Mastra AI
Mastra is a powerful TypeScript framework for building intelligent AI agents that can execute tasks, access knowledge bases, and maintain memory persistently within workflows. This framework simplifies the process of creating and deploying AI-powered agents by leveraging TypeScript’s capabilities to streamline development. With features like customizable agent instructions, memory, and task orchestration, Mastra provides developers with the tools to build and scale AI agents for various applications, from personal assistants to specialized domain experts.
Learn more
Omnara
Omnara gives developers an open-source way to deploy AI agents without building the systems that keep them running. Its API manages execution and agent state, while you decide which models, tools, and environments each agent uses. Build agents that customers can access inside your product, create internal assistants for Slack, or set up workflows for tasks like code review.
You can launch and interact with agents through a REST API, TypeScript SDK, or CLI. Connect models from providers such as OpenAI, Anthropic, and OpenRouter, or use a compatible endpoint for a model you host yourself. Agents can work in managed sandboxes or on machines you connect. MCP integrations and reusable skills let them access tools and data.
Omnara also includes team and project permissions, encrypted secrets, activity records, and human approval for sensitive actions. Its agents retain their state so they can continue after interruptions. You can use the cloud service or self-host the platform.
Learn more
eve
eve is an open source framework for building AI agents that you own, designed around a file-system-based structure and production-ready runtime. An instructions.md file is enough to define an agent, while optional building blocks such as model configuration, skills, tools, sandboxes, channels, connections, subagents, schedules, and evals can be added as the agent grows. Tools are created by dropping TypeScript files into the tools directory, and skills are written as Markdown playbooks that load only when relevant. Agents can connect to services such as GitHub, Stripe, and Linear through authenticated connections and can surface through Slack, Discord, Teams, web chat, APIs, cron jobs, CLIs, and custom applications from the same codebase. Specialized subagents can handle delegated work with their own prompts, tools, and sandboxes.
Learn more
Flue
Flue is an open agent framework for building durable AI agents with a programmable TypeScript harness. Created by the team behind Astro, it uses a React-like hooks API to compose agent behavior, persistent state, lifecycle events, models, tools, sandboxes, subagents, skills, and MCP servers in code. Agents are stateful and addressable over HTTP, keep context across conversations and events, and can change capabilities as work progresses. Flue records every session in a durable stream, so accepted work survives crashes, restarts, and deploys; interrupted sessions resume automatically and clients reconnect without starting over. Developers can run agents locally, in CI, from their own backend, or orchestrate them with systems such as Cloudflare Workflows and Inngest. Secure sandboxes let agents run commands, edit files, and do real work, while tools connect them to APIs and data. Flue is powered by Pi and supports different LLM providers, allowing teams to choose the models they want.
Learn more
