Tinmem Memory System
openclaw-tinmem provides persistent memory capabilities for the OpenClaw AI assistant.
Tools
memory_recall
Search and retrieve relevant memories from past conversations.
Use this tool when:
- The user references something from a previous conversation
- You need context about user preferences, background, or past decisions
- You want to check if a problem has been solved before
Parameters:
query (required): Search query to find relevant memoriesscope: Memory namespace (default: "global")categories: Filter by category: profile, preferences, entities, events, cases, patternslimit: Max results (default: 10)level: Detail level - L0 (headline), L1 (summary), L2 (full content)
Example:
{
"query": "user's preferred programming language",
"categories": ["profile", "preferences"],
"level": "L1"
}
memory_store
Store new information as a persistent memory.
Use this tool when:
- The user shares important personal information
- A significant decision is made
- A problem is solved in a novel way
- A new project or entity is introduced
Parameters:
content (required): The information to storecategory (required): profile | preferences | entities | events | cases | patternsscope: Memory namespaceimportance: 0.0-1.0 (default: 0.5)tags: Keywords for searchability
Example:
{
"content": "User is building a SaaS product called TaskFlow for project management, using Next.js 14 and PostgreSQL with Prisma",
"category": "entities",
"importance": 0.9,
"tags": ["taskflow", "nextjs", "postgresql", "saas"]
}
memory_forget
Remove memories that are no longer relevant or are incorrect.
Parameters:
id: Specific memory ID to deletequery: Search and delete matching memoriesscope: Limit deletion to this scopecategories: Limit deletion to these categories
Example:
{
"query": "old job at previous company",
"categories": ["profile", "entities"]
}
memory_update
Update an existing memory with corrected or additional information.
Parameters:
id (required): Memory ID to updatecontent: New full contentsummary: New summaryheadline: New headlineimportance: New importance scoretags: New tags (replaces existing)
Memory Categories Reference
| Category |
What to Store |
Merge Behavior |
profile |
User identity, role, expertise, demographics |
Always merge |
preferences |
Likes/dislikes, habits, recurring preferences |
Topic-based merge |
entities |
Projects, people, tools, organizations |
Merge if same entity |
events |
Decisions made, milestones, things that happened |
Always append (never merge) |
cases |
Problem-solution pairs, debugging sessions |
Always append (never merge) |
patterns |
Recurring workflows, methodologies, best practices |
Merge if same pattern |
Notes
- Memories are automatically injected into context before each response via
<agent-experience> tags
- New memories are automatically extracted after each conversation turn
- Similar memories are deduplicated using LLM-based analysis
- All memories persist across sessions in a local LanceDB database
1---2name: tinmem-memory-system3description: openclaw-tinmem provides persistent memory capabilities for the OpenClaw AI assistant.4---5
6# Tinmem Memory System
7
8openclaw-tinmem provides persistent memory capabilities for the OpenClaw AI assistant.
9
10## Tools
11
12### memory_recall
13
14Search and retrieve relevant memories from past conversations.
15
16Use this tool when:
17- The user references something from a previous conversation
18- You need context about user preferences, background, or past decisions
19- You want to check if a problem has been solved before
20
21**Parameters:**
22- `query` (required): Search query to find relevant memories
23- `scope`: Memory namespace (default: "global")
24- `categories`: Filter by category: profile, preferences, entities, events, cases, patterns
25- `limit`: Max results (default: 10)
26- `level`: Detail level - L0 (headline), L1 (summary), L2 (full content)
27
28**Example:**
29```json
30{
31 "query": "user's preferred programming language",
32 "categories": ["profile", "preferences"],
33 "level": "L1"
34}
35```
36
37---
38
39### memory_store
40
41Store new information as a persistent memory.
42
43Use this tool when:
44- The user shares important personal information
45- A significant decision is made
46- A problem is solved in a novel way
47- A new project or entity is introduced
48
49**Parameters:**
50- `content` (required): The information to store
51- `category` (required): profile | preferences | entities | events | cases | patterns
52- `scope`: Memory namespace
53- `importance`: 0.0-1.0 (default: 0.5)
54- `tags`: Keywords for searchability
55
56**Example:**
57```json
58{
59 "content": "User is building a SaaS product called TaskFlow for project management, using Next.js 14 and PostgreSQL with Prisma",
60 "category": "entities",
61 "importance": 0.9,
62 "tags": ["taskflow", "nextjs", "postgresql", "saas"]
63}
64```
65
66---
67
68### memory_forget
69
70Remove memories that are no longer relevant or are incorrect.
71
72**Parameters:**
73- `id`: Specific memory ID to delete
74- `query`: Search and delete matching memories
75- `scope`: Limit deletion to this scope
76- `categories`: Limit deletion to these categories
77
78**Example:**
79```json
80{
81 "query": "old job at previous company",
82 "categories": ["profile", "entities"]
83}
84```
85
86---
87
88### memory_update
89
90Update an existing memory with corrected or additional information.
91
92**Parameters:**
93- `id` (required): Memory ID to update
94- `content`: New full content
95- `summary`: New summary
96- `headline`: New headline
97- `importance`: New importance score
98- `tags`: New tags (replaces existing)
99
100---
101
102## Memory Categories Reference
103
104| Category | What to Store | Merge Behavior |
105|----------|---------------|----------------|
106| `profile` | User identity, role, expertise, demographics | Always merge |
107| `preferences` | Likes/dislikes, habits, recurring preferences | Topic-based merge |
108| `entities` | Projects, people, tools, organizations | Merge if same entity |
109| `events` | Decisions made, milestones, things that happened | Always append (never merge) |
110| `cases` | Problem-solution pairs, debugging sessions | Always append (never merge) |
111| `patterns` | Recurring workflows, methodologies, best practices | Merge if same pattern |
112
113## Notes
114
115- Memories are automatically injected into context before each response via `<agent-experience>` tags
116- New memories are automatically extracted after each conversation turn
117- Similar memories are deduplicated using LLM-based analysis
118- All memories persist across sessions in a local LanceDB database
modbender