Subconscious
Subconscious is a developer-first platform designed to build, deploy, and scale production-ready AI agents by handling the hardest parts of agent architecture automatically. It provides a complete agent system that manages context, orchestrates tools, and enables long-horizon reasoning, allowing developers to focus on defining goals and capabilities rather than stitching together complex infrastructure. It introduces a unified inference engine composed of a co-designed model and runtime that decomposes complex tasks, generates workflows dynamically, and executes multi-step reasoning without manual context engineering or multi-agent orchestration. Unlike traditional approaches that rely on chaining APIs and frameworks, Subconscious enables agents to take in goals and tools, then autonomously plan, reason, and act with minimal human intervention, effectively creating systems that can “get the job done” on their own.
Learn more
Flowise
Flowise is an open-source platform that enables developers and teams to build AI agents and LLM-powered applications through a visual interface. The platform provides modular building blocks that allow users to create everything from simple chatbot workflows to complex multi-agent systems. With its drag-and-drop design environment, developers can rapidly prototype and deploy AI-powered applications without extensive coding. Flowise supports integrations with more than 100 large language models, embeddings, and vector databases. It also includes features such as human-in-the-loop workflows, observability tools, and execution tracing for monitoring agent behavior. Developers can extend applications through APIs, SDKs, and embedded chat interfaces using TypeScript or Python. By combining visual development tools with scalable infrastructure, Flowise simplifies the process of building and deploying production-ready AI agents.
Learn more
Archestra
Archestra is an open source, self-hosted AI platform for deploying and governing agents across an organization. It provides agentic chat for non-developers, apps and skills, shared projects, a server-side agent runtime, MCP orchestration, permission-aware RAG, LLM and MCP proxies, security guardrails, and observability in one platform. Users sign in with SSO, and every tool call runs under that person’s own identity rather than a shared service account. Projects keep chats, files, scheduled tasks, and instructions together, while agents run in sandboxed containers and can start from schedules, emails, or webhooks. MCP servers run in the organization’s own Kubernetes environment and move through security-reviewed promotion flows with separate credentials and network policies. Knowledge bases can connect Confluence, Jira, drives, and internal documents while preserving source-system ACLs, so users only retrieve content they are already allowed to access.
Learn more
Contextual AI
The Contextual AI Platform is an enterprise-grade solution designed to help teams build AI agents that reduce hours of technical work to just minutes. It brings together state-of-the-art context engineering tools, enterprise data management, and production-ready security in one unified platform. With Agent Composer, users can define and configure specialized AI agents using natural language prompts, visual editors, or pre-built templates. The platform supports continuous ingestion and extraction from massive knowledge bases, transforming unstructured enterprise data into actionable intelligence. Contextual AI enables traceable reasoning, fine-grained attribution, and grounded outputs that users can trust. Its robust runtime ensures agents perform reliably at scale across complex document volumes. The platform is built to move organizations from experimentation to production quickly and confidently.
Learn more