@neuvybe/jarvis 0.49.4 → 0.50.0
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 +14 -4
- package/dist/index.js +216 -208
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -4,16 +4,18 @@ Jarvis is a voice-first personal agent for developers: one continuous, trusted
|
|
|
4
4
|
collaborator that lives in your terminal, rather than a wall of disposable chat
|
|
5
5
|
threads. You talk, it listens, thinks, acts, and talks back. Text works too.
|
|
6
6
|
|
|
7
|
-
Jarvis runs locally, calling the model and speech providers you configure
|
|
8
|
-
your own keys
|
|
7
|
+
Jarvis runs locally, calling the model and speech providers you configure.
|
|
8
|
+
Hosted providers use your own keys; a local Ollama Brain needs no key.
|
|
9
|
+
It does not keep recordings, and conversation context lasts for
|
|
9
10
|
the session.
|
|
10
11
|
|
|
11
12
|
## Requirements
|
|
12
13
|
|
|
13
14
|
- Node.js 24 or newer.
|
|
14
15
|
- A microphone and speakers (or a headset) for voice. Text-only sessions need neither.
|
|
15
|
-
-
|
|
16
|
-
|
|
16
|
+
- A Brain: Anthropic, OpenAI, Ollama Cloud, or a running Ollama server with a
|
|
17
|
+
tool-capable model. Hosted Brain and Voice providers require your own keys;
|
|
18
|
+
`jarvis init` collects them and checks them where supported.
|
|
17
19
|
- Supported platforms: macOS on Apple silicon, Windows x64, Linux x64 and arm64 (glibc).
|
|
18
20
|
Intel Macs, Windows on ARM, and Alpine/musl are not supported yet.
|
|
19
21
|
|
|
@@ -33,6 +35,14 @@ jarvis # open the session for the current directory
|
|
|
33
35
|
`jarvis` is an interactive doorway, not a prompt runner: it takes no prompt
|
|
34
36
|
argument and does not read piped input.
|
|
35
37
|
|
|
38
|
+
For Ollama, choose the Cloud or local-server Brain in `jarvis init`. Cloud uses
|
|
39
|
+
your Ollama account key, shared with Ollama Search. Local setup asks for a server
|
|
40
|
+
address (default `http://localhost:11434`) and lists installed models with tool
|
|
41
|
+
support; Jarvis does not download models or start the server. Some server models
|
|
42
|
+
run through Ollama Cloud, as indicated in the picker. Model behavior and speed
|
|
43
|
+
vary: local `gemma4:12b` enables thinking for more reliable actions, which can
|
|
44
|
+
add a noticeable delay before speech.
|
|
45
|
+
|
|
36
46
|
## Everyday commands
|
|
37
47
|
|
|
38
48
|
| Command | What it does |
|