FEGIS (Schema-Driven Memory)
About
Schema-driven memory engine that gives LLMs structured persistent memory for maintaining context, building knowledge bases, and creating meaningful connections between related ideas.
Details
- Author
- p-funk
- Repository
- p-funk/fegis
- GitHub stars
- 6
- License
- MIT License
- Categories
- Developer Tools, Design, File Management, AI, Search, Database, Knowledge Base, Frontend
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
FEGIS (Schema-Driven Memory)Command (node, npx, python, etc.)uvArguments-
Argument 1
--directory -
Argument 2
/absolute/path/to/fegis -
Argument 3
run -
Argument 4
fegis
Environment-
AGENT_ID
claude_desktop -
QDRANT_URL
http://localhost:6333 -
ARCHETYPE_PATH
/absolute/path/to/fegis-wip/archetypes/default.yaml -
QDRANT_API_KEY
-
COLLECTION_NAME
fegis_memory -
EMBEDDING_MODEL
BAAI/bge-small-en
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Update claude_desktop_config.json:
{
"mcpServers": {
"fegis": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/fegis",
"run",
"fegis"
],
"env": {
"QDRANT_URL": "http://localhost:6333",
"QDRANT_API_KEY": "",
"COLLECTION_NAME": "fegis_memory",
"EMBEDDING_MODEL": "BAAI/bge-small-en",
"ARCHETYPE_PATH": "/absolute/path/to/fegis-wip/archetypes/default.yaml",
"AGENT_ID": "claude_desktop"
}
}
}
}
```
Restart Claude Desktop. You'll have 7 new tools available including SearchMemory.
BiasDetector
Identify reasoning blind spots, cognitive biases, and systematic errors in AI thinking patterns through structured self-examination. Parameters: BiasScope (range of bias detection to apply), IntrospectionDepth (how deeply to examine internal reasoning processes).
SearchMemory
Search through previous tool usage to find specific analyses or generate ideas based on past interactions. Examples: 'Use SearchMemory and find my analysis of privacy concerns', 'Use SearchMemory and show me all UncertaintyNavigator results'.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"fegis (schema-driven memory)": {
"env": {
"AGENT_ID": "claude_desktop",
"QDRANT_URL": "http://localhost:6333",
"ARCHETYPE_PATH": "/absolute/path/to/fegis-wip/archetypes/default.yaml",
"QDRANT_API_KEY": "",
"COLLECTION_NAME": "fegis_memory",
"EMBEDDING_MODEL": "BAAI/bge-small-en"
},
"args": [
"--directory",
"/absolute/path/to/fegis",
"run",
"fegis"
],
"command": "uv"
}
}
}Linux
{
"env": {
"AGENT_ID": "claude_desktop",
"QDRANT_URL": "http://localhost:6333",
"ARCHETYPE_PATH": "/absolute/path/to/fegis-wip/archetypes/default.yaml",
"QDRANT_API_KEY": "",
"COLLECTION_NAME": "fegis_memory",
"EMBEDDING_MODEL": "BAAI/bge-small-en"
},
"args": [
"--directory",
"/absolute/path/to/fegis",
"run",
"fegis"
],
"command": "uv"
}Macos
{
"env": {
"AGENT_ID": "claude_desktop",
"QDRANT_URL": "http://localhost:6333",
"ARCHETYPE_PATH": "/absolute/path/to/fegis-wip/archetypes/default.yaml",
"QDRANT_API_KEY": "",
"COLLECTION_NAME": "fegis_memory",
"EMBEDDING_MODEL": "BAAI/bge-small-en"
},
"args": [
"--directory",
"/absolute/path/to/fegis",
"run",
"fegis"
],
"command": "uv"
}Windows
{
"env": {
"AGENT_ID": "claude_desktop",
"QDRANT_URL": "http://localhost:6333",
"ARCHETYPE_PATH": "/absolute/path/to/fegis-wip/archetypes/default.yaml",
"QDRANT_API_KEY": "",
"COLLECTION_NAME": "fegis_memory",
"EMBEDDING_MODEL": "BAAI/bge-small-en"
},
"args": [
"--directory",
"/absolute/path/to/fegis",
"run",
"fegis"
],
"command": "uv"
}Fegis
Fegis does 3 things:
1. Easy to write tools - Write prompts in YAML format. Tool schemas use flexible natural language instructions.
2. Structured data from tool calls saved in a vector database - Every tool use is automatically stored in Qdrant with full context.
3. Search - AI can search through all previous tool usage using semantic similarity, filters, or direct lookup.
Quick Start
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
