Back to directory

C2S Agent

A lightweight AI agent construction platform with configurable, hosted agents and MCP services, letting a user turn any HTTP endpoint into an MCP tool and have agents communicate with each other over A2A.

C2S Agent

C2S Agent is a lightweight platform for building AI agents online, where an agent is configured rather than coded: a user supplies an LLM URL, an API key and a description, and can bind an MCP service to it.

An MCP service is likewise configured by wrapping existing HTTP request interfaces as MCP tools, without writing a dedicated server, and agents can then communicate with each other over the A2A protocol to work as a team. It extends the A2A and MCP protocols to run multiple agent or MCP services behind a single port, selected by an agent or server index passed with the request.

It is built with Python, MongoDB and PostgreSQL, and deploys its backend and Vue frontend with Docker Compose.

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.