Rememb
Gives your AI agent a persistent memory layer backed by local JSON files, no server or API keys needed. Exposes MCP tools for reading, writing, and semantically searching structured entries across sections like project context, actions taken, system architecture, and user preferences. Ships with a local web UI for browsing and editing memory, runs over stdio or SSE transport, and uses SentenceTransformers for offline semantic search with configurable model unloading. The agent automatically loads context at session start and writes back learnings, so you stop re-explaining your stack and preferences every conversation. Reach for this when you want stateful sessions without cloud dependencies or when building agents that need to remember project-specific details across runs.
- GitHub stars
- 3
- tools
- 7
- transport
- STDIO
- last updated
- Apr 13, 2026
Tools
7 toolsPublic tool metadata for what this MCP can expose to an agent.
rememb_writeSaves a new memory entry.
Saves a new memory entry.
No parameter schema in public metadata yet.
rememb_editUpdates an existing memory entry without losing its history.
Updates an existing memory entry without losing its history.
No parameter schema in public metadata yet.
rememb_deleteSoft-deletes a memory entry.
Soft-deletes a memory entry.
No parameter schema in public metadata yet.
rememb_restoreRestores a previous version of a memory entry.
Restores a previous version of a memory entry.
No parameter schema in public metadata yet.
rememb_searchSearches memory entries by keyword and returns ids, scores, tags, dates and short excerpts.
Searches memory entries by keyword and returns ids, scores, tags, dates and short excerpts.
No parameter schema in public metadata yet.
rememb_getReturns the full body of a memory entry by id.
Returns the full body of a memory entry by id.
No parameter schema in public metadata yet.
rememb_readReads the full content of memory entries the agent picked.
Reads the full content of memory entries the agent picked.
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
Operate AI agents without losing context between sessions. rememb is local-first long-term memory: structured entries, keyword search, versioning, diff, restore, and audit trail — no cloud, no API keys.
The problem
Teams using agents at real velocity rarely fail because they lack generation. They fail because operating agents every day creates context debt:
- too much re-explaining project facts every session
- too little durable memory outside the chat window
- too little audit trail for why something changed
- too much noise when recalling the right context
Every team or solo developer operating agents professionally hits this wall:
Details
- Repository
- github.com/luizedupp/rememb
- Categories
- AI & LLM Tools, Data & Analytics
- Package
rememb- Transport
- STDIO
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Memori Mcpmemorilabs/memori-mcpMemori MCP server — persistent AI memory with recall and augmentation tools3stars
Mnemon Mcpnikitacometa/mnemon-mcpPersistent layered memory for AI agents. SQLite FTS5, fact versioning, zero-cloud.3stars
agentmemoxgeneral/agentmemLightweight persistent memory for AI agents. Hybrid search. 16 tools. One SQLite file.3stars
OCDS German Procurement Searchqune-tech/ocds-mcpSearch and match German public procurement tenders (OCDS) from your local LLM.3stars
Recallrecallworks/recallOpen-source MCP memory server. Persistent, searchable, tiered memory across sessions.3stars
Mcp Serverroamzy-io/mcp-serverAgent-native global eSIM: buy for 193 countries, per-MB in USDT/USDC. Agents earn 20% referral.0stars