Documentation Index
Fetch the complete documentation index at: https://mintlify.com/dallay/corvus/llms.txt
Use this file to discover all available pages before exploring further.
Memory Tools
Corvus provides three memory tools that enable the agent to maintain long-term context across sessions:
memory_store — Save new memoriesmemory_recall — Search and retrieve memoriesmemory_forget — Delete specific memories
All memory tools integrate with the configured memory backend (SQLite, SurrealDB, or Markdown).
memory_store
Store a new memory entry with category and optional session scope.
Parameters
Unique identifier for the memory (e.g., user_preference_theme)
The memory content to store
Memory category: core, daily, conversation, or custom
Example
{
"key": "user_prefers_rust",
"content": "User strongly prefers Rust for system programming projects",
"category": "core"
}
{
"success": true,
"output": "Memory stored: user_prefers_rust",
"error": null
}
memory_recall
Search memories using hybrid vector + keyword search.
Parameters
Search query (natural language or keywords)
Maximum number of results to return
Search Algorithm
From src/memory/sqlite.rs and src/memory/vector.rs:
- Keyword Search: FTS5 full-text search with BM25 scoring
- Vector Search: Cosine similarity on embeddings
- Hybrid Merge: Weighted combination (default: 70% vector, 30% keyword)
[memory]
vector_weight = 0.7
keyword_weight = 0.3
Example
{
"query": "programming language preferences",
"limit": 3
}
{
"success": true,
"output": "Found 2 memories:\n\n1. user_prefers_rust (score: 0.92)\nUser strongly prefers Rust for system programming projects\n\n2. tried_python_but_slow (score: 0.71)\nUser tried Python but found it too slow for their use case",
"error": null
}
memory_forget
Delete a specific memory by key.
Parameters
Key of the memory to delete
Example
{"key": "outdated_preference"}
{
"success": true,
"output": "Memory deleted: outdated_preference",
"error": null
}
Memory Categories
From src/memory/traits.rs:32-44:
pub enum MemoryCategory {
/// Long-term facts, preferences, decisions
Core,
/// Daily session logs
Daily,
/// Conversation context
Conversation,
/// User-defined custom category
Custom(String),
}
Usage Guidelines
| Category | Use For | Retention |
|---|
| core | User preferences, long-term facts, decisions | Indefinite |
| daily | Session logs, temporary notes | Auto-pruned after 30 days |
| conversation | Current conversation context | Cleared per session |
| custom | Project-specific memories | User-managed |
Auto-Save Mode
When enabled, the agent automatically saves relevant context:
[memory]
auto_save = true
- Store important facts mentioned by the user
- Save decisions and outcomes
- Log errors and learnings
Session Scoping
Memories can be scoped to a specific session:
memory.store(
"current_task",
"Implementing new feature X",
MemoryCategory::Conversation,
Some("session-abc-123"),
).await?;
Backend Comparison
| Backend | Vector Search | Keyword Search | Performance |
|---|
| SQLite | ✅ (BLOB + cosine) | ✅ (FTS5 + BM25) | Fast (local) |
| SurrealDB | ✅ (native vectors) | ✅ (full-text) | Fast (local/remote) |
| Markdown | ❌ | ✅ (grep-based) | Slow (no indexing) |
Embedding Providers
Vector search requires an embedding provider:
[memory]
embedding_provider = "openai" # or "noop" to disable vectors
src/memory/embeddings.rs:13-20:
#[async_trait]
pub trait EmbeddingProvider: Send + Sync {
async fn embed(&self, text: &str) -> anyhow::Result<Vec<f32>>;
fn dimension(&self) -> usize;
}
Implementation Reference
pub struct MemoryStoreTool {
memory: Arc<dyn Memory>,
}
#[async_trait]
impl Tool for MemoryStoreTool {
async fn execute(&self, args: Value) -> Result<ToolResult> {
let key = args["key"].as_str()?;
let content = args["content"].as_str()?;
let category = parse_category(args["category"]);
self.memory.store(key, content, category, None).await?;
Ok(ToolResult {
success: true,
output: format!("Memory stored: {key}"),
error: None,
})
}
}
Best Practices
Use descriptive keys with prefixes: user_pref_theme, project_goal_Q1, decision_architecture_2026
Store memories incrementally as facts are learned, not in bulk at end of session
Don’t store sensitive data (passwords, API keys) in memory. Use config or secure storage.
