traqr-memory-mcp 0.1.6 → 0.1.7
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 +17 -4
- package/package.json +6 -4
package/README.md
CHANGED
|
@@ -1,8 +1,20 @@
|
|
|
1
1
|
# traqr-memory-mcp
|
|
2
2
|
|
|
3
|
-
MCP server for persistent AI agent memory.
|
|
3
|
+
MCP server for persistent AI agent memory. 11 tools, Postgres + pgvector, multi-strategy retrieval (semantic + BM25 + RRF). Works with Claude Code, Cursor, Codex, and any MCP client.
|
|
4
4
|
|
|
5
|
-
##
|
|
5
|
+
## Fastest Setup
|
|
6
|
+
|
|
7
|
+
Just tell your AI assistant: **"Set up TraqrDB for persistent memory."** It reads this README, writes your MCP config, and handles everything. Zero terminal interaction needed.
|
|
8
|
+
|
|
9
|
+
Or run the interactive wizard:
|
|
10
|
+
|
|
11
|
+
```bash
|
|
12
|
+
npx traqr-memory-mcp --install
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
The wizard detects your MCP client, asks for your database and embedding provider, and writes the config automatically.
|
|
16
|
+
|
|
17
|
+
## Manual Setup
|
|
6
18
|
|
|
7
19
|
### 1. Set Up Your Database
|
|
8
20
|
|
|
@@ -111,7 +123,7 @@ TraqrDB Memory MCP v0.1.3 | Schema v2 | DB: Supabase | Embeddings: openai/text-e
|
|
|
111
123
|
|
|
112
124
|
---
|
|
113
125
|
|
|
114
|
-
##
|
|
126
|
+
## 11 MCP Tools
|
|
115
127
|
|
|
116
128
|
| Tool | Description |
|
|
117
129
|
|------|-------------|
|
|
@@ -122,6 +134,7 @@ TraqrDB Memory MCP v0.1.3 | Schema v2 | DB: Supabase | Embeddings: openai/text-e
|
|
|
122
134
|
| `memory_browse` | Navigate by facet. Domain > category > summaries. Zero embedding cost. |
|
|
123
135
|
| `memory_context` | Load task-relevant context — principles, preferences, gotchas. |
|
|
124
136
|
| `memory_pulse` | Batch: capture multiple learnings + search in one call. |
|
|
137
|
+
| `memory_correct` | Store a correction to an existing memory with context about what changed. |
|
|
125
138
|
| `memory_audit` | System health, stats, quality metrics. |
|
|
126
139
|
| `memory_archive` | Archive stale content that was once correct. |
|
|
127
140
|
| `memory_forget` | Forget incorrect or harmful content permanently. |
|
|
@@ -205,4 +218,4 @@ If something goes wrong, the MCP server prints structured error messages with fi
|
|
|
205
218
|
|
|
206
219
|
## License
|
|
207
220
|
|
|
208
|
-
Apache-2.0
|
|
221
|
+
[FSL-1.1-ALv2](https://fsl.software) — use freely for any purpose except offering a competing commercial memory service. Converts to Apache-2.0 after 2 years.
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "traqr-memory-mcp",
|
|
3
|
-
"version": "0.1.
|
|
4
|
-
"description": "Memory-as-a-service MCP server for AI agents.
|
|
3
|
+
"version": "0.1.7",
|
|
4
|
+
"description": "Memory-as-a-service MCP server for AI agents. 11 tools, Postgres + pgvector, multi-strategy retrieval. Works with Claude Code, Cursor, Codex, and any MCP client.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "./dist/index.js",
|
|
7
7
|
"bin": {
|
|
@@ -44,9 +44,11 @@
|
|
|
44
44
|
"cursor",
|
|
45
45
|
"codex"
|
|
46
46
|
],
|
|
47
|
-
"license": "
|
|
47
|
+
"license": "FSL-1.1-ALv2",
|
|
48
|
+
"homepage": "https://traqr.dev/memory",
|
|
48
49
|
"repository": {
|
|
49
50
|
"type": "git",
|
|
50
|
-
"url": "https://github.com/jiggycapital/traqr-oss"
|
|
51
|
+
"url": "https://github.com/jiggycapital/traqr-oss",
|
|
52
|
+
"directory": "packages/memory-mcp"
|
|
51
53
|
}
|
|
52
54
|
}
|