLM applications — 33 input detectors, 9 output scanners, federated ed25519-signed threat-intel feed. Apache 2...

PawFlow Agents

PawFlow (Platform for Agentic Workflows) Self-hosted agent runtime for real infrastructure. Run durable AI agents against your own files, to...