@ai-devkit/agent-manager 0.13.0 → 0.14.0
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 +32 -0
- package/package.json +1 -1
package/README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# @ai-devkit/agent-manager
|
|
2
|
+
|
|
3
|
+
Detect, inspect, and send prompts to running AI coding agent sessions.
|
|
4
|
+
|
|
5
|
+
This package powers the `ai-devkit agent` commands. Use it when you need the lower-level agent session management utilities that AI DevKit uses to find active Claude Code, Codex, Gemini CLI, and other supported coding-agent sessions.
|
|
6
|
+
|
|
7
|
+
## What It Provides
|
|
8
|
+
|
|
9
|
+
- **Session detection** — Find running agent sessions across supported providers
|
|
10
|
+
- **Session details** — Inspect agent metadata, working directory, and status
|
|
11
|
+
- **Prompt sending** — Send follow-up instructions to an existing session
|
|
12
|
+
- **Provider adapters** — Shared adapter layer for agent-specific behavior
|
|
13
|
+
|
|
14
|
+
## Typical Use
|
|
15
|
+
|
|
16
|
+
Most users should use the CLI:
|
|
17
|
+
|
|
18
|
+
```bash
|
|
19
|
+
ai-devkit agent list
|
|
20
|
+
ai-devkit agent send "run the tests and report back" --id <agent-name> --wait
|
|
21
|
+
npm test 2>&1 | ai-devkit agent send --id <agent-name> --stdin
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
Use this package directly only when building custom tooling around AI DevKit's agent detection and control surface.
|
|
25
|
+
|
|
26
|
+
## Documentation
|
|
27
|
+
|
|
28
|
+
Full guides and workflow examples: **[ai-devkit.com/docs](https://ai-devkit.com/docs/)**
|
|
29
|
+
|
|
30
|
+
## License
|
|
31
|
+
|
|
32
|
+
MIT
|