@triedotdev/mcp 1.0.86 → 1.0.87
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 +29 -26
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -2,15 +2,18 @@
|
|
|
2
2
|
|
|
3
3
|
A trainable AI agent that watches all of your codebases, learns from your incidents, and prevents repeat bugs before they ship.
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
<p align="left">
|
|
6
|
+
<a href="https://www.trie.dev"><img alt="Download Workspace" src="https://img.shields.io/badge/Download_Workspace-0b0f14?style=for-the-badge&logo=vercel&logoColor=white"></a>
|
|
7
|
+
<a href="https://x.com/louiskishfy"><img alt="Follow on X" src="https://img.shields.io/badge/Follow_on_X-000000?style=for-the-badge&logo=x&logoColor=white"></a>
|
|
8
|
+
</p>
|
|
6
9
|
|
|
7
10
|
## What Trie Does
|
|
8
11
|
|
|
9
|
-
Central skill repository: One place for all your skills — carry context and rules across Cursor, Claude, VS Code, CLI, and CI/CD. Unlike running skills with Claude Code, Trie will check for anything malicious before you run them.
|
|
10
|
-
Sets and tracks goals: "Reduce login bugs by 50%" then actually measures progress and celebrates wins
|
|
11
|
-
Tests your theories: "Mondays have more bugs" — Trie validates with real data and builds confidence over time
|
|
12
|
-
Learns from your incidents: Train it on your specific patterns, not generic rules that don't fit your prompting
|
|
13
|
-
Predicts "Gotchas" proactively: Ingests Linear tickets and correlates them with past failures to warn you before you even push code
|
|
12
|
+
- Central skill repository: One place for all your skills — carry context and rules across Cursor, Claude, VS Code, CLI, and CI/CD. Unlike running skills with Claude Code, Trie will check for anything malicious before you run them.
|
|
13
|
+
- Sets and tracks goals: "Reduce login bugs by 50%" then actually measures progress and celebrates wins.
|
|
14
|
+
- Tests your theories: "Mondays have more bugs" — Trie validates with real data and builds confidence over time.
|
|
15
|
+
- Learns from your incidents: Train it on your specific patterns, not generic rules that don't fit your prompting.
|
|
16
|
+
- Predicts "Gotchas" proactively: Ingests Linear tickets and correlates them with past failures to warn you before you even push code.
|
|
14
17
|
|
|
15
18
|
## Goal
|
|
16
19
|
|
|
@@ -77,31 +80,31 @@ Trie remembers your decisions across tools, tracks the tradeoffs you've made, an
|
|
|
77
80
|
|
|
78
81
|
### Smart Memory
|
|
79
82
|
|
|
80
|
-
Git-based storage - Your project's memory travels with your code in
|
|
81
|
-
Cross-project learning - Patterns discovered in one project help prevent bugs in others
|
|
82
|
-
Incident tracking - Build a searchable history of what went wrong and why
|
|
83
|
-
Decision memory - Remembers architectural choices and tradeoffs across Cursor, Claude, VS Code, CLI, and CI/CD
|
|
84
|
-
Context that travels - Your thinking and planning keep up with code generation across all your tools
|
|
83
|
+
- Git-based storage - Your project's memory travels with your code in `.trie/` folder.
|
|
84
|
+
- Cross-project learning - Patterns discovered in one project help prevent bugs in others.
|
|
85
|
+
- Incident tracking - Build a searchable history of what went wrong and why.
|
|
86
|
+
- Decision memory - Remembers architectural choices and tradeoffs across Cursor, Claude, VS Code, CLI, and CI/CD.
|
|
87
|
+
- Context that travels - Your thinking and planning keep up with code generation across all your tools.
|
|
85
88
|
|
|
86
89
|
### Intelligent Analysis
|
|
87
90
|
|
|
88
|
-
26 built-in scouts - Automated analyzers for security, performance, accessibility, and more
|
|
89
|
-
Custom skills - Add external analyzers from the community
|
|
90
|
-
Risk scoring - Intelligent priority ranking based on your actual incident history
|
|
91
|
-
Edge case detection - Identifies recurring issues and patterns you've hit before
|
|
92
|
-
System coherence - Tracks relationships between files, changes, incidents, fixes, and decisions
|
|
91
|
+
- 26 built-in scouts - Automated analyzers for security, performance, accessibility, and more.
|
|
92
|
+
- Custom skills - Add external analyzers from the community.
|
|
93
|
+
- Risk scoring - Intelligent priority ranking based on your actual incident history.
|
|
94
|
+
- Edge case detection - Identifies recurring issues and patterns you've hit before.
|
|
95
|
+
- System coherence - Tracks relationships between files, changes, incidents, fixes, and decisions.
|
|
93
96
|
|
|
94
97
|
### Development Integration
|
|
95
98
|
|
|
96
|
-
Git hooks - Automatic checks before commits and pushes
|
|
97
|
-
Watch mode - Real-time monitoring while you code
|
|
98
|
-
Fast performance - Sub-500ms checks, won't slow down your workflow
|
|
99
|
+
- Git hooks - Automatic checks before commits and pushes.
|
|
100
|
+
- Watch mode - Real-time monitoring while you code.
|
|
101
|
+
- Fast performance - Sub-500ms checks, won't slow down your workflow.
|
|
99
102
|
|
|
100
103
|
### Developer Experience
|
|
101
104
|
|
|
102
|
-
Plain English warnings - "This auth change broke twice before" instead of cryptic codes
|
|
103
|
-
Multiple interfaces - CLI, MCP tools for Claude/Cursor, visual dashboards
|
|
104
|
-
Flexible workflow - Works with any editor, any git workflow, any deployment setup
|
|
105
|
+
- Plain English warnings - "This auth change broke twice before" instead of cryptic codes.
|
|
106
|
+
- Multiple interfaces - CLI, MCP tools for Claude/Cursor, visual dashboards.
|
|
107
|
+
- Flexible workflow - Works with any editor, any git workflow, any deployment setup.
|
|
105
108
|
|
|
106
109
|
## How It Works
|
|
107
110
|
|
|
@@ -109,10 +112,10 @@ Flexible workflow - Works with any editor, any git workflow, any deployment setu
|
|
|
109
112
|
|
|
110
113
|
Trie uses a "Guardian Agent" architecture:
|
|
111
114
|
|
|
112
|
-
Scouts continuously analyze your code for potential issues
|
|
113
|
-
Guardian receives scout reports and decides what matters based on your history
|
|
114
|
-
Memory Tree stores incident patterns using a trie data structure for fast lookups
|
|
115
|
-
Learning Loop improves predictions based on your feedback
|
|
115
|
+
- Scouts continuously analyze your code for potential issues.
|
|
116
|
+
- Guardian receives scout reports and decides what matters based on your history.
|
|
117
|
+
- Memory Tree stores incident patterns using a trie data structure for fast lookups.
|
|
118
|
+
- Learning Loop improves predictions based on your feedback.
|
|
116
119
|
|
|
117
120
|
### Memory That Travels
|
|
118
121
|
|