Cognio
by 0xReLogic
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | No | Optional API key for authentication | |
| DB_PATH | No | Path to the SQLite database file | ./data/memory.db |
| API_HOST | No | API server host | 0.0.0.0 |
| API_PORT | No | API server port | 8080 |
| LOG_LEVEL | No | Logging level | info |
| BATCH_SIZE | No | Batch size for processing | 32 |
| GROQ_MODEL | No | Groq model | openai/gpt-oss-120b |
| EMBED_MODEL | No | Sentence transformer model for embeddings | all-MiniLM-L6-v2 |
| HYBRID_MODE | No | Hybrid search mode: candidate or rerank | rerank |
| EMBED_DEVICE | No | Device for embedding model (cpu or cuda) | cpu |
| GROQ_API_KEY | No | Groq API key (required if LLM_PROVIDER=groq) | |
| HYBRID_ALPHA | No | Hybrid search alpha parameter | 0.6 |
| LLM_PROVIDER | No | LLM provider for auto-tagging | groq |
| OPENAI_MODEL | No | OpenAI model | gpt-4o-mini |
| LEANN_BACKEND | No | LEANN backend | hnsw |
| LEANN_ENABLED | No | Enable LEANN vector search | false |
| HYBRID_ENABLED | No | Enable hybrid search | true |
| OPENAI_API_KEY | No | OpenAI API key | |
| AUTOTAG_ENABLED | No | Enable auto-tagging | true |
| MAX_TEXT_LENGTH | No | Maximum text length for processing | 10000 |
| LEANN_INDEX_PATH | No | Path to LEANN index | ./data/leann/memories.leann |
| LEANN_LAZY_BUILD | No | Lazy build LEANN index | true |
| HYBRID_RERANK_TOPK | No | Rerank candidate pool size | 100 |
| SUMMARIZE_THRESHOLD | No | Summarization threshold | 50 |
| DEFAULT_SEARCH_LIMIT | No | Default number of search results | 5 |
| EMBEDDING_CACHE_PATH | No | Path to embedding cache | ./data/embedding_cache.pkl |
| SIMILARITY_THRESHOLD | No | Similarity threshold for search | 0.4 |
| SUMMARIZATION_METHOD | No | Summarization method: extractive or abstractive | abstractive |
| LEANN_WARMUP_ON_START | No | Warmup LEANN on start | false |
| SUMMARIZATION_ENABLED | No | Enable summarization | true |
| LEANN_RECOMPUTE_ON_SEARCH | No | Recompute LEANN index on search | true |
| SUMMARIZATION_EMBED_MODEL | No | Summarization embedding model | all-MiniLM-L6-v2 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/0xReLogic/Cognio'
If you have feedback or need assistance with the MCP directory API, please join our Discord server