{"id":"0xrelogic-cognio","name":"Cognio","homepage":"https://github.com/0xReLogic/Cognio/blob/main/QUICKSTART.md","repo_url":"https://github.com/0xReLogic/Cognio","category":"ai-ml","subcategories":[],"tags":["ai-memory","mcp-server","semantic-search","sqlite","fastapi","sentence-transformers","vector-search","self-hosted"],"what_it_does":"Cognio is an MCP server and local REST API for storing persistent semantic memories in a SQLite database, enabling semantic (and optional hybrid) search across conversations/projects. It also exposes MCP tools for memory CRUD, project management, stats, export, and text summarization, plus a local web UI dashboard.","use_cases":["Long-term personal knowledge base that persists across AI sessions","Semantic retrieval of notes, research, and learning journals","Project-scoped memory management to reduce cross-workspace mixing","Embedding-based memory search for assistants (via MCP or REST)","Exporting memories for backup/migration and generating summaries"],"not_for":["Highly secure multi-tenant deployments without network isolation","Use cases requiring strict data residency guarantees or enterprise compliance commitments","Production systems needing guaranteed SLAs or formal reliability guarantees"],"best_when":"You want a self-hosted/local semantic memory store for an AI assistant, with project/tag organization and an agent-friendly MCP tool interface.","avoid_when":"You cannot control network access to the server or where storing user content in a local SQLite DB without formal compliance/security controls is unacceptable.","alternatives":["Local vector DB + custom RAG/Memory service (e.g., PostgreSQL+pgvector, Qdrant, Weaviate) paired with a thin MCP layer","Other MCP memory/knowledge services (community implementations) if they provide similar CRUD + semantic search"],"af_score":56.5,"security_score":45.5,"reliability_score":22.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:41:29.766105+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Optional API key via API_KEY environment variable (exact header/behavior not specified in provided content)"],"oauth":false,"scopes":false,"notes":"Authentication appears optional (API_KEY in .env.example). The README does not document auth header format, enforcement behavior, or scope granularity."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source self-hosted. Costs depend on embedding model runtime and optional LLM-based features (e.g., Groq/OpenAI) if enabled."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":56.5,"security_score":45.5,"reliability_score":22.5,"mcp_server_quality":78.0,"documentation_accuracy":65.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":55.0,"rate_limit_clarity":10.0,"tls_enforcement":70.0,"auth_strength":35.0,"scope_granularity":20.0,"dependency_hygiene":45.0,"secret_handling":60.0,"security_notes":"Self-hosted service with optional API_KEY authentication; no details provided on header names, enforcement, or rate limiting. LLM provider keys (e.g., GROQ_API_KEY/OPENAI_API_KEY) are listed as env vars, but no guidance is shown on logging/propagation. TLS requirements and secure deployment hardening are not documented in provided content.","uptime_documented":0.0,"version_stability":30.0,"breaking_changes_history":25.0,"error_recovery":35.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"offset/limit or page-based pagination is implied for list_memories, but the specific style and parameters are not provided in the README excerpt.","retry_guidance_documented":false,"known_agent_gotchas":["Project isolation requires explicitly setting project or using set_active_project; otherwise memories may mix across workspaces.","Optional auto-tagging and summarization depend on external LLM provider configuration; failures there may impact tool flows."]}}