Multi-AI CLI Team Orchestrator
Multi-AI CLI team orchestrator that dispatches work to gemini, codex, opencode, cursor, kilo, and custom agents with judge, peer-review, experiment loops, and a local web dashboard.
curl -fsSL https://aid.agent-tools.org/install.sh | sh
One CLI for gemini, codex, opencode, cursor, kilo, and custom agents. Same flags and workflow across all of them.
Watch background tasks in real time with aid watch, the TUI, or the local web dashboard.
Per-agent usage, budgets, and spend windows. Set limits and run low-value work with --budget.
Per-task worktrees, auto-merge, and escape detection. Parallel work without polluting the main branch.
--judge, --peer-review, and --best-of let you auto-review, score, and compare agent outputs.
Autonomous edit-measure-keep/revert cycles. Optimize any metric across iterations with aid experiment run.
--judge auto-reviews output, --peer-review sends to another agent for scored (1-10) critique.
--cascade opencode,codex,cursor auto-retries with the next agent on failure. No manual retry needed.
Dispatch the same task to N agents, run quality metrics, and keep the best result.
Local web UI for live task monitoring, agent status, and workgroup overview.
Run TOML batch files with dependency scheduling, parallel execution, concurrency limits, and conditional chains.
Let aid pick the best agent for the task from capability scores and history.
Project-scoped discoveries, conventions, and lessons auto-injected into agent prompts.
Define agents in ~/.aid/agents/ so any CLI or wrapper can join the orchestrator.
aid watch --tui for live progress, stats view, and task timeline.
Role-based agent groups with knowledge context, behavioral rules, and capability overrides via --team.
Per-repo .aid/project.toml with hobby/standard/production presets for verify, budget, and rules.
Stop-word filtering, cross-layer dedup, and relevance scoring keep agent prompts lean and focused.
Input sanitization, worktree sandbox guards, shell injection prevention, and path traversal protection.
Batch resilience, process group management, on_done child reaping, idle timeout, and double-dispatch prevention.
Subprocess concurrency limits, --dir agent isolation via GIT_CEILING_DIRECTORIES, zero production unwrap().
Claude Code as a first-class agent with auto-selection support, streaming output, and full orchestration integration.
GitHub Copilot CLI as a built-in agent with setup, selection, pricing, sandbox, and usage integration.
Tiered memory injection, compact prompt format, and knowledge graph CLI for richer agent context.
Real-time progress visibility in quiet batch mode, smarter concurrency limits, and isolated best-of-N output paths.
When an agent hits its rate limit, aid auto-falls back to the next capable agent in the chain.
aid merge --approve for interactive Merge/Retry/Skip decisions via hiboss before merging.
aid stop / aid stop --force for termination, aid steer for mid-flight guidance injection.
Browse and install community agents from the GitHub-backed store with version pinning.
aid hook session-start integrates with Claude Code's SessionStart lifecycle for automatic context injection.
--dry-run previews dispatch without running. --read-only prevents file writes for safe research tasks.
| Command | Purpose | Example |
|---|---|---|
| run | Dispatch task with --judge, --peer-review, --cascade, --best-of, --timeout, --read-only, --dry-run, plus bg/verify/worktree/context/scope/skill flags. | aid run codex "Refactor auth" --verify --judge --cascade opencode,cursor |
| batch | Run TOML batch files with DAG scheduling. Subcommands: init (template), retry (re-dispatch failures). | aid batch tasks.toml --parallel --max-concurrent 3 |
| experiment | Autonomous experiment loop: edit, measure, keep/revert. Optimize any metric across iterations. | aid experiment run codex "Optimize parser" --metric "cargo bench" --max-runs 5 |
| benchmark | Compare the same task across multiple agents. | aid benchmark --agents codex,cursor "Implement parsing" |
| watch | Follow live progress in text, quiet, or TUI mode. | aid watch --tui |
| board | List tracked tasks with filters and zombie detection. | aid board --today |
| completions | Print the most recent completion notifications. | aid completions |
| show | Inspect task summary, diff, output, log, or AI explanation. | aid show t-1234 --diff |
| usage | View task history, per-agent analytics, and budget windows. | aid usage --agent codex --period 7d |
| retry | Re-dispatch a failed task with feedback, optionally switching agent or dir. | aid retry t-1234 -f "Fix the error" --agent opencode |
| respond | Send interactive input to a running background task. | aid respond t-1234 "Rerun with logging" |
| stop | Stop a running task. Graceful by default, --force for immediate SIGKILL. | aid stop t-1234 --force |
| steer | Inject guidance into a running PTY task mid-flight. | aid steer t-1234 "Switch to approach B" |
| output | Show task output directly without additional metadata. | aid output t-1234 |
| ask | Quick research or exploration task. | aid ask "How does retry work in this repo?" |
| mcp | Start the stdio MCP server for Claude Code or other MCP clients. | aid mcp |
| merge | Mark done tasks as merged. --group for bulk, --approve for interactive approval. | aid merge --group wg-a3f1 --approve |
| clean | Remove old tasks, orphaned worktrees, and logs. | aid clean --days 30 |
| agent | Manage custom agent definitions: list, show, add, remove, fork. | aid agent fork codex --as codex-fast |
| config | Inspect agents, skills, pricing, templates, and prompt token budget. | aid config pricing --update |
| worktree | Manage worktree lifecycle (create/list/remove). | aid worktree create --dir feat/parser |
| group | Workgroup management: create, list, show, update, delete, summary, finding, broadcast. | aid group summary wg-a3f1 |
| store | Browse, install (with version pinning), and update community agent packages. | aid store install sunoj/aider |
| upgrade | Upgrade aid to latest version from crates.io. | aid upgrade |
| memory | Manage project-scoped agent memory (discoveries, conventions, lessons, facts). | aid memory add discovery "Auth uses bcrypt" |
| export | Export a task with full context in markdown or JSON. | aid export t-1234 --format json |
| tree | Show retry chain as an ASCII tree. | aid tree t-1234 |
| query | Fast LLM query via OpenRouter (no agent startup). Free and auto tiers. | aid query "question" |
| setup | Interactive setup wizard. Detects agents, sets API keys, initializes skills. | aid setup |
| team | Manage teams with knowledge context, rules, and agent preferences. | aid team list |
| project | Per-repo project profiles (.aid/project.toml) with built-in presets. | aid project init |
| hook | Claude Code lifecycle hooks for aid context injection. | aid hook session-start |
Each agent wraps a different AI CLI. aid run auto picks the best fit based on task type, model capability, cost, and rate limits. Define custom agents in ~/.aid/agents/.
Research, web search, fact-checking, documentation
Complex implementation, multi-file refactors, test suites
Simple edits, renames, type fixes, quick patches
Simple edits and renames (free tier)
Frontend/UI, general coding, strong model routing
┌─────────────────────────────────────┐ │ aid (CLI binary) │ ├──────┬──────┬──────┬───────┬────────┬───────────┤ │ run │ watch│ show │ board │ usage │experiment │ ← commands ├──────┴──────┴──────┴───────┴────────┤ │ Task Manager │ │ ┌────────┐ ┌────────┐ ┌────────┐ │ │ │Classif.│ │ Watch │ │ Store │ │ │ │+ Agent │ │ Engine │ │(SQLite)│ │ │ │Registry│ │ │ │ │ │ │ └────┬───┘ └────┬───┘ └────┬───┘ │ │ │ │ │ │ ├───────┴──────────┴──────────┴───────┤ │ Agent Adapters │ │ ┌──────┐ ┌─────┐ ┌────────┐ ┌──────┐ ┌────┐ │ │Gemini│ │Codex│ │OpenCode│ │Cursor│ │Kilo│ │ └──────┘ └─────┘ └────────┘ └──────┘ └────┘ └─────────────────────────────────────┘
Install aid. No Rust toolchain required — pre-compiled binaries for macOS and Linux.
Run aid setup to configure API keys and detect installed agents.
Set up your project profile and dispatch tasks.