@lmctl-ai/lmctl 0.1.126 → 0.1.128

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.
Files changed (3) hide show
  1. package/README.md +11 -13
  2. package/dist/cli/index.js +619 -774
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -4,8 +4,8 @@
4
4
 
5
5
  [Homepage](https://lmctl.com) · [Documentation](https://lmctl.com/lmctl) · [Changelog](https://lmctl.com/lmctl/docs/changelog)
6
6
 
7
- AI agents shouldn't be locked to one provider, one workflow, or one context
8
- window. **lmctl** is a local-first control plane for running *teams* of AI coding
7
+ AI agents shouldn't be locked to one provider or one context window. **lmctl**
8
+ is a local-first control plane for running *teams* of AI coding
9
9
  agents — across providers, with adversarial cross-provider review and durable
10
10
  memory, composed in plain text. It coordinates the agent CLIs you already use
11
11
  (Claude, Codex, Gemini, and more); it's not an IDE and not another chatbot.
@@ -41,7 +41,6 @@ npm install -g @lmctl-ai/lmctl
41
41
  ```sh
42
42
  lmctl --help
43
43
  lmctl status
44
- lmctl run https://lmctl.com/workflows/research.compound.json
45
44
  lmctl plan ./my-project
46
45
  lmctl lint ./my-project/my-project.lmctl
47
46
  lmctl seed ./my-project/my-project.lmctl
@@ -54,23 +53,22 @@ pending mailbox lanes. From a plain operator shell it shows a workspace summary.
54
53
  Use `lmctl status --json` for the full machine-readable view; `--project` and
55
54
  `--web` are not status flags.
56
55
 
57
- Start with `lmctl run <url>` for published workflows. For a custom AI-Lead team,
58
- use the plan -> lint -> seed -> chat flow. lmctl does not manage foreground vs.
59
- background execution for provider turns or shell commands; use the provider or
60
- host runtime's own background/task surface when you need async execution.
56
+ Start with the plan -> lint -> seed -> chat flow. lmctl does not manage
57
+ foreground vs. background execution for provider turns or shell commands; use
58
+ the provider or host runtime's own background/task surface when you need async
59
+ execution.
61
60
  Daemon, web, API, and MCP surfaces are secondary integration paths; the CLI is
62
61
  the golden path for onboarding.
63
62
  Lintable teamfile templates for research, writing, and review teams ship in the
64
63
  [examples gallery](https://lmctl.com/examples/).
65
64
 
66
- `lmctl` top-level subcommands are: `api`, `chat`, `code`, `serve`, `intake`,
67
- `mcp`, `monitor`, `device`, `team`, `terminal`, `tail`, `health`,
68
- `recover`, `ls`, `lint`, `seed`, `hire`, `refresh`, `clone`, `plan`, `workflow`,
69
- `run`, `project`, `workspace`, `diagnose`, `diagnose-prompt`, `status`, and
70
- `db`. Run `lmctl <command> --help` for details on each, and see the
65
+ `lmctl` top-level subcommands are: `api`, `chat`, `serve`, `mcp`, `device`,
66
+ `team`, `terminal`, `tail`, `health`, `recover`, `ls`, `lint`, `seed`, `hire`,
67
+ `refresh`, `clone`, `plan`, `workspace`, `diagnose`, `diagnose-prompt`,
68
+ `status`, and `db`. Run `lmctl <command> --help` for details on each, and see the
71
69
  [documentation](https://lmctl.com/lmctl) to define your first team.
72
70
 
73
- - `lmctl chat <teamfile> <alias> "message"` drives or messages a member; if a member-origin target is busy, chat queues the message for that lane.
71
+ - `lmctl chat <teamfile> <alias> "message"` drives or messages a member. If a member-origin target is busy, chat queues the message for that sender->receiver lane; the next chat to that receiver when it is free delivers the queued lane plus the new message.
74
72
 
75
73
  ## Model selection
76
74