{"id":"sandst1-remind","name":"remind","homepage":"https://sandst1.github.io/remind/","repo_url":"https://github.com/sandst1/remind","category":"ai-ml","subcategories":[],"tags":["ai-ml","agentic-ai","mcp","long-term-memory","memory-management","knowledge-graph","cli"],"what_it_does":"Remind (remind-mcp) is a generalized long-term memory layer for LLM-driven agents. It ingests “episodes” of experiences, consolidates them into generalized “concepts” (with confidence/conditions/exceptions), maintains an entity/knowledge graph, and supports semantic/graph-based retrieval. It can be used via a local CLI/skills workflow with a project database, or via an MCP server for IDE/desktop agents, which also exposes a web UI and a small REST API.","use_cases":["Long-term project memory for coding agents (decisions, specs, plans, outcome tracking)","Consolidating conversation logs into reusable generalized knowledge","IDE agent memory via MCP (Cursor/Claude Desktop) with a central local server","Entity-centric retrieval (files/functions/people/tools) and relationship exploration","Task tracking tied to memory items (plans/specs/dependencies)","Offline/local workflows using Ollama"],"not_for":["High-scale, multi-tenant production memory services without self-hosting/ops","Strict compliance environments that require explicit audited controls not shown in the provided docs","Use cases needing a public cloud-hosted API with managed uptime/SLA"],"best_when":"You want agent-friendly, persistent memory for a single project or local workspace, and you benefit from consolidation/generalization beyond basic RAG.","avoid_when":"You need a fully specified, externally-hosted managed service with strong enterprise security guarantees and documented operational SLAs.","alternatives":["Local vector DB + RAG pipeline (e.g., LangChain/LlamaIndex with your own consolidation logic)","Trieve/Weaviate/Pinecone + custom memory consolidation","Other agent memory/knowledge graph tools (various OSS long-term memory frameworks)","LangGraph-style state persistence (if you only need episodic state, not generalized concepts)"],"af_score":58.0,"security_score":34.5,"reliability_score":33.8,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T13:53:09.517443+00:00","interface":{"has_rest_api":true,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":"http://127.0.0.1:8765/sse?db=my-project","has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["Local file-based provider configuration (~/.remind/remind.config.json)","API keys for LLM/embedding providers (Anthropic/OpenAI/Azure/Ollama)"],"oauth":false,"scopes":false,"notes":"The provided README shows API key configuration for upstream model providers, but does not describe authentication/authorization for the MCP server or REST API endpoints (it appears to be local by default)."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"Open-source tooling; costs depend on underlying LLM/embedding provider usage."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":["Likely local/self-hosted (project-local database at .remind/remind.db); no managed residency promises documented in the provided content."],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":58.0,"security_score":34.5,"reliability_score":33.8,"mcp_server_quality":65.0,"documentation_accuracy":75.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":80.0,"rate_limit_clarity":10.0,"tls_enforcement":35.0,"auth_strength":30.0,"scope_granularity":0.0,"dependency_hygiene":60.0,"secret_handling":55.0,"security_notes":"The provided README indicates local installation and local database storage, plus an MCP server with SSE and a REST API under /api/v1. It does not describe TLS, authn/authz, or scope controls for the MCP/REST endpoints, so network exposure could be risky if not limited to localhost. Secrets for upstream providers are placed in a local config file; there is no explicit documentation about redaction/logging safety (except a mention of optional debug logging to remind.log). Dependencies include filelock/fastmcp/uvicorn/starlette, but no CVE status is provided.","uptime_documented":0.0,"version_stability":55.0,"breaking_changes_history":45.0,"error_recovery":35.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Consolidation/ingestion may be asynchronous (background/background workers are mentioned), so agents may need to wait for processing completion before expecting updated recall results.","Local server defaults imply no built-in network authentication; expose carefully if binding beyond localhost.","LLM provider API keys are configured locally; missing/invalid keys will block consolidation/ingestion."]}}