agent-orchestration-standard vs claude-code-karma
Read-only live monitor for Claude Code: a streaming graph of sessions, subagents, tokens, cost, file conflicts and alerts, as plugin, TUI and MCP server. Ships the AOS-1 spec. — versus — Local-first dashboard over ~/.claude — sessions, timelines, per-session costs, tool/agent/skill/plugin analytics, live activity via hooks, and ticket linking. No cloud, no telemetry.
Both are local dashboards over Claude Code sessions. Karma is retrospective; AOS is a live stream.
| agent-orchestration-standard | claude-code-karma | |
|---|---|---|
| Stars | 103 | 337 |
| Forks | 22 | 35 |
| Language | JavaScript | Python |
| License | MIT | Apache-2.0 |
| Last activity | 2 days ago | yesterday |
| Topics | orchestration, coding | coding |
| Curated connections | 3 | 6 |
agent-orchestration-standard — the curator's take
Use it to watch what parallel Claude Code sessions and subagents are doing right now, with replay and alerts, at no install cost (no dependencies). Despite the name, it does not orchestrate anything: that is a separate experimental repo. Active development has moved to Fenceline, so this repo may go stale. Claude Code only.
claude-code-karma — the curator's take
Your ~/.claude directory is a goldmine Claude Code never shows you — Karma turns the JSONL into browsable sessions with full chronological timelines, cost and cache-hit breakdowns, subagent trees, and a surprisingly complete inventory of every plugin, skill, and hook you've installed with usage stats. Read-only ticket linking (Linear/Jira/GitHub) is the team-ready touch. Know the limits: Claude Code prunes session data after ~30 days, so history evaporates unless you keep Karma indexing; it's a two-process dev setup (FastAPI + SvelteKit), not a single binary; and it's Claude-only — no Codex/OpenCode. Pair with ai-token-monitor when all you want is the spend number next to your clock.