Build resilient agents.
Repository Index
142,273 visible repositories in the index
1–15 of 15 · Most stars
Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents
- distributed-systems
- grpc
- java
- javascript
Dapr is a portable runtime for building distributed applications across cloud and edge, combining event-driven architecture with workflow orchestration.
- microservices
- microservice
- kubernetes
- sidecar
🪓 An orchestration engine for background tasks, AI agents, and durable workflows
Restate is the platform for building resilient applications that tolerate all infrastructure faults w/o the need for a PhD.
- distributed-systems
- async-await
- durable-execution
- microservices
The open-source managed agent platform. A self-hostable alternative to Claude Managed Agents and OpenAI's Agents API.
- agent-infrastructure
- managed-agents
- durable-agents
- agent-platform
Workflow SDK: Build durable, reliable, and observable apps and AI Agents in TypeScript
Go Implementation For Seata
- at
- tcc
- saga
- xa
Durable Task Framework allows users to write long running persistent workflows in C# using the async/await capabilities.
A production-oriented AI workflow runtime for building, validating, recovering, and shipping complex AI workflows as dependable services. 面向生产的 AI 工作流运行时:快速开发、验证和恢复复杂 AI 工作流,并将其稳定交付为服务。
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
QuickJS with durable execution: suspend running JS, snapshot the whole heap, resume it in another process. Native TypeScript, a REPL that survives restarts, Rust bindings.
- c
- durable-execution
- embeddable
- hibernation
LittleHorse Server: Business-as-Code Platform for Microservices, Workflows, and Agents
Self-hosted, multi-tenant agent harness for SRE incident diagnosis — risk-gated tool approvals, durable resumable runs, audit trail, model gateway, MCP tools, and a native desktop chat client. Written in Go.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.