Embage

Abacus AI Agent is a general-purpose AI agent from Abacus.AI for building and hosting full-stack and mobile applications from natural-language prompts, generating documents, slides, images, and videos, and automating research, data analysis, and other tasks. It can create applications with frontend, backend, database, hosting, and payment functionality, and can use connected services such as Gmail for agent-driven outreach. The agent is offered within the ChatLLM subscription, which also provides access to multiple AI models, model routing through RouteLLM, browser automation, custom chatbots, workflows, and always-on personal agents.

Hyperagent is an AI agent platform presented by Airtable founder Howie Liu that deploys a fleet of agents to research, draft, build, deliver, and maintain outputs such as websites, videos, presentations, documents, and dashboards using an organization's data, tools, and working style. Agents run in dedicated computing environments with access to real browsers, shells, files, and connected software; their execution can be inspected as searches, decisions, and generated artifacts. The platform supports always-on agents with scheduled or heartbeat wake-ups, agent-to-agent orchestration, human approval steps, and learning through generated memories and skills. Agents can be invoked from Slack, email, or Telegram, through webhooks, or on a schedule, and are managed from a central command center.

DocsBot is an AI-agent platform for businesses that turns company knowledge into customer-support, presales, internal-knowledge, research, and voice agents. Its agents answer questions from indexed documentation and other sources, can take actions through skills, APIs, webhooks, billing, booking, MCP, and app integrations, and can hand support conversations to humans when needed. Users create and configure a bot, import source data from websites, documents, cloud services, help centers, tickets, YouTube, and other supported sources, then test responses and deploy the agent through a chat interface, website or help-center embed, Zapier, Make, or the API. DocsBot supports custom instructions, privacy settings, multiple AI models, scheduled source updates, logs, analytics, live web search, and Code Interpreter for research workflows.

LibreChat is an open-source, self-hosted AI chat platform that provides a ChatGPT-inspired interface for connecting to major AI providers and custom OpenAI-compatible endpoints. It supports model switching, multimodal file interactions, web search, speech-to-text and text-to-speech, image generation, conversation search, presets, branching, resumable streams, and a sandboxed Code Interpreter for languages including Python, JavaScript/TypeScript, Go, C/C++, Java, PHP, Rust, and Fortran. Its agent system supports no-code custom assistants, community-shared agents, MCP servers, tools, file search, code execution, reusable SKILL.md instruction bundles, subagents, and an Agent Management API. Agents can optionally use attached workspaces to inspect, search, edit, and run commands in bounded environments. The platform also provides generative UI artifacts, including React, HTML, and Mermaid content, plus custom actions and integrations with providers such as Anthropic, AWS Bedrock, OpenAI, Azure OpenAI, Google, Vertex AI, Ollama, Groq, Mistral, OpenRouter, and others. LibreChat includes multi-user authentication through OAuth2, LDAP, and email login; browser-based administration of users, groups, roles, and configuration; role-based permissions; observability through OpenTelemetry and Langfuse; Redis-backed synchronization for scaled deployments; and Docker Compose deployment options. It is built in public and intended for local or cloud self-hosting.

CowAgent is an open-source AI assistant and agent harness developed by LinkAI. It plans complex tasks step by step, runs tools and skills, controls computers and external services, maintains long-term memory and a personal knowledge base, and supports multi-agent teams with separate roles, models, skills, knowledge, and workspaces. Its architecture routes messages from web and messaging channels through an agent core that reasons over available models, tools, skills, memory, and knowledge before returning a response. Memory uses a three-tier structure of conversation context, daily memory, and long-term MEMORY.md, with a nightly Deep Dream process that distills memories; the knowledge base is an automatically curated Markdown wiki with cross-references and a browsable knowledge graph. Built-in tools include file and terminal operations, web fetching and search, scheduling, memory retrieval, vision, and browser automation, while MCP servers can be added through configuration. Skills can be installed from the Skill Hub, GitHub, ClawHub, or URLs, or authored through conversation. CowAgent supports multiple LLM providers and routes chat, vision, image generation, speech, and embedding workloads separately. It can run locally, in Docker, on a server, or through its macOS and Windows desktop client, with a web console for configuration and a command-line interface for service and skill management. The project is licensed under the MIT License and was formerly named chatgpt-on-wechat.