@triedotdev/mcp 1.0.101 → 1.0.102

package/README.md

@@ -8,11 +8,11 @@
 
 Trie is an **autonomous, trainable AI agent** that maintains a decision ledger for your codebase:
 
-- **🤖 Autonomous Operation**: Run `trie watch` and the agent monitors your codebase 24/7
-- **🧠 Intelligent Extraction**: Automatically extracts decisions, facts, blockers from every change
-- **📊 Decision Ledger**: Builds institutional knowledge that travels from Cursor → CLI → CI/CD
-- **🎯 Predictive Intelligence**: `trie gotcha` queries the ledger to predict problems before they happen
-- **📈 Continuous Learning**: Feed it incidents with `trie tell`, teach it patterns with your history
+- **Autonomous Operation**: Run `trie watch` and the agent monitors your codebase 24/7
+- **Intelligent Extraction**: Automatically extracts decisions, facts, blockers from every change
+- **Ledger**: Builds institutional knowledge that travels from Cursor/Claude Code → CLI → CI/CD
+- **Predictive Intelligence**: `trie gotcha` queries the ledger to predict problems before they happen
+- **Continuous Learning**: Feed it incidents with `trie tell`, teach it patterns with your history
 
 The agent learns from every incident, decision, and fix. When you ship, Trie remembers. When something breaks, Trie learns. Over time, your agent gets better at predicting what will go wrong before it does.
 
@@ -52,46 +52,17 @@ cd your-project
 trie init
 ```
 
-### 2. Start the Agent
+### 2. Start Teaching Trie
 
-The agent runs autonomously, watching your codebase and building the decision ledger:
+When bugs happen, tell Trie about them:
 
 ```bash
-# Start the autonomous agent
-trie watch
-
-# The agent now:
-# - Watches file changes in real-time
-# - Extracts decisions, facts, blockers from every change
-# - Builds decision ledger automatically
-# - Predicts problems based on historical patterns
-```
-
-### 3. Teach the Agent
-
-When bugs happen, teach the agent:
-
-```bash
-# Report a specific incident (agent extracts structured signals)
-trie tell "Users can't log in after password reset - bcrypt config was wrong"
+# Report a specific incident (extracts structured signals)
+trie tell "Users can't log in after password reset"
 
-# Train agent from your git history (reverts/bugfixes)
+# Train Trie from your history (reverts/bugfixes)
 trie learn
 
-# Query what the agent knows
-trie gotcha  # Predicts problems in your current changes
-```
-
-### 4. Let the Agent Work
-
-The agent learns continuously:
-- Every commit → Extracts decisions
-- Every incident → Learns patterns  
-- Every fix → Updates predictions
-- Every change → Queries ledger for "gotchas"
-
-**Set `ANTHROPIC_API_KEY` for full signal extraction** (Claude Haiku for fast, cheap extraction)
-
 # Give feedback on predictions
 trie ok    # Prediction was helpful
 trie bad   # Prediction was wrong
@@ -131,7 +102,7 @@ Trie remembers your decisions across tools, tracks the tradeoffs you've made, an
 
 ### Developer Experience
 
-- Plain English warnings - "This auth change broke twice before" instead of cryptic codes.
+- Plain English warnings - "This payment flow broke twice before" instead of cryptic codes.
 - Multiple interfaces - CLI, MCP tools for Claude/Cursor, visual dashboards.
 - Flexible workflow - Works with any editor, any git workflow, any deployment setup.
 
@@ -187,22 +158,13 @@ When you switch from Cursor to Claude Code to terminal, Trie remembers. Your thi
 
 **Trie's Solution**: Extract signal, not noise.
 
-#### Three-Tier Architecture
+#### Three-Tier Storage
 
-```
-HOT (In-Memory)
-└─ Current session data
-   └─ Active decisions being worked on
-   
-WARM (Queryable DB)
-└─ Recent decisions, facts, blockers
-   └─ Agents query what they need: "decisions related to auth in last 30 days"
-   └─ Fast retrieval, targeted results
-   
-COLD (Archived)
-└─ Full history, indexed but dormant
-   └─ Moves here after 90 days of low access
-```
+| Tier | What's Stored | Purpose |
+|------|---------------|---------|
+| **HOT** (In-Memory) | Current session data, active decisions | Instant access during work |
+| **WARM** (SQLite DB) | Recent decisions, facts, blockers | Query what you need: *"payment decisions in last 30 days"* |
+| **COLD** (Archived) | Full history, indexed but dormant | Auto-archives after 90 days of low access |
 
 #### How Extraction Works
 
@@ -224,7 +186,7 @@ Agents don't get dumps—they **query** for what they need:
 ```typescript
 // Agent queries decision ledger
 trie_get_decisions({
-  relatedTo: "auth/validator.ts",
+  relatedTo: "checkout/validator.ts",
   since: "30d",
   limit: 5
 })
@@ -245,7 +207,7 @@ trie_get_decisions({
 ```bash
 # Before starting work on a feature, check what broke before
 trie gotcha                    # Predict risks for current changes
-trie memory search "auth"      # See past incidents in this area
+trie memory search "payments"      # See past incidents in this area
 trie status                   # Check overall project health
 
 # Review past decisions and tradeoffs
@@ -316,7 +278,7 @@ Set improvement goals and test theories:
 
 ```bash
 # Set a goal
-trie goal add "Reduce authentication bugs by 50%"
+trie goal add "Reduce checkout bugs by 50%"
 
 # Add a hypothesis
 trie hypothesis add "Code reviews reduce bug rate"
@@ -497,7 +459,7 @@ trie gotcha        # Predict problems with current changes
 ### Memory Management
 
 ```bash
-trie memory search "auth"     # Search incident history
+trie memory search "database"     # Search incident history
 trie memory stats             # View memory statistics
 trie memory purge smart       # Clean up old/resolved issues
 trie learn                    # Extract patterns from reverts/fixes

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@triedotdev/mcp",
-  "version": "1.0.101",
+  "version": "1.0.102",
   "description": "Trainable AI Agent for Maintaining AI-Generated Codebases",
   "main": "dist/index.js",
   "type": "module",