agent-fleet

Plan, run and supervise fleets of agents from task to merged PR. Desktop (macOS, Windows, Linux) + iPhone & Android apps. Supports Claude Code, Codex & 35+ coding agents.

The open-source governance layer for AI agents: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

Open-Source Software factory for Open Models

Asynchronous Pi subagents and agent fleet orchestration for parallel coding agents with nested delegation, background work, and supervision in herdr.

Turn tracker tickets into autonomous agent sessions

Run many Claude Code (or Codex) sessions in parallel — across every project — from one screen. Local-first, git-worktree-isolated tasks, no API key.

Long-running fleet orchestration and memory infrastructure for AI agents. Enables persistent context, shared memory, task execution, and governed coordination across multi-agent systems.

Multi-agent memory governance demo using Caura + OpenClaw. Three agents (Sales, Legal, Admin) share one memory backend with hard fleet boundaries enforced at the query layer. Shows scoped writes, blocked recall, cross-fleet synthesis, and conflict detection.

A runnable reference implementation of multi-agent constraint propagation using Caura. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.

Self-hosted remote control for Claude Code, Codex, OpenCode, Kimi Code, Grok Build and Cursor: run coding agents on your own machines and supervise them from anywhere, end-to-end encrypted.

OpenRouter for agents and sandbox environments. Provides a control plane and configuration options for persistent agent workers. Route runtime + substrates, provision specialist presets, and supervise your fleet.

Herd: open-source meta-harness for agent fleets

Swarm is a headless AI agent platform you self-host on Linux. It runs coding, research, design and media agents, workflows, schedules and monitoring across your machines. Drive it from your AI over MCP, or from your own code with the SDK, HTTP API or CLI.

Donmai is an open-source agent runtime for running local agent fleets across coding harnesses, with isolated workareas and a terminal dashboard. MIT-licensed.

Codex skill for diagnosing Hermes Desktop remote fleet routing and workspace issues

An open registry of 76 fully specified AI agent skills — taxonomy, canonical schema, composer, governance model, and a fleet runner that deploys hundreds of agents against one objective and rehearses them against their own definitions.

A github issue agent to provide detail PRD for new issue.

Governed agent fleets for an enterprise. platform/ is the build: append-only output ledger, provenance cascade, computed scope, agent registry, time-boxed invoke grants, audit trail. skills/ is the personal control plane — routing + per-agent memory as Claude Code skills.

Task-coordination store for agent fleets — a dependency graph of beads in SQLite, one unblocked bead per request via an atomic single-transaction claim, and a git-tracked checkpoint for recovery. Rust.

A Claude Code plugin to plan, launch and watch a fleet of coding agents: goal, org chart, per-agent model and effort, time budget, and a live dashboard.