aegra/aegra

Open source alternative to LangGraph Platform (now LangSmith Deployments) - Self-hosted AI agent backend with FastAPI and PostgreSQL. Zero vendor lock-in, full control over your agent infrastructure.

What it solves

Aegra provides a self-hosted alternative to LangSmith Deployments, allowing developers to deploy and manage AI agents built with LangGraph without relying on a proprietary cloud service. It eliminates vendor lock-in by allowing users to maintain full control over their own infrastructure, data residency, and database (PostgreSQL).

How it works

Aegra acts as a drop-in replacement for LangSmith Deployments by using the same LangGraph SDK and APIs. It leverages a worker architecture with a Redis job queue for horizontal scaling and crash recovery. For persistence, it uses PostgreSQL for checkpoints and pgvector for semantic storage. It also implements the Agent Protocol to ensure compatibility with various agent UIs.

Who it’s for

Developers and organizations that want to deploy LangGraph agents on their own infrastructure while maintaining compatibility with the LangGraph SDK and existing agent-chat interfaces.

Highlights

  • Self-hosted infrastructure: Full control over data and deployment using PostgreSQL and Redis.
  • Agent Protocol compliance: Compatible with Agent Chat UI, LangGraph Studio, and CopilotKit.
  • Agent Protocol v2 streaming: Supports thread-scoped SSE with content-block events and native human-in-the-loop resume.
  • Worker architecture: Redis-based job queue supporting horizontal scaling and lease-based crash recovery.
  • Scheduled cron jobs: Built-in support for triggering agent runs on a schedule with timezone support.
  • Unified Observability: Fan-out tracing via OpenTelemetry to backends like Langfuse or Phoenix.
  • Flexible Authentication: Support for JWT, OAuth, and Firebase handlers.

Related

  • Project
    langchain-ai/agent-chat-ui

    Agent Chat UI is a Next.js front‑end that lets you chat with any LangGraph server. Configure the server URL, assistant ID, and optional LangSmith key, then use the web UI to send messages, stream LLM replies, hide unwanted output via special tags, and display extra “artifacts” in a side panel. The repo includes a quick‑start (`npx create-agent-chat-app`), environment‑variable shortcuts, and production guidance (API‑passthrough proxy or custom authentication).

  • Project
    JoshuaC215/agent-service-toolkit

    A full-stack toolkit for building and deploying AI agent services, combining LangGraph for agent logic, FastAPI for the API, and Streamlit for the chat interface.

  • Project
    EpicStaff/EpicStaff

    A self-hosted AI agent orchestration platform that allows operations teams to visually design, manage, and audit agent workflows while engineers handle the system integrations.

  • Project
    langchain-ai/langchain-aws

    A collection of LangChain and LangGraph components that integrate AWS services like Bedrock, SageMaker, and DynamoDB for building AI agents and RAG applications.

  • Project
    labring/FastGPT

    FastGPT is an open‑source platform for building AI agents and LLM‑driven applications. It provides a visual Flow editor, knowledge‑base (RAG) support, plugin hot‑reloading, debugging tools, and can be run locally via Docker or deployed on Sealos/Kubernetes. A hosted SaaS version and a commercial edition are also offered.