#296 · Primary category： AI Agents & Automation
rivet
Rivet Actors are the primitive for stateful workloads. Built for AI agents, collaborative apps, and durable execution.
Project last updated：08/28/26
GitHub Stars
6.1K
Forks
236
Contributors
30
License
Apache-2.0
Why we included this project
Most agent stacks hand you orchestration and leave session memory, background jobs, and realtime delivery to a pile of separate services. Rivet collapses those into one primitive: a long-running actor that keeps durable in-memory state, a queue, scheduling, and WebSocket streaming in a single process. For conversational and collaborative AI products that is the useful part, because one actor can hold an agent's message history while pushing token-level updates to connected clients, which saves a fair amount of glue code. The actor also hibernates when idle and scales to zero, so bursty agent workloads don't leave you paying for idle infrastructure. If your agents need persistent context and ongoing execution rather than stateless request-response calls, this is a solid runtime to build them on.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.