Agent Coordination Python Packages

agent-parley

Run Claude Code, Codex, Copilot, Gemini, OpenCode and Amp side by side in isolated Git worktrees, with shared issue ownership, reservations and explicit handoffs.

fcop-mcp

FCoP — file-based behavior-governance protocol for multi-agent AI. Tasks, reports, review, evidence, and lifecycle state over ordinary files; Python + MCP.

fcop

FCoP — file-based behavior-governance protocol for multi-agent AI. Tasks, reports, review, evidence, and lifecycle state over ordinary files; Python + MCP.

firekeep-client

Self-hosted shared context, memory, coordination, and evidence for Claude Code, Codex, Kiro, OpenCode, and MCP agents.

agent-coordination-substrate

Wiggle (wiggle.network): a privacy-first, agent-native coordination layer — A2A + MCP messaging, three-tier rooms (public / invite-only / private), inbox, per-agent memory, roles, polls, and file exchange. Self-signup, no approval. Built on a clear stance about agent autonomy — the essay is on the site.

okto-nexus

Local-first MCP coordination hub for multi-agent teams, with durable messaging, handoffs, governance, and observability.

squads

The coordination layer for a team of AI agents working on one - stable IDs, roles, and handoffs, all in plain markdown.

ememdev

emem is the machine-maintained, external memory of our physical world a.k.a. Satellites for AI.

emem-langmem

Satellites for AI. emem is the machine-maintained, external memory of our physical world.

fleetpost-mcp

Offline-tolerant, server-less coordination for AI coding agents (Claude Code and friends) across machines — carried by any rclone remote (Drive/S3/Dropbox).

claude-agent-sync

Coordinate multiple AI coding-agent sessions in one repo: shared tasks, file locks, and live messaging over a local SQLite layer — no server, no network. Ships as a Claude Code skill + hooks and an agent-agnostic CLI.

agent-commons

Private, self-hosted coordination control plane for coding agents

mpac

Application-layer protocol for AI agents serving different principals to coordinate over shared state. 📦 PyPI: https://pypi.org/project/mpac/ · Spec, Python + TypeScript reference implementations, two-machine demo.

swarmmesh-cli

Shared context and memory coordination layer for swarms of parallel AI agents. Documented HTTP + WebSocket protocol, interoperable Python and Node CLIs, BM25 keyword memory search, built-in MCP server for agent tool calls.

slm-mesh

Peer-to-peer communication for AI coding agents. 8 MCP tools, full CLI, Python client. Part of the Qualixar research initiative by Varun Pratap Bhardwaj.

mmcp-core

Multi-Model Collaboration Pipeline — orchestrate AI models as a DAG. RL routing, multi-verifier voting, agent mesh, self-improving. Works with OpenAI, Anthropic, Gemini, DeepSeek. npm install mmcp-core | pip install mmcp-core

animus-forge

Personal AI operating environment with evidence-graded maturity, local-first control, and autonomous improvement.

ainl-native

Graph-native memory and self-learning for Claude Code. Every session remembered, every pattern learned, every agent connected — powered by AI Native Lang.

animus-bootstrap

Personal AI operating environment with evidence-graded maturity, local-first control, and autonomous improvement.

swarlo

Open coordination protocol for AI agent + human teams. Inspired by agenthub.

convergentai

Personal AI operating environment with evidence-graded maturity, local-first control, and autonomous improvement.

causal-field

Gaussian resource-contention fields for multi-agent coordination

yutha

Open-source infrastructure for groups of AI agents — identity, capability, accountability, and norms. Framework-agnostic.

animus-kernel

Personal AI operating environment with evidence-graded maturity, local-first control, and autonomous improvement.