smux leverages tmux panes and a CLI bridge to enable AI agents to collaborate inside the terminal without APIs or shared state. Simple install, macOS/Linux compatible.
souls-directory is a Next.js app hosting curated SOUL.md personality templates for OpenClaw AI agents, using Convex backend and GitHub OAuth. Explore its architecture and usage.
text-to-cad bridges AI coding agents with parametric CAD using a local-first architecture and a novel @cad reference system for geometry-aware iterative edits and multi-format export.
Tolaria is a Tauri desktop app for managing markdown knowledge bases with git versioning and AI agent integration via a bundled MCP server. Supports 10,000+ notes offline.
tui-use bridges AI agents and terminal apps by intercepting PTY output with a headless xterm emulator, enabling smart wait semantics for reliable interaction in CLI TUIs.
usecomputer is a Zig-based native CLI for cross-platform desktop automation, solving coordinate mismatches via a coord-map system for AI agents working with downscaled screenshots.
claude-video-vision adds adaptive video frame extraction and audio transcription to Claude Code, bridging natural language queries with dynamic ffmpeg processing. It supports multiple audio backends and runs on Node.js 20+.
Clawd Cursor offers AI agents native desktop control on Windows, macOS, and Linux with a unified PlatformAdapter and local-first architecture, enabling secure, model-agnostic automation without cloud round-trips.
CORAL uses git worktree branches combined with symlinked shared state to orchestrate multiple AI coding agents collaborating in real-time. This Python infrastructure supports iterative code improvement through evaluation loops.
DeepChat is an Electron-based TypeScript desktop app unifying multi-LLM chat, MCP protocols, and ACP agent integration with remote control and Skills support.
awesome-design-skills offers a registry of structured design system files that constrain AI UI code generation for consistent, accessible results using TypeUI CLI.
AG2 Studio offers a FastAPI + Next.js UI for prototyping multi-agent AI workflows on the AG2 framework. It supports multiple LLMs and skill composition but is a reference, not production-ready.
LangAlpha uses AI agents that write and execute Python to analyze financial data, reducing token waste and enabling persistent, steerable multi-agent research workspaces.
lich-skills offers seven domain-specific AI coding assistant skills with a focus on spec-driven development and scientific debugging to improve reliability.
Lumibot unifies backtesting and live trading for stocks, options, crypto, and forex with AI agent runtime using DuckDB, supporting multiple brokers and data sources.
MemKraft is a zero-dependency local-first memory system storing AI agent knowledge as Markdown, featuring bitemporal tracking, hybrid search, and a prompt self-improvement loop.
Mind offers a SQLite-backed persistent memory layer with a 3-tier model for AI agents, solving context decay via checkpoint recovery and semantic search integration.
opsrobot-ai/opsrobot offers a full-stack observability platform for AI agents, using Vector pipelines to transform OpenClaw logs into structured data in Apache Doris, enabling detailed multi-agent tracing.
Prefab offers a Python DSL for building declarative UI compiled to JSON and rendered via React, designed for MCP apps and AI agent-generated interfaces without frontend JavaScript.
A curated repo of 30+ Claude Code agents focusing on architectural consulting across languages, frameworks, and infrastructure. Guidance-first approach flips typical code-gen agents.
