brain-memory 0.5.1 → 0.5.2
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 +12 -0
- package/package.json +1 -1
- package/prompts/openai.md +15 -15
package/CHANGELOG.md
CHANGED
|
@@ -6,6 +6,18 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/), and this
|
|
|
6
6
|
|
|
7
7
|
## [Unreleased]
|
|
8
8
|
|
|
9
|
+
## [0.5.2] - 2026-11-08
|
|
10
|
+
|
|
11
|
+
Codex now suggests brain commands it can actually run.
|
|
12
|
+
|
|
13
|
+
### Fixed
|
|
14
|
+
- **Codex: `$brain-memorize`, not `/brain-memorize`.** The Codex prompt
|
|
15
|
+
(`AGENTS.md`) listed the brain skills as `/brain-…` slash commands, so Codex
|
|
16
|
+
told users to type `/brain-memorize` and then rejected it as an unrecognized
|
|
17
|
+
command. Codex runs skills with `$` (or from `/skills`); every command in the
|
|
18
|
+
Codex prompt now uses the `$brain-` form. Re-run `brain --codex --global`
|
|
19
|
+
to refresh `~/.codex/AGENTS.md`.
|
|
20
|
+
|
|
9
21
|
## [0.5.1] - 2026-10-18
|
|
10
22
|
|
|
11
23
|
An account with several brains can now choose which one each device, and the
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "brain-memory",
|
|
3
|
-
"version": "0.5.
|
|
3
|
+
"version": "0.5.2",
|
|
4
4
|
"description": "A brain-inspired hierarchical memory system for AI coding agents. Deep nested file structure that mimics human memory with time-decay and strength-based recall.",
|
|
5
5
|
"keywords": [
|
|
6
6
|
"claude-code",
|
package/prompts/openai.md
CHANGED
|
@@ -51,25 +51,25 @@ Every memory carries a consent tier: `standard` (default), `sensitive` (health,
|
|
|
51
51
|
|
|
52
52
|
## Available Commands
|
|
53
53
|
|
|
54
|
-
Brain skills are
|
|
54
|
+
Brain skills are invoked with the `$brain-` prefix (type `$brain-memorize`, or pick one from `/skills`). Codex runs skills with `$`, not as slash commands — always suggest the `$` form:
|
|
55
55
|
The everyday loop is **ambient** — `remember` and `memorize` run automatically at session start/end; you rarely type them.
|
|
56
56
|
|
|
57
57
|
Core:
|
|
58
|
-
-
|
|
59
|
-
-
|
|
60
|
-
-
|
|
61
|
-
-
|
|
62
|
-
-
|
|
58
|
+
- `$brain-remember [query]` — Recall relevant memories with spreading activation and context matching
|
|
59
|
+
- `$brain-memorize [topic]` — Store memories from the current context
|
|
60
|
+
- `$brain-status` — Dashboard with brain health overview
|
|
61
|
+
- `$brain-pin [id|query]` — Pin a memory to the always-present tier (toggle — also unpins, e.g. `--off`)
|
|
62
|
+
- `$brain-forget [target]` — Decay or archive memories (`--deep` = forensic erasure of every reference)
|
|
63
63
|
|
|
64
64
|
Cold start:
|
|
65
|
-
-
|
|
65
|
+
- `$brain-import [--project P] [--since 30d]` — Seed a new brain from transcripts your agents already wrote
|
|
66
66
|
|
|
67
67
|
Sync & skills:
|
|
68
|
-
-
|
|
69
|
-
-
|
|
68
|
+
- `$brain-sync [subcommand]` — Sync via Brain Cloud, Git remote, or export/import (auto-initializes on first run)
|
|
69
|
+
- `$brain-skills [list|show|add|use|remove|export]` — Manage procedural skills
|
|
70
70
|
|
|
71
71
|
Maintenance (usually automatic — runs in the background):
|
|
72
|
-
-
|
|
72
|
+
- `$brain-sleep [scope]` — Full maintenance cycle: replay, homeostasis, propagation, crystallization, reorganize, consolidate, prune, review reinforcement, REM dreaming, expertise detection
|
|
73
73
|
|
|
74
74
|
## Session Start Behavior
|
|
75
75
|
|
|
@@ -117,13 +117,13 @@ Track these categories as they happen:
|
|
|
117
117
|
If notable items have accumulated, append a **brief one-liner** at the end of your next natural response:
|
|
118
118
|
|
|
119
119
|
```
|
|
120
|
-
◉ Notable <type(s)> this session —
|
|
120
|
+
◉ Notable <type(s)> this session — $brain-memorize when ready
|
|
121
121
|
```
|
|
122
122
|
|
|
123
123
|
**Rules:**
|
|
124
124
|
- **Never interrupt flow** — only append to the end of a response the user is already receiving, never send as a standalone message
|
|
125
125
|
- **At most once per ~10 substantive interactions** — no spamming
|
|
126
|
-
- **Reset the counter** after the user runs
|
|
126
|
+
- **Reset the counter** after the user runs `$brain-memorize`
|
|
127
127
|
- **Don't mention if nothing notable** has accumulated
|
|
128
128
|
- **Be specific about types** — say "decisions and learnings" not just "notable content"
|
|
129
129
|
|
|
@@ -157,7 +157,7 @@ If the session contained meaningful content based on your ambient tracking:
|
|
|
157
157
|
|
|
158
158
|
```
|
|
159
159
|
💡 This session contained notable <type(s)>. Would you like to store them as brain memories?
|
|
160
|
-
Run
|
|
160
|
+
Run $brain-memorize to capture them before this context is lost.
|
|
161
161
|
```
|
|
162
162
|
|
|
163
163
|
**Rules:**
|
|
@@ -221,7 +221,7 @@ Writes whose content came from outside the user/agent dialogue (origin `tool-out
|
|
|
221
221
|
|
|
222
222
|
Brain memories can be synced across devices in two ways:
|
|
223
223
|
|
|
224
|
-
1. **Git remote** — Push/pull `~/.brain/` to any private Git repository (GitHub, GitLab, Codeberg, self-hosted). Run
|
|
225
|
-
2. **Export/Import** — Pack the entire `~/.brain/` into a single portable file for manual transfer. Run
|
|
224
|
+
1. **Git remote** — Push/pull `~/.brain/` to any private Git repository (GitHub, GitLab, Codeberg, self-hosted). Run `$brain-sync setup <url>` to configure, then use `$brain-sync push` and `$brain-sync pull`.
|
|
225
|
+
2. **Export/Import** — Pack the entire `~/.brain/` into a single portable file for manual transfer. Run `$brain-sync export` and `$brain-sync import <path>`.
|
|
226
226
|
|
|
227
227
|
Both methods support optional AES-256-GCM encryption. Sync is always manual — never automatic.
|