memorable-cli 0.3.6 → 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.
Files changed (3) hide show
  1. package/README.md +15 -4
  2. package/dist/cli.js +505 -134
  3. package/package.json +3 -3
package/README.md CHANGED
@@ -6,16 +6,27 @@ 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
- ## Install
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 init # picks the standalone local store + issues an API key (no sign-up)
29
+ memorable login # once per machine a key that belongs to your workspace
19
30
  memorable enable # explicit consent — until you run this, nothing is stored
20
31
  # AND nothing is sent for extraction
21
32
 
@@ -45,7 +56,7 @@ memorable doctor # every integration point, asserted — including wheth
45
56
  # whether the API returned 200
46
57
  memorable install-hooks # add the Claude Code prompt hook so recall injects
47
58
  # automatically at the start of a session
48
- memorable setup # init + enable + AGENTS.md in one shot
59
+ memorable setup # enable + AGENTS.md in one shot (after `login`)
49
60
  ```
50
61
 
51
62
  ## Revisions
@@ -107,7 +118,7 @@ still works on exact and lexical matches — but the CLI says so on every write
107
118
  rather than degrading quietly, and `memorable doctor` reports the semantic
108
119
  tier as unavailable.
109
120
 
110
- 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.
111
122
 
112
123
  ## Chaining: when one procedure is not the answer
113
124