LongMemory (formerly OpenMemory) MCP alternatives
LongMemory is the CaviraOSS project that was published as OpenMemory until recently, and it is a separate codebase from Mem0's OpenMemory. Each memory is classified into one of five sectors that decay at different rates, memories link through a waypoint graph, and a temporal knowledge graph holds facts with validity periods. The published MCP server has six tools over a local SQLite file, with a user_id on each call.
It is an interesting design for one assistant's long-term recall. Teams looking for memory their coding agents share, recorded without anyone calling store, should start with Glen.
The 9 best alternatives
- GlenOur pick
Team memory recorded from the work, not stored one call at a time
LongMemory stores what an assistant chooses to keep in one SQLite file. Glen records a team's sessions and tools automatically and shares them across the org with permissions per fact.
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 testsLongMemory (formerly OpenMemory)GlenWho writes memoryThe agent, via storeRecorded from every session and toolWho can read itOne SQLite file, split by user_idYour whole org, permissions per factWhat the agent getsMatching memoriesOne cited answer, injected in-sessionWhat you runA local npx processNothing: 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 →MemPalace keeps conversations and files verbatim, without summarizing, and files each piece into wings and rooms so a search can be scoped to one person or project; ChromaDB with local embeddings does retrieval, and a SQLite graph tracks facts with validity windows. Hooks for Claude Code, Codex and Cursor save sessions automatically. A palace lives on one machine unless you run your own HTTP hub, search returns raw drawers for the agent to read rather than an answer, and its 47 tool definitions sit in every session's context window.
Set up MemPalace →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 →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
LongMemory is worth a look if you want to experiment with decay-based memory for a single assistant. For a team's coding agents, Glen records the work automatically and shares it with permissions and citations. MCP Memory Service is the fuller self-hosted option; claude-mem and MemPalace record sessions locally; Mem0 and Supermemory are hosted memory APIs.
FAQ
- Is this OpenMemory the same as Mem0's OpenMemory?
- No. This is CaviraOSS's project, now named LongMemory. Mem0's OpenMemory was a different local MCP server, sunset in July 2026.
- What is the best OpenMemory alternative?
- For coding teams, Glen. For another self-hosted server with richer consolidation and conflict handling, MCP Memory Service.
- Does LongMemory share memory across a team?
- The published version separates users with a user_id in one database. Team and role identity exist on the repository's main branch but were not published to npm when we checked.