Back to directory

Chamber

An Electron desktop workspace for creating, running and coordinating AI agents ('minds') powered by GitHub Copilot, built around Agent-to-Agent collaboration: minds discover each other, message each other, delegate stateful tasks and hand off artifacts.

Chamber

Chamber is a desktop application, built with Electron, for running several AI agents together rather than treating chat as the whole interface. Each agent, called a mind, has its own identity, memory, tools, scheduled work and UI that can grow with the tasks it is given, and minds are built around Agent-to-Agent collaboration: they expose Agent Card-style metadata describing their skills so other minds can discover what they do, send each other direct messages, create stateful tasks that can be tracked, checked on or canceled, and share context across a conversation through a shared context ID, with task results becoming artifacts another mind can review or build on.

Beyond chat, Chamber provides Lens views, Canvas pages, tables, timelines, forms and status boards as practical desktop tools, plus built-in cron jobs, conversation history, model selection and desktop notifications, and marketplace-installed minds extend what is available. Multiple minds can collaborate in a chatroom under concurrent, sequential, moderated, handoff or manager-led modes.

It downloads as a Windows desktop application and is powered by GitHub Copilot for its underlying model access.

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.