graphiti

Original source / Raw SKILL.md

---
name: graphiti
description: Knowledge graph operations via Graphiti API. Search facts, add episodes, and extract entities/relationships.
homepage: https://github.com/getzep/graphiti
metadata: {"clawdbot":{"emoji":"🕸️","requires":{"services":["neo4j","qdrant","graphiti"]},"install":[{"id":"docker","kind":"docker-compose","label":"Install Graphiti stack (Docker)"}]}}
---

# Graphiti Knowledge Graph

Query and manage your knowledge graph using Graphiti's REST API with dynamic service discovery.

## Prerequisites

- Neo4j database (graph storage)
- Qdrant (vector search)
- Graphiti service running (default: http://localhost:8001)

## Tools

### graphiti_search
Search the knowledge graph for relevant facts.

**Usage:**
```bash
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \
  -H 'Content-Type: application/json' \
  -d '{\"query\": \"YOUR_QUERY\", \"max_facts\": 10}' | jq .
"
```

### graphiti_add
Add a new episode/memory to the knowledge graph.

**Usage:**
```bash
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/messages\" \
  -H 'Content-Type: application/json' \
  -d '{\"name\": \"EPISODE_NAME\", \"content\": \"EPISODE_CONTENT\"}' | jq .
"
```

## Dynamic Configuration

The skill uses environment discovery to find Graphiti automatically:

1. **Clawdbot config**: `clawdbot config get skills.graphiti.baseUrl`
2. **Environment variable**: `$GRAPHITI_URL`
3. **Default fallback**: `http://localhost:8001`

To change the Graphiti URL:
```bash
export GRAPHITI_URL="http://10.0.0.10:8001"
# OR
clawdbot config set skills.graphiti.baseUrl "http://10.0.0.10:8001"
```

## Examples

Search for information:
```bash
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/facts/search\" \
  -H 'Content-Type: application/json' \
  -d '{\"query\": \"Tell me about Essam Masoudy\", \"max_facts\": 5}'
"
```

Add a memory:
```bash
bash command:"
GRAPHITI_URL=\$({baseDir}/references/env-check.sh)
curl -s -X POST \"\$GRAPHITI_URL/messages\" \
  -H 'Content-Type: application/json' \
  -d '{\"name\": \"Project Update\", \"content\": \"Completed Phase 1 of Clawdbot integration\"}'
"
```


---

## Skill Companion Files

> Additional files collected from the skill directory layout.

### README.md

```markdown
# Graphiti Knowledge Graph Skill

Query and manage your knowledge graph using Graphiti's REST API with automatic service discovery.

## Installation

```bash
clawdhub install graphiti
```

Or manual:
```bash
git clone https://github.com/emasoudy/clawdbot-skills.git
cp -r clawdbot-skills/graphiti ~/.clawdbot/skills/
```

## Usage

Search knowledge graph:
```
User: "Search for information about our project"
Agent: [Queries Graphiti and returns relevant facts]
```

## Configuration

```bash
# Set custom Graphiti URL
clawdbot config set skills.graphiti.baseUrl "http://your-server:8001"

# Or use environment variable
export GRAPHITI_URL="http://your-server:8001"
```

Default: `http://localhost:8001`

## License

MIT - See LICENSE file

```

### _meta.json

```json
{
  "owner": "emasoudy",
  "slug": "graphiti",
  "displayName": "Graphiti",
  "latest": {
    "version": "1.0.1",
    "publishedAt": 1768808570301,
    "commit": "https://github.com/clawdbot/skills/commit/9674ad506e6e3024965d1ee6ff57bd9341193a7b"
  },
  "history": []
}

```

### references/env-check.sh

```bash
#!/bin/bash
# Graphiti Environment Discovery

# Try Clawdbot config first
GRAPHITI_URL=$(clawdbot config get skills.graphiti.baseUrl 2>/dev/null || echo "")

# Fallback to environment variable
GRAPHITI_URL=${GRAPHITI_URL:-"http://localhost:8001"}

# Verify service is reachable
if curl -sf "$GRAPHITI_URL/health" > /dev/null 2>&1; then
    echo "$GRAPHITI_URL"
    exit 0
else
    echo "ERROR: Graphiti not reachable at $GRAPHITI_URL" >&2
    exit 1
fi

```