AI Agents

Kun is a local-first AI agent workspace with desktop GUI and TUI sharing one runtime. Agents can plan and execute coding, writing, design, research, and automation tasks, with multi-agent collaboration, MCP, skills, approvals, and evidence tracking.

AI Agents | TypeScript · local-first · multi-agent

A TypeScript SDK for building persistent, stateful AI agents on Cloudflare Durable Objects. It includes chat and streaming, tool use, MCP, sub-agents, scheduling, workflows, voice, browser agents, and sandboxed code execution.

AI Agents | TypeScript · stateful agents · Cloudflare Workers

A deep-research agent pipeline for Claude Code and OpenAI Codex that searches the web and scholarly sources, checks claims and citations, and saves sources in a persistent searchable vault. Includes agent skills, parallel research roles, and resumable runs.

AI Agents | Python · deep research · research agent

A native macOS AI assistant that runs local models with llama.cpp and answers questions grounded in files, folders, and websites. Includes RAG, web search, function-calling agents, deep research, memory, and support for OpenAI-compatible APIs.

AI Agents | Swift · local LLM · AI agent

Persistent coordination layer for Claude Code and Codex teams, with MCP tools for shared tasks, memory, messaging, and workflows. Includes agent templates, lifecycle hooks, and a React dashboard; agents execute through their host's native tools.

AI Agents | Python · multi-agent orchestration · agent teams

Stash captures agent traces and human corrections, curates durable knowledge, and makes it retrievable through a CLI, API, MCP, and skills. It is infrastructure for carrying lessons across agent runs without changing model weights.

AI Agents | Python · agent memory · continual learning

0 is a local, multi-model AI security agent for investigating authorized codebases and applications. It can review source, run security tools, examine findings, and propose fixes through an extensible toolchain.

AI Agents | TypeScript · AI security · autonomous agent

LambChat is a full-stack platform for deploying and managing governed AI agents. It includes a DeepAgents/LangGraph runtime, MCP integrations, skills and memory, human approvals, scheduled tasks, sandbox execution, and web, mobile, and desktop clients.

AI Agents | Python · multi-agent · agent runtime

OpenGhost is a cross-platform desktop agent that can run commands, edit files, use Git, and operate a built-in browser. It supports approval-based and autonomous modes, plus visual charts and editable diagrams.

AI Agents | JavaScript · desktop agent · computer use

DreamGraph is a persistent, graph-based architecture cognition environment for software projects. Its daemon, MCP tools, CLI, and editor integrations help AI assistants reason about codebases, decisions, and workflows with auditable evidence and human review.

AI Agents | TypeScript · agent memory · knowledge graph

A self-hostable AI workstation for multi-agent tasks, cited knowledge search, skills, and MCP-connected tools. Supports multiple model providers, sandboxed execution, and web and desktop clients.

AI Agents | TypeScript · multi-agent · self-hosted