Back to directory

Brigade

A self-hosted, open-source ecosystem of AI agents that share long-term memory, work across many messaging apps, and can switch models mid-task.

Brigade

Brigade organizes a crew of agents on an org chart that share one long-term memory store called Tideline, so what one agent learns is available to the rest. Agents delegate tasks to each other, switch between models such as Claude, GPT, Gemini, Llama, or a local Ollama model without losing context, and act inside a large set of connected applications, with privileged actions waiting for explicit approval.

It can run on hardware as small as a Raspberry Pi or on a server, defaults to a small filesystem install, and can switch to a self-hosted Convex database. Users reach the crew from a terminal or from chat apps including WhatsApp, Telegram, Slack, Discord, and iMessage.

Keys and data stay on the user's own machine, and the project reports no telemetry.

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.