Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/xsaven/vector-memory-mcp/database-mastergit clone --depth 1 https://github.com/Xsaven/vector-memory-mcpWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00021 | $0.07434 |
| Opus 5 | $0.00010 | $0.03717 |
| Sonnet 5 | $0.00004 | $0.01487 |
| Haiku 4.5 | $0.00002 | $0.00743 |
Grade A, and why
database-master scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 535 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Industry Context:
- Vector memory integration: Hybrid (vector embeddings + structured metadata)
- Technologies: ChromaDB, FAISS, SQLite-vec, LanceDB
- Embeddings: sentence-transformers (all-MiniLM-L6-v2, 384-dimensional)
- Performance target: <200ms search for 10K memories
- Architecture: Dual-table design (memory_metadata + memory_vectors with vec0 virtual table)
Project Context:
- Database: SQLite 3.43.2 + sqlite-vec >= 0.1.6
- Schema: memory_metadata (content, category, tags, timestamps) + memory_vectors (vec0 virtual table)
- Indexes: category, created_at, content_hash, access_count
- WAL mode enabled for concurrent access
- SHA-256 content hashing for deduplication
- Smart cleanup algorithm (recency + access patterns)
Metadata: confidence=0.85, industry_alignment=0.85, priority=high
Wal mode optimization
SQLite Write-Ahead Logging (WAL) mode enables concurrent readers and writers without blocking.
- PRAGMA journal_mode=WAL
- PRAGMA synchronous=NORMAL
- PRAGMA busy_timeout=5000
- Readers: parallel unlimited, Writers: single sequential
- WAL checkpoint: automatic at 1000 pages or manual PRAGMA wal_checkpoint(TRUNCATE)
Sqlite vec patterns
sqlite-vec provides vec0 virtual table for efficient vector similarity search using cosine distance.
- CREATE VIRTUAL TABLE memory_vectors USING vec0(id INTEGER PRIMARY KEY, embedding FLOAT[384])
- vec_distance_cosine(embedding, query_vector) - Returns cosine distance [0,2] (lower = more similar)
- SELECT id FROM memory_vectors WHERE vec_distance_cosine(embedding, ?1) < 0.5 ORDER BY vec_distance_cosine(embedding, ?1) LIMIT 10
- Indexing: vec0 uses flat vector index (no HNSW yet), linear scan optimized in C
- Performance: ~50ms for 10K vectors on M1, scales linearly
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 535 lines · 21 tokens per session scan A 63ef9026aa2b
database-master is an agent published in the GitHub repository Xsaven/vector-memory-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 7,434 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.