How do I install the Lightrag Memory skill?

Run npx skillmds@latest add lord1egypt/lightrag-memory in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Lightrag Memory safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Lightrag Memory?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Lightrag Memory free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Lightrag Memory?

Lord1Egypt (@lord1egypt) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Lightrag Memory by lord1egypt — Agent Skill

Name: Lightrag Memory
Rating: 4.5 (4 reviews)
Author: Lord1Egypt

Lightrag Memory

LightRAG-based semantic memory system for AI agents. Provides efficient long-term knowledge storage and retrieval using vector embeddings and knowledge graphs. Use when: (1) semantic search over agent memory files is needed, (2) reducing token usage by avoiding full-file re-reading, (3) building a knowledge graph from text documents, (4) querying memory with natural language instead of keyword matching. Supports naive, local, global, and hybrid query modes.

Lord1Egypt Updated Sep 8, 2026 2 repo stars

File contents

LightRAG Memory

Semantic memory system with vector search + knowledge graph. Replaces reading entire memory files on every request with targeted retrieval (~1-3K tokens vs 30K+).

Quick Setup

cd skills/lightrag-memory
pip install -r requirements.txt

Set environment variables:

export OPENAI_API_KEY="your-key"
export OPENAI_BASE_URL="https://your-api-endpoint/v1"  # optional, defaults to OpenAI

Or create a .env file in the skill directory.

Commands

Index memory files

Index MEMORY.md and memory/*.md from workspace:

python3 scripts/rag.py index

Insert content

# From file
python3 scripts/rag.py insert --file /path/to/file.md --source "filename"

# From text
python3 scripts/rag.py insert --text "Important fact" --source "manual"

# From stdin
echo "Some text" | python3 scripts/rag.py insert --source "stdin"

Query

# Hybrid search (best results, costs more API calls)
python3 scripts/rag.py query "What do I know about the user?" --mode hybrid

# Local search (entities + relationships, balanced)
python3 scripts/rag.py query "What projects were discussed?" --mode local

# Naive search (simple vector lookup, cheapest)
python3 scripts/rag.py query "Any notes about deployment?" --mode naive

# Global search (broad context, expensive)
python3 scripts/rag.py query "Summarize everything" --mode global

Query Modes

Mode	What it searches	Cost	Best for
naive	Vector embeddings only	Lowest	Quick fact lookup
local	Entities + relationships	Low	Specific entities
global	Community-level context	High	Broad understanding
hybrid	Local + global	Highest	Comprehensive answers

Storage

Data stored in ~/.openclaw/workspace/lightrag_storage/ by default. Override with LIGHTARG_WORKING_DIR env var.

Integration Pattern

For agent memory systems, index files on change and query on demand:

# Check if reindex needed (files modified since last index)
find MEMORY.md memory/ -name '*.md' -newer memory/lightrag-last-index.txt

# Reindex if needed
python3 scripts/rag.py index
touch memory/lightrag-last-index.txt

# Query when context needed
python3 scripts/rag.py query "user preferences" --mode naive

Architecture

Embeddings: text-embedding-3-small (1536 dim) via OpenAI-compatible API
LLM: gpt-4o-mini for entity extraction and answer generation
Storage: JSON-based vector DB + GraphML knowledge graph
Batching: 8 items per embedding batch, 4 concurrent async requests

Troubleshooting

OPENAI_API_KEY not set: Ensure env vars are exported or .env exists.

numpy RuntimeError (X86_V2): On older CPUs lacking AVX2, install pip install "numpy<2.0".

Slow first index: Initial indexing processes all files. Subsequent updates are incremental.

Reset storage: rm -rf <storage_dir>/* && python3 scripts/rag.py index

---name: lightrag-memorydescription: LightRAG-based semantic memory system for AI agents. Provides efficient long-term knowledge storage and retrieval using vector embeddings and knowledge graphs. Use when: (1) semantic search over agent memory files is needed, (2) reducing token usage by avoiding full-file re-reading, (3) building a knowledge graph from text documents, (4) querying memory with natural language instead of keyword matching. Supports naive, local, global, and hybrid query modes.---# LightRAG MemorySemantic memory system with vector search + knowledge graph. Replaces reading entirememory files on every request with targeted retrieval (~1-3K tokens vs 30K+).## Quick Setup```bashcd skills/lightrag-memorypip install -r requirements.txt```Set environment variables:```bashexport OPENAI_API_KEY="your-key"export OPENAI_BASE_URL="https://your-api-endpoint/v1" # optional, defaults to OpenAI```Or create a `.env` file in the skill directory.## Commands### Index memory filesIndex `MEMORY.md` and `memory/*.md` from workspace:```bashpython3 scripts/rag.py index```### Insert content```bash# From filepython3 scripts/rag.py insert --file /path/to/file.md --source "filename"# From textpython3 scripts/rag.py insert --text "Important fact" --source "manual"# From stdinecho "Some text" | python3 scripts/rag.py insert --source "stdin"```### Query```bash# Hybrid search (best results, costs more API calls)python3 scripts/rag.py query "What do I know about the user?" --mode hybrid# Local search (entities + relationships, balanced)python3 scripts/rag.py query "What projects were discussed?" --mode local# Naive search (simple vector lookup, cheapest)python3 scripts/rag.py query "Any notes about deployment?" --mode naive# Global search (broad context, expensive)python3 scripts/rag.py query "Summarize everything" --mode global```## Query Modes| Mode | What it searches | Cost | Best for ||------|-----------------|------|----------|| naive | Vector embeddings only | Lowest | Quick fact lookup || local | Entities + relationships | Low | Specific entities || global | Community-level context | High | Broad understanding || hybrid | Local + global | Highest | Comprehensive answers |## StorageData stored in `~/.openclaw/workspace/lightrag_storage/` by default.Override with `LIGHTARG_WORKING_DIR` env var.## Integration PatternFor agent memory systems, index files on change and query on demand:```bash# Check if reindex needed (files modified since last index)find MEMORY.md memory/ -name '*.md' -newer memory/lightrag-last-index.txt# Reindex if neededpython3 scripts/rag.py indextouch memory/lightrag-last-index.txt# Query when context neededpython3 scripts/rag.py query "user preferences" --mode naive```## Architecture- **Embeddings**: `text-embedding-3-small` (1536 dim) via OpenAI-compatible API- **LLM**: `gpt-4o-mini` for entity extraction and answer generation- **Storage**: JSON-based vector DB + GraphML knowledge graph- **Batching**: 8 items per embedding batch, 4 concurrent async requests## Troubleshooting**OPENAI_API_KEY not set**: Ensure env vars are exported or `.env` exists.**numpy RuntimeError (X86_V2)**: On older CPUs lacking AVX2, install `pip install "numpy<2.0"`.**Slow first index**: Initial indexing processes all files. Subsequent updates are incremental.**Reset storage**: `rm -rf <storage_dir>/* && python3 scripts/rag.py index`

Frequently asked questions