memorable-cli 0.3.4 → 0.4.0
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 +17 -5
- package/dist/cli.js +505 -134
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -6,17 +6,29 @@ Procedural memory for coding agents, stored on your own machine.
|
|
|
6
6
|
|
|
7
7
|
When an agent finishes a task, `memorable` extracts what actually happened — files changed, commands that verified the work, real outcomes — into a stored procedure. When a similar task comes back, `memorable recall` surfaces it, so the agent skips the diagnosis it has already done. Extraction is deterministic (no LLM anywhere in the pipeline) and nothing is stored in Memorable's cloud.
|
|
8
8
|
|
|
9
|
-
##
|
|
9
|
+
## Start here — nothing installed yet
|
|
10
|
+
|
|
11
|
+
```
|
|
12
|
+
npx memorable-cli login # opens a browser, links this machine to your workspace
|
|
13
|
+
memorable install-hooks # Claude Code: recall runs on every new prompt
|
|
14
|
+
memorable enable # explicit consent — until you run this, nothing is stored
|
|
15
|
+
# AND nothing is sent for extraction
|
|
16
|
+
```
|
|
17
|
+
|
|
18
|
+
`npx` fetches the package on first use, so there is nothing to install before that first line. To get the short `memorable` name on PATH afterwards:
|
|
10
19
|
|
|
11
20
|
```
|
|
12
21
|
npm install -g memorable-cli
|
|
13
22
|
```
|
|
14
23
|
|
|
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
|
+
|
|
15
26
|
## Quickstart
|
|
16
27
|
|
|
17
28
|
```
|
|
18
|
-
memorable
|
|
19
|
-
memorable enable # explicit
|
|
29
|
+
memorable login # once per machine — a key that belongs to your workspace
|
|
30
|
+
memorable enable # explicit consent — until you run this, nothing is stored
|
|
31
|
+
# AND nothing is sent for extraction
|
|
20
32
|
|
|
21
33
|
# store a procedure from any agent's trace:
|
|
22
34
|
memorable ingest trace.json
|
|
@@ -44,7 +56,7 @@ memorable doctor # every integration point, asserted — including wheth
|
|
|
44
56
|
# whether the API returned 200
|
|
45
57
|
memorable install-hooks # add the Claude Code prompt hook so recall injects
|
|
46
58
|
# automatically at the start of a session
|
|
47
|
-
memorable setup #
|
|
59
|
+
memorable setup # enable + AGENTS.md in one shot (after `login`)
|
|
48
60
|
```
|
|
49
61
|
|
|
50
62
|
## Revisions
|
|
@@ -106,7 +118,7 @@ still works on exact and lexical matches — but the CLI says so on every write
|
|
|
106
118
|
rather than degrading quietly, and `memorable doctor` reports the semantic
|
|
107
119
|
tier as unavailable.
|
|
108
120
|
|
|
109
|
-
Switch anytime by re-running `memorable init` / `memorable init gbrain
|
|
121
|
+
Switch anytime by re-running `memorable init` / `memorable init gbrain` — the sign-in from `login` carries over.
|
|
110
122
|
|
|
111
123
|
## Chaining: when one procedure is not the answer
|
|
112
124
|
|