quoroom 0.1.30 → 0.1.32
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +29 -20
- package/out/mcp/api-server.js +3705 -4370
- package/out/mcp/cli.js +2193 -3128
- package/out/mcp/server.js +413 -594
- package/package.json +12 -9
package/README.md
CHANGED
|
@@ -49,7 +49,7 @@ See `TRADEMARKS.md` for full trademark usage terms.
|
|
|
49
49
|
|
|
50
50
|
Run a swarm of AI agents that pursue goals autonomously. The Queen strategizes, a swarm of Workers execute, and the Quorum votes on decisions. Agents learn new skills, modify their own behavior, manage a crypto wallet, and rent cloud stations for more compute — all governed by democratic consensus.
|
|
51
51
|
|
|
52
|
-
|
|
52
|
+
Always-on autonomous execution is inevitable. It's already happening behind closed doors. We believe it should happen in the open — publicly, transparently — so everyone can learn. Quoroom is an experiment: let's see what AI swarms can actually execute.
|
|
53
53
|
|
|
54
54
|
The architecture draws from swarm intelligence research: decentralized decision-making, emergent behavior from local interactions, and collective intelligence that exceeds any individual agent. The queen doesn't dictate — the swarm decides.
|
|
55
55
|
|
|
@@ -66,7 +66,7 @@ Quoroom is an open research project exploring autonomous agent collectives. Each
|
|
|
66
66
|
|
|
67
67
|
## This Repo
|
|
68
68
|
|
|
69
|
-
`quoroom-ai/room` is the engine: agent loop, quorum governance, goals, skills, self-modification, wallet, stations, memory, task scheduling,
|
|
69
|
+
`quoroom-ai/room` is the engine: agent loop, quorum governance, goals, skills, self-modification, wallet, stations, memory, task scheduling, MCP server, HTTP/WebSocket API, dashboard UI, and CLI.
|
|
70
70
|
|
|
71
71
|
| Repo | Purpose |
|
|
72
72
|
|------|---------|
|
|
@@ -101,13 +101,11 @@ Quoroom is an open research project exploring autonomous agent collectives. Each
|
|
|
101
101
|
|
|
102
102
|
**Webhooks** — HTTP endpoints to trigger tasks or wake the queen from any external service. GitHub push, Stripe payment, monitoring alert — any system that can POST to a URL can drive your agents. Per-task and per-room tokens, 30 req/min rate limiting, no auth setup required beyond the URL.
|
|
103
103
|
|
|
104
|
-
**
|
|
104
|
+
**Keeper Control Model** — Rooms run in a keeper-controlled mode with full dashboard/API control for agent and user tokens. Cloud member tokens are read-only plus limited collaboration endpoints (vote, resolve/reply, mark read).
|
|
105
105
|
|
|
106
|
-
**
|
|
106
|
+
**Public Rooms** — Toggle your room public on [quoroom.ai/rooms](https://quoroom.ai/rooms). Live room stats and activity appear on the leaderboard. Room registers with cloud and sends heartbeats every 5 minutes. No account needed to browse.
|
|
107
107
|
|
|
108
|
-
**
|
|
109
|
-
|
|
110
|
-
**HTTP Server + REST API** — Full REST API with dual-token auth (agent + user) and WebSocket real-time events. Role-based access control per autonomy mode. Run `quoroom serve` to start.
|
|
108
|
+
**HTTP Server + REST API** — Full REST API with dual-token auth (agent + user) and WebSocket real-time events. Cloud member role uses constrained collaboration access. Run `quoroom serve` to start.
|
|
111
109
|
|
|
112
110
|
**Dashboard** — React SPA served directly by your local Quoroom server at `http://localhost:3700` (or your configured port). Manage rooms, agents, goals, memory, wallet — all from the browser, with local-first data storage.
|
|
113
111
|
|
|
@@ -144,8 +142,8 @@ Quoroom is an open research project exploring autonomous agent collectives. Each
|
|
|
144
142
|
│ └────────┘ └──────────┘ └────────────────┘ │
|
|
145
143
|
│ │
|
|
146
144
|
│ ┌──────────────────────────────────────────┐ │
|
|
147
|
-
│ │ Auth: agent token
|
|
148
|
-
│ │ Access:
|
|
145
|
+
│ │ Auth: agent token + user token + member │ │
|
|
146
|
+
│ │ Access: agent/user full · member scoped │ │
|
|
149
147
|
│ └──────────────────────────────────────────┘ │
|
|
150
148
|
└────────────────────┬────────────────────────────┘
|
|
151
149
|
│
|
|
@@ -304,6 +302,7 @@ The room engine exposes an MCP server over stdio. All tools use the `quoroom_` p
|
|
|
304
302
|
| `quoroom_set_goal` | Set a room's primary objective |
|
|
305
303
|
| `quoroom_create_subgoal` | Decompose a goal into sub-goals |
|
|
306
304
|
| `quoroom_update_progress` | Log a progress observation |
|
|
305
|
+
| `quoroom_delegate_task` | Delegate a task to a specific worker |
|
|
307
306
|
| `quoroom_complete_goal` | Mark a goal as completed |
|
|
308
307
|
| `quoroom_abandon_goal` | Abandon a goal |
|
|
309
308
|
| `quoroom_list_goals` | List goals for a room |
|
|
@@ -351,16 +350,6 @@ The room engine exposes an MCP server over stdio. All tools use the `quoroom_` p
|
|
|
351
350
|
| `quoroom_delete_task` | Delete a task |
|
|
352
351
|
| `quoroom_reset_session` | Clear session continuity for a task |
|
|
353
352
|
|
|
354
|
-
### File Watching
|
|
355
|
-
|
|
356
|
-
| Tool | Description |
|
|
357
|
-
|------|-------------|
|
|
358
|
-
| `quoroom_watch` | Watch a file/folder for changes |
|
|
359
|
-
| `quoroom_unwatch` | Stop watching |
|
|
360
|
-
| `quoroom_pause_watch` | Pause a watch |
|
|
361
|
-
| `quoroom_resume_watch` | Resume a paused watch |
|
|
362
|
-
| `quoroom_list_watches` | List active watches |
|
|
363
|
-
|
|
364
353
|
### Memory
|
|
365
354
|
|
|
366
355
|
| Tool | Description |
|
|
@@ -409,11 +398,19 @@ The room engine exposes an MCP server over stdio. All tools use the `quoroom_` p
|
|
|
409
398
|
|
|
410
399
|
| Tool | Description |
|
|
411
400
|
|------|-------------|
|
|
412
|
-
| `
|
|
401
|
+
| `quoroom_send_message` | Send a message to the keeper or another worker |
|
|
413
402
|
| `quoroom_inbox_send_room` | Send a message to another room |
|
|
414
403
|
| `quoroom_inbox_list` | List inbox messages |
|
|
415
404
|
| `quoroom_inbox_reply` | Reply to a room message |
|
|
416
405
|
|
|
406
|
+
### Invite
|
|
407
|
+
|
|
408
|
+
| Tool | Description |
|
|
409
|
+
|------|-------------|
|
|
410
|
+
| `quoroom_invite_create` | Create an invite link for your room |
|
|
411
|
+
| `quoroom_invite_list` | List invite links and usage |
|
|
412
|
+
| `quoroom_invite_network` | View rooms in your invite network |
|
|
413
|
+
|
|
417
414
|
### Credentials
|
|
418
415
|
|
|
419
416
|
| Tool | Description |
|
|
@@ -427,6 +424,18 @@ The room engine exposes an MCP server over stdio. All tools use the `quoroom_` p
|
|
|
427
424
|
|------|-------------|
|
|
428
425
|
| `quoroom_resources_get` | Get local system resources (CPU, memory, disk) |
|
|
429
426
|
|
|
427
|
+
### Browser
|
|
428
|
+
|
|
429
|
+
| Tool | Description |
|
|
430
|
+
|------|-------------|
|
|
431
|
+
| `quoroom_browser` | Control a headless browser for multi-step web flows |
|
|
432
|
+
|
|
433
|
+
### WIP
|
|
434
|
+
|
|
435
|
+
| Tool | Description |
|
|
436
|
+
|------|-------------|
|
|
437
|
+
| `quoroom_save_wip` | Save in-progress context for later continuation |
|
|
438
|
+
|
|
430
439
|
### Settings
|
|
431
440
|
|
|
432
441
|
| Tool | Description |
|