Back to directory

Agent-Graph

A multi-agent system built around Context Engineering principles, combining sub-agents, long-term memory, MCP, and agent-based workflows in a visual development environment for building and deploying multi-agent applications.

Agent-Graph

Agent-Graph integrates sub-agents, long-term memory, MCP, and agent-based workflow orchestration into a visual builder for multi-agent applications, aiming to let developers assemble and test complex agent systems without hand-writing every workflow.

It deploys with Docker Compose for its backing services, including MongoDB and MinIO for file storage, and a FastAPI backend that can run with uv or plain pip, alongside a separate frontend for development. A generated JWT secret and other credentials are configured through an environment file before the Docker services start, and the running application exposes its own API documentation and health-check endpoints.

The project is documented primarily in English and Chinese and maintained through its own documentation site.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.