Awesome Infra for AI › Workflow Orchestration for AI

Abilityai/trinity

⭐ 619 Python added to this list on 2026-09-07 repository created 2025-12-10

Trinity is a self-hosted platform for deploying and operating AI agents in production rather than for building them from scratch. Each agent runs inside its own isolated Docker container, and the platform provides fleet-wide scheduling (including cron-based jobs), agent-to-agent delegation over a bidirectional A2A protocol, real-time observability of running agents, cost tracking and a tamper-evident audit trail aimed at governance and audit requirements. It is designed to complement AI coding assistants: agents are authored and configured with tools such as Claude Code, and Trinity then runs, schedules and monitors them continuously afterward. The project ships a CLI (trinity-cli) and a Vue-based web console called "Workspace" for managing agent fleets, viewing dashboards, browsing a multi-source skills library, and completing installation and credential provisioning through a guided setup flow. Agents can be imported from GitHub or a remote template registry through a manifest-driven install UI. SQLite is supported for local development and evaluation, with PostgreSQL recommended for production, including a guided migration path between the two. Trinity targets teams and individuals who want to run semi- or fully autonomous AI-driven systems, ranging from single background agents to larger agent-operated workflows, on infrastructure they control rather than a third-party SaaS platform, while retaining audit and observability guarantees suited to security-conscious or regulated environments. It is open source under the Apache 2.0 license and has undergone independent penetration testing. The README positions the tool as a runtime and fleet-management layer distinct from agent authoring, i.e. the operational counterpart to code-generation tools rather than a code generator itself.

https://github.com/Abilityai/trinity

agent-orchestrationai-agentsself-hosteddockerobservabilityaudit-trail

Also in Workflow Orchestration for AI

ComposioHQ/composio

Composio provides SDKs for building AI agents capable of interacting with over 1000 tools, offering capabilities like tool search, context management, and authentication across various AI frameworks.

TencentCloud/TencentDB-Agent-Memory

TencentDB Agent Memory is a memory management system for AI agents, featuring a 4-tier progressive pipeline to improve efficiency and reasoning by categorizing and condensing agent memories without...

TransformerOptimus/SuperAGI

SuperAGI is an open-source framework designed for building, managing, and running autonomous AI agents, offering tools for deployment, capability extension, and performance monitoring.

dataelement/bisheng

BISHENG is an open LLM application DevOps platform focusing on enterprise scenarios, providing comprehensive features for GenAI workflows, RAG, agents, model management, evaluation, and enterprise-...

iflytek/astron-agent

Astron Agent is an enterprise-grade platform for building, orchestrating, and deploying AI agent applications with integrated RPA, model management, and high-availability features.

0xPlaygrounds/rig

Rig is a Rust library designed for building modular and scalable LLM-powered applications, offering a unified interface for multiple model providers and vector stores.

plastic-labs/honcho

Honcho is a memory infrastructure for building stateful AI agents, enabling them to understand and retain information about people, agents, groups, projects, and ideas over time.

julep-ai/julep

Julep is an open-source platform for building, orchestrating, and self-hosting agent-based AI workflows with persistent memory and tool integration.