AI Agents & MCP

Run Codex and Claude Code on separate cloud computers, managed from desktop, mobile, web, or CLI.

Build autonomous AI agents that understand codebases, edit files, run commands, and execute workflows.

Self-hosted AI workspace for chat, agents, research, documents, email, and local models

A TypeScript library for orchestrating AI coding agents with configurable sandboxes and Git branch strategies.

Open-source skills, agents, memory, and security tools for coordinated AI coding workflows.

Open-source vector database for storage-efficient semantic search and local RAG on personal data.

An experimental graph-native programming language for agents, with checked edits and human-readable projections.

Open-source knowledge framework for document search, RAG, reasoning agents and a self-maintaining wiki.

Create and edit draw.io diagrams through AI chat, with manual editing, version history and MCP support.

Create, train, and chat with AI agents for business tasks, content creation, coding, and learning.

AI agents that automate workflows, query business data, and use connected tools with human approval.

AI phone assistants for business calls and developer-built voice bots connected to OpenAI assistants.

AI assistants and agents for building apps, automating work, analyzing data, and creating content.

Search API for coding agents to find context across documentation, repositories and specialized indexes.

Open-source, no-code AI agents for multichannel support, knowledge retrieval, and workflow automation.

Cloud VMs, isolated sandboxes, and serverless GPUs for AI agents and model inference.

AI teammates with their own identity, permissions, cloud computer, and persistent knowledge.

Conversational AI for ecommerce sales, customer support, cart recovery, and multichannel messaging.

AI backlink outreach for business owners, with prospect research, personalized pitches, follow-ups, and link monitoring.

API access to chat, reasoning, image, video, audio and search models with unified billing.

Build with open models locally or in the cloud, with prompt privacy and usage-based cloud pricing.

A Python framework for building MCP servers, clients, and interactive applications.

Manage parallel AI coding agents through persistent terminal sessions, a web dashboard, and mobile browser access.

An open-source autonomous development loop for Claude Code with exit detection, rate limiting, and sandbox execution.

A desktop manager for switching AI coding providers and organizing MCP, Skills, and Prompts.

AI-powered task management for development, with PRD parsing, project research, editor integrations and a CLI.

Open-source Python framework for multi-agent workflows, sandbox tasks, realtime agents, and voice pipelines.

Open-source terminal coding agent that reads repositories, edits files, and runs commands with cloud or local models.

Open-source AI workstation for multi-model chat, agents, local knowledge bases, and image creation.

Open-source CLI for configuring Claude Code with agents, commands, MCP integrations, hooks, and monitoring tools.

LibreChat unifies AI conversations with model selection, agents, code execution, and MCP connections.

Open-source skills framework for coding agents, with design planning, test-driven development, and code review.