Back to directory

AgentTeams

A DeepSeek Harness plugin that turns the current session into a captain able to assemble durable sub-agents, split a goal into dependency-aware tasks, and coordinate them through direct messages and a live web UI.

AgentTeams

AgentTeams is a plugin for DeepSeek Harness that turns the current session into a captain that assembles a team of durable sub-agents, splits a goal into dependency-aware tasks, and coordinates work between them through direct messages, without needing a separate workflow engine. It provides the team protocol, 14 coordination tools, persistent state, and an automatic shared-task scheduler.

Members are continuable sub-agents that can be woken for focused follow-up turns; tasks move through explicit states and cannot be claimed before their dependencies finish; idle members automatically claim the next ready task, and reassignment revokes stale attempts while cold recovery retries stranded ones. A live web UI shows segmented progress, a collapsible roster and an interactive task graph, and every run first stages an unspawned roster and task plan for approval before any member starts work. Optional quality gates add a requirements-implementation-verification-review-integration pipeline with automatic repair and re-review.

It is written in JavaScript under the MIT license.

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.