Memory Mcp Lite
A local-first memory layer that sits between your AI client and your filesystem, storing technical decisions, gotchas, and commands that should outlive a single session. Organizes everything in a global/project/task tree backed by SQLite with FTS5 search. Ships nine tools split across retrieval (get_global_summary, search_memory_light, get_memory_detail) and storage (remember_decision, remember_fact, upsert summaries). The retrieval discipline pushes agents through summaries first, then light search, then full detail for 1-3 hits only, keeping token burn low. Identifies projects by normalized git remote URL so memory survives directory moves. Works via npx with Windsurf, Cursor, and Claude Desktop. Point it at a local SQLite file or a remote Turso database.
- GitHub stars
- 2
- tools
- 9
- transport
- STDIO
- last updated
- Apr 19, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
get_global_summaryrecurring preferences, cross-project conventions
recurring preferences, cross-project conventions
No parameter schema in public metadata yet.
get_project_summaryarchitecture, key decisions, long-term project context
architecture, key decisions, long-term project context
No parameter schema in public metadata yet.
get_task_summaryresuming a specific piece of work
resuming a specific piece of work
No parameter schema in public metadata yet.
search_memory_lightsummaries aren't enough; you want compact candidates
summaries aren't enough; you want compact candidates
No parameter schema in public metadata yet.
get_memory_detailyou've picked a candidate and need the full body
you've picked a candidate and need the full body
No parameter schema in public metadata yet.
remember_decisionan architecture choice, trade-off, or rejected path
an architecture choice, trade-off, or rejected path
No parameter schema in public metadata yet.
remember_facta command, env note, gotcha, link, or convention
a command, env note, gotcha, link, or convention
No parameter schema in public metadata yet.
upsert_project_summaryafter an arch change or new convention worth recording
after an arch change or new convention worth recording
No parameter schema in public metadata yet.
upsert_task_summaryafter progress, blockers, or a plan change
after progress, blockers, or a plan change
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
memory-mcp-lite
A small, opinionated memory server for AI coding assistants (Windsurf, Cursor, Claude Desktop — anything that speaks MCP).
It runs locally, stores durable knowledge on your disk, and tries very hard to stay out of your agent's way until you actually need it.
Why this exists
Most AI clients already have some form of short-term memory. They remember the current conversation, maybe a few rules you've set, and that's about it. What they don't give you is a place to park things that should outlive the session — the architectural decision you made last week, the one weird build command for this repo, the gotcha that bit you three times in a row.
memory-mcp-lite is that place. It stores:
- technical decisions and the reasoning behind them,
- project architecture and conventions,
- commands, env notes, links, and gotchas,
- task state so you can resume work later,
- rolled-up summaries at the global / project / task level.
It deliberately does not store raw chat transcripts, replace your client's built-in rules, run embeddings or vector search, or need a server or cloud connection.
How it's organised
Memory lives in a tree:
Details
- Repository
- github.com/thuupx/memory-mcp-lite
- Category
- AI & LLM Tools
- Package
memory-mcp-lite- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Agent Mosaic Skillable-rip/agent-mosaic-skillConvert photos to LEGO-style brick mosaic previews with AI-powered color quantization.1stars
Impact Previewagent-polis/impact-previewImpact preview for AI agents - see what changes before any action executes.1stars
Agent Moduleagentmodule/mcpDeterministic compliance and vertical knowledge bases for autonomous agents. Free 24hr trial.0stars
AgentScrapehshintelligence/agent-scrapePay-per-call web scraping for AI agents via x402 on Base USDC. Six tools, no signup.1stars
Dingdawg Data Agentdingdawg/dingdawg-agent-1AI data agent — schema analysis, query optimization, PII detection, pipelines.0starsDingdawg Devops Agentdingdawg/dingdawg-agent-1DevOps AI. Deploy checks, incident analysis, infra audit. Learns from past failures.0stars