MemPalace MCP alternatives
MemPalace stores conversations and files verbatim, without summarizing them, and files each piece into a structure of wings and rooms so search can be scoped to one person or project. ChromaDB and local embeddings handle retrieval, a SQLite knowledge graph tracks facts with validity windows, and hooks for Claude Code, Codex and Cursor save sessions automatically. Its MCP server exposes 47 tools.
It records sessions without a save call, which puts it ahead of most memory servers, and it keeps them on one machine by default. Teams who want the same automatic recording shared across everyone's agents should start with Glen.
The 9 best alternatives
- GlenOur pick
Automatic session memory, shared and reconciled for a team
MemPalace records sessions automatically and keeps them verbatim on one machine. Glen records every teammate's sessions and tools into one hosted memory and returns a cited answer instead of raw drawers.
Recorded automaticallyClaude CodeCodexCursorSlackGitHubLinearNotionCall transcriptsOne memory for your orgSourced, permissioned per fact, newer decisions winEvery teammate's agentClaude CodeCodexCursorGets one cited answer, injected into the session before it goes looking.29%fewer tokens across 100 replayed PRs21%faster, measured end to endParity+quality on withheld testsMemPalaceGlenWho writes memoryRecorded by hooksRecorded from every session and toolWho can read itOne machine, or your own hubYour whole org, permissions per factWhat the agent getsVerbatim drawers to readOne cited answer, injected in-sessionWhat you runLocal Python and ChromaDBNothing: hosted, OAuth 2.1 The closest to Glen in mechanism: claude-mem records sessions through hooks in Claude Code, Codex, Cursor and others, compresses tool use into observations with an observer model, and injects context when a session starts. The difference is scope. Memory lives in SQLite on one machine, grouped by project, and TeamBrain, its sharing feature, was a pilot with no public pricing when we checked. It is good memory for one developer, and your teammates' agents never see any of it.
Set up claude-mem →Mem0 runs an LLM over whatever the agent passes to add_memory, extracts discrete memories, and returns them through semantic search from a hosted endpoint at mcp.mem0.ai. It is built for per-user memory inside an application: every memory hangs off a user_id, agent_id or run_id, nothing is written unless the agent decides to call add_memory, and search hands back matching memories rather than an answer with sources. The self-run mem0-mcp package is archived and Mem0's OpenMemory was sunset in July 2026, so the hosted server is the only maintained route.
Set up Mem0 →Cognee runs an LLM pipeline over what it is given, extracting entities and relationships into a knowledge graph beside vector embeddings, and recall picks among graph, RAG, temporal and Cypher strategies. It runs locally on SQLite, LanceDB and an embedded graph and needs your own LLM key. Each MCP client writes to its own dataset by default, so Claude Code and Cursor on one machine don't share memory unless you change COGNEE_MCP_AGENT_SCOPED, and nothing is stored until the agent calls remember.
Set up Cognee →Graphiti, the open-source library under Zep's commercial product, is the most careful about time of anything on this list: facts are graph edges with validity timestamps, and a newer episode that contradicts an older fact invalidates it. You run it yourself on FalkorDB or Neo4j with your own LLM and embedding keys, and the README calls the MCP server a reference implementation with no authentication, so anyone who reaches the port can read or clear the whole graph. Episodes still arrive only when the agent calls add_memory.
Set up Zep Graphiti →Supermemory's hosted server turns content the agent saves into documents, extracts memories from them asynchronously, and returns matches with a similarity score and the source document's ID. Spaces partition memory per project or user, and clients with MCP Apps support get a space picker and an interactive memory graph. Through this server, memory enters when the agent or the user calls a save tool, so what a space holds is whatever someone remembered to store.
Set up Supermemory →ByteRover keeps project knowledge as topic files in a .brv/context-tree directory inside the repository, with git-style branches and merges and optional cloud sync for a team. Its MCP server is deliberately small: brv-query runs BM25 over the tree and brv-curate saves a topic the agent wrote. Knowledge enters only when an agent or a person curates it, so the tree holds what someone chose to document, which is the AGENTS.md problem with better tooling.
Set up ByteRover →LongMemory, the CaviraOSS project published until recently as OpenMemory and unrelated to Mem0's product of that name, sorts memories into five sectors that decay at different rates and links them through a waypoint graph. It is six tools over a local SQLite file, with a user_id on each call to keep users apart. It records only what the agent chooses to store, and the team-aware rewrite on its main branch was not on npm when we checked.
Set up LongMemory (formerly OpenMemory) →Basic Memory writes memory as plain Markdown in a folder you choose, parses observations and wiki-link relations into a graph, and indexes it in SQLite for hybrid search. The files open in Obsidian and diff cleanly in git, and Basic Memory Cloud serves the same 17 tools over OAuth with shared workspaces. A note exists only when the agent calls bm_write or bm_edit, so the memory is exactly as complete as the agent's judgment about what was worth writing down.
Set up Basic Memory →
How to choose
MemPalace is a thoughtful free option for one person who wants verbatim, local session memory with fine-grained scoping. Glen is the option for teams: the same automatic recording, plus your team's tools, in one shared memory that returns cited, reconciled answers. claude-mem is MemPalace's closest peer; Mem0 and Supermemory are hosted memory APIs; Graphiti and Cognee are graph engines to self-host.
FAQ
- What is the best MemPalace alternative?
- For teams, Glen: it records sessions automatically like MemPalace does, but into one shared, hosted memory with per-observation access control. For another free local recorder, claude-mem.
- Can several people share a MemPalace palace?
- You can run a self-hosted hub over HTTP with a bearer token and point several clients at it. By default a palace lives on one machine.
- Why does the number of MCP tools matter?
- Every tool definition is loaded into the agent's context window. A server with dozens of tools spends tokens and attention on them in every session, before any memory is recalled.