RemindCAUTION
A memory layer for AI Agents
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://pypi.org/project/remind-mcp/) [](https://www.python.org/downloads/) [](LICENSE)
Agent-driven memory layer for LLMs. Remind is a deterministic memory substrate with temporal facts, semantic retrieval, and structured curation — the calling agent is the only intelligence.
[Documentation](https://sandst1.github.io/remind/) · [Examples](https://sandst1.github.io/remind/examples/) · [Changelog](https://sandst1.github.io/remind/reference/changelog)
Quick start
pip install remind-mcp
No configuration required — Remind uses local embeddings by default (fastembed, no API key).
remind remember "This project uses React with TypeScript" remind remember "Chose PostgreSQL for the database" -t decision remind remember "Cache TTL is 600 seconds" -t fact -e concept:caching remind recall "What tech stack are we using?"
How it works
Remind stores episodes (raw experiences) and concepts (generalized knowledge). You capture and curate memories explicitly using CLI commands or MCP tools.
For facts (-t fact), Remind automatically:
- Creates a
Factrow with validity tracking - Assigns it to a cluster based on entity overlap (Jaccard similarity)
- Detects potential collisions with existing facts — same-cluster collisions and cross-cluster related facts are returned with ready-to-paste
applycommands
For any remember call, the output also surfaces the top-5 nearest episodes and concepts semantically, so you can catch contradictions before they go unnoticed.
For patterns and concepts, you use remind apply to create them from episodes:
remind apply << 'EOF' concept from=ep:11,ep:12 title="Retry-with-backoff for resilience" "Exponential
e2996848dbd7OBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add remind-docs --env AZURE_OPENAI_API_KEY=${AZURE_OPENAI_API_KEY} --env OPENAI_API_KEY=${OPENAI_API_KEY} --env REMIND_HYBRID_KEYWORD_WEIGHT=${REMIND_HYBRID_KEYWORD_WEIGHT} -- npx -y [email protected]{
"mcpServers": {
"remind-docs": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"AZURE_OPENAI_API_KEY": "${AZURE_OPENAI_API_KEY}",
"OPENAI_API_KEY": "${OPENAI_API_KEY}",
"REMIND_HYBRID_KEYWORD_WEIGHT": "${REMIND_HYBRID_KEYWORD_WEIGHT}"
}
}
}
}Exposed tools (20)
15 read · 3 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
apply | write | Apply a batch changeset to memory. |
delete_concept | destructive | Soft delete a concept from memory. |
delete_episode | destructive | Soft delete an episode from memory. |
dismiss_conflict | read | Dismiss a conflict: both claims are valid (e.g. different contexts). |
entities | read | List entities (files, functions, people, etc.) in memory. |
episode_types | read | List configured episode types. |
events | read | Read the append-only change feed of writes. |
inspect | read | Inspect concepts or episodes in memory. |
inspect_entity | read | Inspect an entity and its relationships. |
list_conflicts | read | List detected memory conflicts (contradictions) awaiting triage. |
list_deleted | read | List soft-deleted episodes and concepts. |
recall | read | Retrieve relevant memories for a query. |
remember | read | Store an experience or observation in memory (fast, no LLM calls). |
resolve_conflict | read | Resolve a conflict by declaring which fact is correct. |
restore_concept | read | Restore a previously deleted concept. |
restore_episode | read | Restore a previously deleted episode. |
snapshot | read | Read a snapshot of memory state as JSON. |
stats | read | Get memory statistics. |
update_concept | write | Update an existing concept. |
update_episode | write | Update an existing episode in memory. |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (10 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (13)
memory.db
delete_concept, delete_episode
return hashlib.md5(db_url.encode()).hexdigest()[:12]
return hashlib.md5(raw.encode()).hexdigest()[:16]
"url": "http://127.0.0.1:8765/sse?db=my-project"
Web UI at `http://127.0.0.1:8765/ui/`, REST API at `/api/v1/`.
"url": "http://127.0.0.1:8765/sse?db=my-project"
d3, lucide-svelte, @sveltejs/vite-plugin-svelte, @tsconfig/svelte, svelte, svelte-check, typescript, vite
vitepress
.remind/remind.db
docs/architecture.png
docs/architecture_original.png
website/public/architecture.png
Gates applied: no_behavioural_pass.
e2996848dbd7full audit observations/trust-audit/mcp-server/sandst1__remind.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | e2996848dbd7 | CAUTION | B | 89 | first audit |
Questions
What is the Remind MCP server?
A memory layer for AI Agents
What tools does Remind expose?
20 in total: 15 read-only, 3 that write, and 2 that can delete or overwrite (delete_concept, delete_episode). Every one is listed on this page with its risk.
Is Remind safe to connect to an agent?
With care. The audit graded it B (89/100) and found 13 things worth knowing before you trust this server, listed below with the exact line each was found on. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Remind need?
It reads AZURE_OPENAI_API_KEY, OPENAI_API_KEY and REMIND_HYBRID_KEYWORD_WEIGHT from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How current is this page?
The grade is for one exact copy of the source (e2996848dbd7), read on 2026-10-07. The repository is watched and re-audited when it changes.