@cachly-dev/mcp-server 0.5.26 → 0.5.28

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
@@ -122,19 +122,35 @@ The interactive wizard:
122
122
 
123
123
  ---
124
124
 
125
- ## 38 MCP Tools
125
+ ## 51 MCP Tools
126
126
 
127
127
  ### 🧠 Session & Memory (most used)
128
128
 
129
129
  | Tool | What it does |
130
130
  |------|-------------|
131
131
  | **`session_start`** | Full briefing: last session summary, open failures, recent lessons, brain health |
132
- | **`session_end`** | Save what you built, auto-extract lessons from summary |
132
+ | **`session_end`** | Save what you built, auto-extract lessons from summary + ambient git log |
133
+ | **`session_handoff`** | Hand off remaining tasks to next window, with context |
134
+ | **`auto_learn_session`** | Batch-learn from a list of observations |
135
+ | **`sync_file_changes`** | Sync changed files into brain index |
133
136
  | **`learn_from_attempts`** | Store structured lessons after any fix, deploy, or discovery |
134
137
  | **`recall_best_solution`** | Best known solution for a topic — with success/failure history |
138
+ | **`recall_at`** | Recall a lesson at a specific point in time |
135
139
  | **`remember_context`** | Cache architecture findings, decisions, file summaries |
140
+ | **`recall_context`** | Get exact context by key (supports glob) |
141
+ | **`list_remembered`** | See all cached context entries |
142
+ | **`forget_context`** | Remove stale context |
136
143
  | **`smart_recall`** | BM25+ full-text search across all brain data |
137
- | **`session_handoff`** | Hand off remaining tasks to next window, with context |
144
+ | **`setup_ai_memory`** | Interactive wizard to configure AI memory |
145
+
146
+ ### 💡 Legendary Brain Features
147
+
148
+ | Feature | How it works |
149
+ |---------|-------------|
150
+ | **Team Telepathy** | Multi-dev Brain: the `author` param on `learn_from_attempts` shares fixes across the whole team. Every `session_start` shows colleagues' lessons. |
151
+ | **Ambient Git Learning** | Pass `workspace_path` to `session_end` — it auto-reads `git log`, stores recent commits as Brain lessons. Zero extra calls. |
152
+ | **Memory Crystals** | `memory_crystalize` distills all lessons into a compact Crystal injected at every `session_start`. AI arrives pre-loaded with team knowledge. |
153
+ | **IQ Boost** | `brain_doctor` reports `iq_boost_pct` — how much smarter your AI gets vs. baseline from cached lessons. |
138
154
 
139
155
  ### ⚙️ Instance Management
140
156
 
@@ -168,9 +184,14 @@ The interactive wizard:
168
184
  | Tool | What it does |
169
185
  |------|-------------|
170
186
  | `team_learn` / `team_recall` | Share lessons across the team |
187
+ | `team_synthesize` | Consolidate multiple lessons into one authoritative version |
188
+ | `memory_crystalize` | Distill all lessons into a Crystal snapshot for instant team context |
189
+ | `brain_doctor` | Health check: lesson count, IQ boost %, open failures, quality score |
171
190
  | `global_learn` / `global_recall` | Cross-project universal lessons |
191
+ | `publish_lesson` / `import_public_brain` | Share/import community knowledge |
192
+ | `trace_dependency` | Causal chain — find lessons affected by a dependency change |
172
193
  | `list_orgs` / `create_org` | Manage team organizations |
173
- | `invite_member` | Invite a developer to your org by email |
194
+ | `invite_member` / `get_org_plan` | Invite a developer to your org by email |
174
195
 
175
196
  ---
176
197
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@cachly-dev/mcp-server",
3
- "version": "0.5.26",
3
+ "version": "0.5.28",
4
4
  "mcpName": "io.github.cachly-dev/mcp-server",
5
5
  "description": "AI memory brain for Claude Code, Cursor, Copilot & Windsurf — persistent sessions, lessons learned, semantic search, team brain. 38 MCP tools.",
6
6
  "type": "module",
@@ -0,0 +1,23 @@
1
+ const fs = require('fs');
2
+
3
+ const src = fs.readFileSync('src/index.ts', 'utf8');
4
+ const initSrc = fs.readFileSync('../init/index.js', 'utf8');
5
+ const pkg = JSON.parse(fs.readFileSync('package.json', 'utf8'));
6
+
7
+ let pass = 0, fail = 0;
8
+ function check(name, cond) {
9
+ if (cond) { console.log('PASS:', name); pass++; }
10
+ else { console.log('FAIL:', name); fail++; }
11
+ }
12
+
13
+ check('Test 1 - Ambient git learning in session_end', src.includes('git log --since') || src.includes('Ambient git'));
14
+ check('Test 2a - author param in learn_from_attempts schema', src.includes('"author"') && src.includes('learn_from_attempts'));
15
+ check('Test 2b - Team Telepathy in session_start', src.includes('Team Telepathy') || src.includes('team telepathy'));
16
+ check('Test 3 - memory_crystalize tool', src.includes('memory_crystalize'));
17
+ check('Test 4 - init team detection (~/.cachly-teams.json)', initSrc.includes('cachly-teams.json'));
18
+ check('Test 5 - brain_doctor workspace_path param', src.includes('workspace_path') && src.includes('brain_doctor'));
19
+ check('Bugfix - Pre-Warning uses splice(2,0)', src.includes('splice(2, 0'));
20
+ check('Bugfix - No broken unshift in pre-warning', !src.includes('lines.unshift('));
21
+ check('MCP version is 0.5.26', pkg.version === '0.5.26');
22
+
23
+ console.log(`\n${pass}/${pass+fail} tests passed`);