remind

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.

Evaluated Mar 30, 2026 (22d ago)
Homepage ↗ Repo ↗ Ai Ml ai-ml agentic-ai mcp long-term-memory memory-management knowledge-graph cli
⚙ Agent Friendliness
58
/ 100
Can an agent use this?
🔒 Security
34
/ 100
Is it safe for agents?
⚡ Reliability
34
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
75
Error Messages
0
Auth Simplicity
80
Rate Limits
10

🔒 Security

TLS Enforcement
35
Auth Strength
30
Scope Granularity
0
Dep. Hygiene
60
Secret Handling
55

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.

⚡ Reliability

Uptime/SLA
0
Version Stability
55
Breaking Changes
45
Error Recovery
35
AF Security Reliability

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.

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

Interface

REST API
Yes
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Local file-based provider configuration (~/.remind/remind.config.json) API keys for LLM/embedding providers (Anthropic/OpenAI/Azure/Ollama)
OAuth: No Scopes: No

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

Free tier: No
Requires CC: No

Open-source tooling; costs depend on underlying LLM/embedding provider usage.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known 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.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for remind.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered