LLM orchestration 4

No-code AI workflow platform with multi-LLM support and cost optimization. Prompteus is a platform designed for developers to build, deploy, and scale AI workflows using a no-code editor. It offers features like multi-LLM orchestration, adaptive caching, and built-in guardrails to ensure cost-effective, compliant, and robust AI operations. It provides observability, cost reduction, safety guardrails, and intelligent request routing for AI integrations.

Open-source workspace for building, deploying, and monitoring AI agents Sim is an open-source AI workspace for building, deploying, and managing AI agents. It enables teams to connect agents to more than 1,000 integrations and major large language models, then create workflows visually, conversationally, or with code. Sim provides tools for agent memory through knowledge bases, files, and tables, along with workflow execution, monitoring, logs, tracing, and cost visibility. It is designed for automating operational work across sales, engineering, IT, compliance, finance, and HR, with enterprise capabilities including SOC2 compliance, access control, SSO, self-hosting, and dedicated support on eligible plans.

Fleak simplifies AI workflows for data teams with a serverless API builder and integrations. Fleak simplifies AI workflows for data teams by providing a serverless API builder and integrating with leading cloud data warehouses and vector databases. It allows users to build complex model chaining data workflows in minutes, deploy in one click, and monitor in real-time for data correctness and cost. Fleak is an enterprise-ready platform that transforms how organizations build intelligent data workflows, creating self-healing AI orchestration that adapts to changes automatically.

Open standard for defining, versioning, and running AI agents natively in Git repositories. GitAgent is an open standard and framework that allows developers to define, version, and run AI agents natively within Git repositories. It extracts an agent's configuration, logic, tools, and memory into a portable, version-controlled definition, moving them out of proprietary frameworks and into files like agent.yaml and SOUL.md. This approach allows developers to treat agent prompts and logic like code, enabling branching, pull requests for reviews, and full audit trails. It is framework-agnostic, meaning a single definition can be run across various platforms including Claude Code, OpenAI, CrewAI, and OpenClaw. GitAgent also features built-in support for regulatory compliance and deterministic multi-step workflows.