agent-memory-sqlite
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@agent-memory-sqlite remember that we deploy to Vercel on merge to main"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
agent-memory-sqlite
Persistent, searchable memory for coding agents, exposed as an MCP server. Your agent saves the decisions and conventions it learns, and recalls them in the next session instead of rediscovering them.
One SQLite file, shared safely by every agent session (WAL mode)
Zero native dependencies: Node's built-in
node:sqlitewith FTS5, nothing to compile on Windows, macOS or LinuxRanked recall: BM25 relevance, boosted by recency, scoped per project
Works with any MCP client: Claude Code, Cursor, Claude Desktop, Windsurf
Quick start
Requires Node 24+.
Claude Code
claude mcp add memory -- npx -y github:Urthella/agent-memory-sqliteCursor / Claude Desktop (mcp.json / claude_desktop_config.json)
{
"mcpServers": {
"memory": { "command": "npx", "args": ["-y", "github:Urthella/agent-memory-sqlite"] }
}
}Then just work: tell the agent "remember that we deploy on Vercel", and ask "what do we know about deploys?" in a later session.
Related MCP server: rekal
Tools
Tool | What it does |
| Save a fact, decision or convention, with optional tags. Saving the same text again refreshes it instead of duplicating. |
| Keyword search, best match first. Prefix matching, so |
| The latest saved or refreshed memories. |
| Delete a memory by its |
Every tool takes an optional project. It defaults to the name of the directory the agent runs in; "*" searches all projects.
How it works
flowchart LR
A[Coding agent] -- MCP over stdio --> S[server.ts]
S --> M[(memories table)]
M -- insert/update/delete triggers --> F[(FTS5 index)]
S -- MATCH + bm25 --> FStorage: a plain
memoriestable plus an external-content FTS5 index kept in sync by triggers, so text is stored once and every write path updates search.Dedup: a SHA-256 of the text is unique per project; saving it again only bumps
updated_at.Safe queries: free text is reduced to quoted prefix terms (
"redis"* OR "lua"*), so punctuation and FTS operators in a question can't break the query.Ranking: the top BM25 hits are reranked by
relevance × (1 + recency), where recency halves every 30 days.Accents: the tokenizer folds diacritics, so
agacfindsağaç.
Configuration
Variable | Default |
|
|
| name of the current directory |
Develop
npm ci # also builds dist/
npm test # node --test, runs the .ts sources directlynix develop (or direnv) gives you the same Node 24 toolchain. CI runs on Linux, macOS and Windows.
License
Available Tools
4 toolsforgetADestructive
Delete a memory by its id (the #number shown by recall and recent).
Inputs: id (required).
recallCRead-only
Search saved memories by keywords. Best matches first (BM25), with recent memories ranked higher.
Inputs: query (required), limit, project.
recentBRead-only
List the most recently saved or refreshed memories.
Inputs: limit, project.
rememberB
Save a durable fact, decision or convention for future sessions. Saving the same text again refreshes it instead of duplicating.
Inputs: content (required), tags, project.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool maps to a clear memory operation: save, search, list-recent, and delete. The only mild overlap is between recall and recent, since both retrieve memories, but their descriptions distinguish keyword search from recency listing.
Names are short, lowercase, and mostly verb-based (remember, recall, forget). 'recent' is an adjective rather than a verb, which is a minor deviation from the otherwise consistent pattern.
Four tools is well-scoped for a lightweight memory server: save, search, list, and delete cover the core lifecycle without bloat. Each tool earns its place.
The surface covers create, search, list, and delete, with deduplication on re-save. A direct update-by-id operation is missing, but remember's refresh behavior and forget cover most practical workflows.
Related MCP Connectors
Persistent memory for AI agents. Search, store, and recall across sessions.
Persistent memory for AI agents. Search and store durable facts, preferences and decisions.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Universal memory for AI agents and tools. Save, organize and search context anywhere.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides AI coding assistants with persistent project memory to retain architectural decisions, code patterns, and domain knowledge across sessions. It stores data locally in a SQLite database, allowing agents to remember, recall, and manage project-specific context using full-text search.3 npmApache 2.0
- AlicenseNot gradedqualityCmaintenanceProvides long-term memory for LLMs via local SQLite storage with hybrid search (BM25, vectors, recency decay), enabling AI coding agents to persist and recall memories across sessions without cloud or API keys.52MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI coding agents to persist and retrieve project-scoped memories across sessions using local SQLite FTS5 keyword search.1MIT
- AlicenseAqualityBmaintenanceProvides AI agents with a persistent long-term memory over a single SQLite file, letting them write, screen, consolidate, and recall notes across sessions without any generative LLM in the loop. Recall judges relevance, follows links between notes, and signals when memory is insufficient, so agents get one to three useful facts per question instead of a generic top-k list.1184 PyPI4MIT