Turn repeatable agent research into an AgentRun workflow DSL
Show HN for AgentRun: split a research question into subquestions, fan out agents, screen evidence, then write the report—inspect each step without paying for a full agent loop every time.
Topic
orchestration use cases: 12 examples
Source-linked workflows that name orchestration. Part of the AI agent use cases on UsecaseBoard, or browse all use cases.
When to build an agent: fraud, refunds, vendor review, insurance claims
OpenAI’s practical guide frames agents for complex judgment (fraud/refunds), brittle rule piles (vendor security reviews), and unstructured docs (home insurance claims)—not for simple deterministic checklists.
Nine Grok Bot agents bought domains on my card while I stayed on Saturday
A founder spun up nine Grok Bot agents plus an orchestrator sharing one Obsidian vault on xAI Premium; after he approved, an agent purchased domains with his credit card and he went back to his weekend.
Root Agent: Grok Bot coordinator that sizes multi-bot teams
Marketplace bot by Berkay that turns a request into a right-sized Grok Bot crew: clarifies goals, spins up Leads and specialists, tracks delivery, archives closed work, and returns verified results—built for people already running work across multiple Bots (v0.2.1 adds difficulty-based headcount and safer cleanup).
Tern: free native fleet IDE—one worktree per agent, one review queue
Tern is a free closed-source Mac-native (CLI/TUI also on Linux) control plane for 16 coding-agent CLIs: each task gets its own git worktree/branch, changes land in one review queue with comments routed back to the agent, conflict radar, multi-step runs with gates, phone approvals without Tern servers, and a daemon that keeps agents alive after you close the window.
Bandito: Mac crew that runs Claude Code/Codex/Grok on your servers
Native macOS app orchestrates official Claude Code, Codex and Grok CLIs as a role-based crew (lead/builder/reviewer/docs/auditor/on-call) on your Mac or VPS with schedules, one-click risky-command approvals (Telegram too), and server screen/browser/terminals—no Bandito cloud for your code.
Paseo: cross-device control plane for many coding agents
Apache-2.0 Paseo runs Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity, and Muse Code in isolated worktrees from desktop, native mobile, or remote hosts—with MCP/CLI/SDK automation, plugins, and optional E2E-encrypted relay so you steer agents without changing their subscriptions.
Google AX: Kubernetes-style orchestrator for agent workloads
Google’s open AX runtime declares Task/Workspace/Model manifests on Agent Substrate: sandboxed agent jobs with git/MCP/skills pre-wired, suspend/resume, and ax ssh—aimed at high-throughput cluster runs of autonomous agents, not one laptop session.
Band for Developers: desktop control plane for multi-agent coding
Thenovi AI (Band) launched a desktop app plus CLI so engineers can see fleets of coding agents at once—projects, ownership, blockers, questions, progress—and intervene without manually shuttling session context between isolated harnesses.
Sakana Agentic Scientist v3: coding agents as experiment loop
Open pipeline turns a task.md into idea→experiments→ablations→sealed eval→paper, orchestrating coding agents (Docker/yolo by default) for automated scientific co-discovery.
agent-teams-mcp: Claude Code lead with push worker replies
Rust MCP server makes Claude Code the team lead over Claude/Codex/Gemini workers; Stop-hook + asyncRewake pushes replies (~50ms) into the lead session, with a local live team UI.
OpenCode 2.0: one local service, Code Mode MCP, background subagents
Anomaly OpenCode 2.0 (Oct 12; changelog still shipping 2.0.x Oct 16): auto-started local background service shared by TUI/web/desktop; rewritten API + @opencode/client; @opencode/codemode turns MCP/OpenAPI into scriptable functions (all MCP servers default to Code Mode); background subagents + async shell; 80+ hot-reload plugins; @opencode/sdk for embed. Upgrade: `opencode upgrade --major`.