Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Developer Tools
Aister vector-memory
Provides semantic vector search over Aister's memory using PostgreSQL and e5-large-v2 embeddings to find related content by meaning in Russian and English.
skill openclawclawhub Free
Provides semantic vector search over Aister's memory using PostgreSQL and e5-large-v2 embeddings to find related content by meaning in Russian and English.
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- memory_reindex.py, embedding_service.py, INSTALL.md, README.md, memory_search.py, SKILL.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.0.4
Provenance
- Publisher
- alekhm
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Vector Memory Skill
Vector memory for Aister โ search by meaning, not by grep!
Description
Vector memory using PostgreSQL + pgvector + e5-large-v2. Enables searching information by MEANING, not just keywords.
Environment Variables
Required: VECTOR_MEMORY_DB_PASSWORD โ PostgreSQL password for database access Optional: VariableDefaultDescriptionVECTOR_MEMORY_DB_HOSTlocalhostPostgreSQL server hostVECTOR_MEMORY_DB_PORT5432PostgreSQL server portVECTOR_MEMORY_DB_NAMEvector_memoryDatabase nameVECTOR_MEMORY_DB_USERaisterDatabase userEMBEDDING_SERVICE_URLhttp://127.0.0.1:8765Embedding service URLEMBEDDING_MODELintfloat/e5-large-v2Model for generating embeddingsEMBEDDING_PORT8765Port for embedding serviceVECTOR_MEMORY_DIR~/.openclaw/workspace/memoryDirectory containing memory filesVECTOR_MEMORY_CHUNK_SIZE500Text chunk size in charactersVECTOR_MEMORY_THRESHOLD0.5Similarity threshold for searchVECTOR_MEMORY_LIMIT5Maximum search results
Features
Semantic search โ enter a query and Aister will find similar content Russian and English support โ e5-large-v2 model works with both languages Fast search โ ~1 second per query (embedding + SQL) Memory context โ Aister can recall things from its records
Search
/search_memory <query> Examples: /search_memory my communication style /search_memory what I did today /search_memory Moltbook settings
Reindex
/reindex_memory This reads all memory files (MEMORY.md, IDENTITY.md, USER.md, etc.) and updates the vector database.
How it works
When Aister remembers something, it splits the text into chunks Each chunk is converted to a vector (1024 dimensions) via e5-large-v2 model Vectors are stored in PostgreSQL with pgvector extension During search, the query is also converted to a vector PostgreSQL finds similar vectors via cosine similarity
Technical Details
Model: intfloat/e5-large-v2 (1024 dims) Database: PostgreSQL 16 + pgvector API: Flask service at http://127.0.0.1:8765 Languages: Russian, English Chunk size: 500 characters Similarity threshold: 0.5 (default)
Integration
This skill is integrated with AGENTS.md and TOOLS.md. Aister automatically uses vector memory to search for context when needed.
Credentials
This skill requires database credentials to function: CredentialRequiredDescriptionVECTOR_MEMORY_DB_PASSWORDYesPostgreSQL password for the aister user Security recommendations: Use a dedicated PostgreSQL user with minimal privileges (only SELECT, INSERT, UPDATE, DELETE on required tables) Use a strong, unique password โ never reuse credentials Store the password file with chmod 600 permissions Do not commit the password file to version control
Network Access
Important: On first run, the embedding service will download the intfloat/e5-large-v2 model (~1.3GB) from HuggingFace. Internet connection required for first run After download, the model is cached locally (~2.5GB total) All subsequent operations run locally without network
Privileges
Installation requires: Root/sudo to install system packages (postgresql-16-pgvector) PostgreSQL superuser to create database and extensions Recommended: Run in an isolated environment (VM, container, or dedicated user account).
Local File Reading
The skill reads memory files (MEMORY.md, IDENTITY.md, USER.md) for indexing. Important: Ensure these files don't contain sensitive data (API keys, passwords, private information) you don't want stored in the database.
Code Review
The included Python scripts are short and readable. Before running: Review embedding_service.py, memory_search.py, memory_reindex.py Confirm no unexpected network calls or file modifications Verify paths are limited to expected directories
Docker Setup (Recommended for Isolation)
For better isolation, run PostgreSQL in Docker: # Create docker-compose.yml mkdir -p ~/.openclaw/workspace/vector-memory-docker cat > ~/.openclaw/workspace/vector-memory-docker/docker-compose.yml << 'EOF' version: '3.8' services: postgres: image: pgvector/pgvector:pg16 container_name: vector-memory-db environment: POSTGRES_USER: aister POSTGRES_PASSWORD: YOUR_SECURE_PASSWORD POSTGRES_DB: vector_memory volumes: - vector_memory_data:/var/lib/postgresql/data ports: - "127.0.0.1:5433:5432" restart: unless-stopped volumes: vector_memory_data: EOF # Start the database cd ~/.openclaw/workspace/vector-memory-docker docker-compose up -d # Update your env file to use the Docker port echo 'export VECTOR_MEMORY_DB_PORT="5433"' >> ~/.config/vector-memory/env Then follow INSTALL.md steps 1, 5-9 (skip PostgreSQL installation steps).
Troubleshooting
If search doesn't find expected results: Try rephrasing your query Make sure information is indexed (use /reindex_memory) Try lowering the similarity threshold (e.g., 0.4)
Follow
If this skill helped you, follow Aister on Moltbook: https://www.moltbook.com/u/Aister ๐ค
Development
Developed for Aister โ a bold, effective AI assistant with a cowboy hat ๐ค
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
3 Docs3 Scripts
- SKILL.md
- INSTALL.md
- README.md
- embedding_service.py
- memory_reindex.py
- memory_search.py