open-mem 0.12.0 → 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/CHANGELOG.md +21 -0
- package/README.md +9 -3
- package/bin/cli.mjs +873 -0
- package/dist/ai/opencode-bridge.d.ts +27 -0
- package/dist/ai/opencode-bridge.d.ts.map +1 -0
- package/dist/hooks/chat-capture.d.ts +5 -1
- package/dist/hooks/chat-capture.d.ts.map +1 -1
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +49 -49
- package/dist/types.d.ts +5 -1
- package/dist/types.d.ts.map +1 -1
- package/package.json +4 -1
package/CHANGELOG.md
CHANGED
|
@@ -5,6 +5,27 @@ All notable changes to this project will be documented in this file.
|
|
|
5
5
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
|
|
6
6
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
7
7
|
|
|
8
|
+
## [0.14.0] - 2026-02-23
|
|
9
|
+
|
|
10
|
+
### Added
|
|
11
|
+
- **Interactive setup wizard** — `npx open-mem` now launches a beautiful interactive onboarding wizard (powered by `@clack/prompts`) that guides users through provider selection, dashboard, workflow mode, and context file configuration. Use `--quick` to skip the wizard.
|
|
12
|
+
- **OpenCode session bridge** — when no API key is configured, open-mem automatically routes AI compression through OpenCode's own session model. Zero-config AI compression for all users, regardless of auth method (env vars, OAuth, Copilot, etc.).
|
|
13
|
+
- **Smart provider detection** — at plugin init, queries OpenCode's configured providers via the SDK client and gives actionable guidance instead of generic warnings.
|
|
14
|
+
|
|
15
|
+
### Changed
|
|
16
|
+
- `chat.message` hook now accepts the new OpenCode model format (`{ providerID, modelID }` object alongside legacy string).
|
|
17
|
+
- Auto-detect provider option updated to reflect automatic OpenCode fallback — no separate API key warning removed.
|
|
18
|
+
- Wizard messaging reflects that AI compression works out-of-the-box without extra configuration.
|
|
19
|
+
|
|
20
|
+
## [0.13.0] - 2026-02-23
|
|
21
|
+
|
|
22
|
+
### Added
|
|
23
|
+
- **`npx open-mem` CLI installer** — one-command plugin setup for OpenCode. Automatically finds or creates the config file and adds `open-mem` to the plugin array. Supports `--global`, `--uninstall`, `--dry-run`, `--force`, and `--version` flags. JSONC-aware (preserves comments in existing config files). Cleans OpenCode plugin cache on uninstall.
|
|
24
|
+
- AI provider detection in installer — shows which providers are configured after install.
|
|
25
|
+
|
|
26
|
+
### Changed
|
|
27
|
+
- Documentation updated — README Quick Start and Getting Started guide now recommend `npx open-mem` as the primary installation method, with manual `bun add` as alternative.
|
|
28
|
+
|
|
8
29
|
## [0.12.0] - 2026-02-16
|
|
9
30
|
|
|
10
31
|
### Changed
|
package/README.md
CHANGED
|
@@ -31,11 +31,19 @@ You use tools, open-mem captures the outputs, AI compresses them into structured
|
|
|
31
31
|
|
|
32
32
|
## Quick start
|
|
33
33
|
|
|
34
|
+
```bash
|
|
35
|
+
npx open-mem
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
That's it. This adds `open-mem` to your OpenCode plugin config automatically. It starts capturing from your next session.
|
|
39
|
+
|
|
40
|
+
Or install manually:
|
|
41
|
+
|
|
34
42
|
```bash
|
|
35
43
|
bun add open-mem
|
|
36
44
|
```
|
|
37
45
|
|
|
38
|
-
|
|
46
|
+
Then add to your OpenCode config (`~/.config/opencode/opencode.json` or `.opencode/opencode.json`):
|
|
39
47
|
|
|
40
48
|
```json
|
|
41
49
|
{
|
|
@@ -43,8 +51,6 @@ Add it to your OpenCode config (`~/.config/opencode/opencode.json`):
|
|
|
43
51
|
}
|
|
44
52
|
```
|
|
45
53
|
|
|
46
|
-
That's it. open-mem starts capturing from your next session.
|
|
47
|
-
|
|
48
54
|
### AI compression (optional)
|
|
49
55
|
|
|
50
56
|
By default, open-mem uses a basic metadata extractor. For semantic compression, add an AI provider:
|