memorix 0.2.2 → 0.3.0

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 CHANGED
@@ -44,8 +44,26 @@ Memorix stores and indexes project knowledge (architecture decisions, bug fixes,
44
44
  - **Rules Parser**: 4 format adapters (Cursor `.mdc`, Claude Code `CLAUDE.md`, Codex `SKILL.md`, Windsurf `.windsurfrules`)
45
45
  - **Rules Syncer**: Scan → Deduplicate → Conflict detection → Cross-format generation
46
46
  - **Workspace Sync**: MCP config migration + workflow sync across agents
47
+ - **Skills Sync**: Scan `.codex/skills/`, `.cursor/skills/`, `.windsurf/skills/`, `.claude/skills/` → copy entire skill folders across agents (no format conversion needed — SKILL.md is a universal standard)
47
48
  - **Apply with Safety**: Backup → Atomic write → Auto-rollback on failure
48
49
 
50
+ ### P3 — Auto-Memory Hooks
51
+
52
+ - **Hook Events**: `user_prompt`, `post_response`, `post_edit`, `post_command`, `post_tool`, `session_end`
53
+ - **Agent Normalizer**: Maps Windsurf/Cursor/Claude/Codex native events to unified hook events
54
+ - **Pattern Detection**: Auto-detects decisions, errors, gotchas, configurations, learnings, implementations
55
+ - **Cooldown Filtering**: Prevents duplicate storage within configurable time windows
56
+ - **Noise Filtering**: Skips trivial commands (`ls`, `cat`, `pwd`, etc.)
57
+ - **Agent Rules**: Auto-installs `.windsurf/rules/memorix.md` (or equivalent) to guide agents in proactive memory management
58
+ - **One-Command Install**: `memorix hooks install` sets up hooks + rules for your agent
59
+
60
+ ### Context Continuity
61
+
62
+ - **Session Start**: Agent rules instruct AI to search memories before responding
63
+ - **During Session**: Auto-capture decisions, bugs, gotchas via hooks + agent-driven `memorix_store`
64
+ - **Session End**: Agent stores a "handoff note" summarizing progress and next steps
65
+ - **Result**: Start a new session and your AI already knows everything — no re-explaining needed
66
+
49
67
  ### P5 — Intelligence (Competitor-Inspired)
50
68
 
51
69
  - **Access Tracking**: `accessCount` + `lastAccessedAt` on every search hit (from mcp-memory-service)
@@ -115,7 +133,7 @@ npm install memorix
115
133
  | `memorix_detail` | L3 | Full observation details | ~500-1000/result |
116
134
  | `memorix_retention` | Analytics | Memory decay & retention status | — |
117
135
  | `memorix_rules_sync` | Rules | Scan, dedup, convert rules across agents | — |
118
- | `memorix_workspace_sync` | Workspace | Scan/migrate MCP configs across agents | — |
136
+ | `memorix_workspace_sync` | Workspace | Scan/migrate MCP configs, workflows, and skills across agents | — |
119
137
 
120
138
  #### MCP Official Compatible
121
139
 
@@ -158,9 +176,16 @@ npm install memorix
158
176
  │ └─────────────────────────────────────┘ │
159
177
  │ │
160
178
  │ ┌────────────────────────────────────┐ │
161
- │ │ Rules Syncer │ │
179
+ │ │ Rules & Skills Syncer │ │
162
180
  │ │ Cursor│Claude│Codex│Windsurf │ │
163
- │ │ scan dedup conflict gen │ │
181
+ │ │ rules: scan→dedup→conflict→gen │ │
182
+ │ │ skills: scan→copy (no convert) │ │
183
+ │ └────────────────────────────────────┘ │
184
+ │ │
185
+ │ ┌────────────────────────────────────┐ │
186
+ │ │ Auto-Memory Hooks │ │
187
+ │ │ normalize→detect→filter→store │ │
188
+ │ │ + agent rules (context cont.) │ │
164
189
  │ └────────────────────────────────────┘ │
165
190
  └──────────────────────────────────────────────┘
166
191
  ```
@@ -179,7 +204,7 @@ npm install memorix
179
204
  | Entity extraction | Regex patterns | MemCP |
180
205
  | Rule parsing | `gray-matter` | — |
181
206
  | Build | `tsup` | — |
182
- | Test | `vitest` | 195 tests |
207
+ | Test | `vitest` | 219 tests |
183
208
 
184
209
  ## Optional: Enable Vector Search
185
210
 
@@ -200,7 +225,7 @@ npm install
200
225
  # Build
201
226
  npm run build
202
227
 
203
- # Run tests (195 tests)
228
+ # Run tests (219 tests)
204
229
  npm test
205
230
 
206
231
  # Type check