memorable-cli 0.4.1 → 0.4.3
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 +17 -0
- package/dist/cli.js +123 -1508
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -23,6 +23,23 @@ npm install -g memorable-cli
|
|
|
23
23
|
|
|
24
24
|
Running Codex, Cursor or a custom harness instead of Claude Code? `memorable setup` writes the instructions into `AGENTS.md` instead of installing a hook. Storing in your own gbrain database? `memorable init gbrain`. Both need `login` first.
|
|
25
25
|
|
|
26
|
+
## Local Codex trace capture (no account required)
|
|
27
|
+
|
|
28
|
+
```
|
|
29
|
+
npm install -g memorable-cli
|
|
30
|
+
memorable install-hooks codex
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
Restart Codex and approve the new hooks when `/hooks` asks you to review them.
|
|
34
|
+
Each completed turn is written locally to
|
|
35
|
+
`~/.memorable/traces/<session-id>/<turn-id>.json`. The capture contains the
|
|
36
|
+
prompt, minimized tool inputs, explicit tool outcomes, and Codex's final agent
|
|
37
|
+
response in `agent_output`; command output, file contents, and patch bodies are
|
|
38
|
+
not retained. Agent output is capped at 256 KiB and marked with
|
|
39
|
+
`agent_output_truncated: true` when capped. This checkpoint only records trace
|
|
40
|
+
JSON—it does not process, upload, or store a procedure. Set
|
|
41
|
+
`MEMORABLE=0` before starting Codex to disable capture without removing hooks.
|
|
42
|
+
|
|
26
43
|
## Quickstart
|
|
27
44
|
|
|
28
45
|
```
|