Memtether

io.github.lanbass869-cellv0.1.0a16Updated Oct 3, 2026

Cross-client AI memory hub: agents share one SQLite memory.db via file-level pointers.

VerifiedSTDIODesktop onlyDatabasesKnowledge & Memory

Overview

AI-generated overview

Gives an assistant a shared local SQLite memory store so multiple AI clients can read and write the same memories.

What it does
MemTether is a local memory hub that keeps memories in one SQLite file (memory.db) that many AI clients point at. It supports remembering, searching, correcting and retiring memories, with multi-path recall combining vector search, FTS5 full-text, literal matching and an entity graph. It adds source attribution, bi-temporal as-of queries, supersession instead of deletion, usage-based ranking, and optional projection of a MEMORY.md file for context injection.
When to use it
Use it when you work across several AI coding clients and want context to carry over instead of being lost on each switch. It suits users who want memory kept entirely on their own machine rather than in a cloud service.
Requirements
Runs as a local process installed from PyPI (pip install memtether) or from source, with optional extras for semantic search and a REST server. It needs Python and a local SQLite database file; optional environment variables MEM_DB and MEM_DEFAULT_SOURCE override the database path and default source attribution. No account or API key is declared.
Before you install
It writes to and reads from a local memory database shared by many clients, so memories recorded by one client become visible to the others. The connect command modifies client configuration files, and the README notes some deep customizations cannot be safely rewritten, so preview changes first. Semantic search requires optional dependencies and degrades to keyword search without them.

Installation

In SourceWeft

  1. Open Memtether in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Quick Start

mcp-name: io.github.lanbass869-cell/memtether

bash
# 1. Installpip install memtether
# 2. Initialize (creates a demo memory DB)memtether init
# 3. Connect all detected AI clients (Claude Code, Cursor, Windsurf, etc.)memtether connect --all

Try it:

bash
memtether search "shared memory"memtether remember "my first shared memory"memtether stats

Or on Windows, double-click install.bat for one-click setup.

More install options
bash
# From sourcegit clone https://github.com/MemTether/MemTether.git && cd MemTether && pip install -e .
# With semantic search (local embedding, no cloud)pip install "memtether[vector]"
# With REST API serverpip install "memtether[server]"
# Dockerdocker build -t memtether . && docker run -p 8420:8420 -v ./data:/app/data memtetherdocker-compose up

Try it without installing:

bash
python scripts/make_demo_db.pyMEM_DB=~/.memtether/demo.db python mem.py search "shared memory"

Why MemTether

The problem

You use Claude Code for coding, Cursor for refactoring, and Windsurf for exploration. Each has its own memory. Switch tools and your AI forgets everything.

MemTether's answer is simpler than you'd expect: make them all point to the same file.

How it is different

Common approachProblemMemTether approach
Per-client memorySwitch tools, lose contextFile-level pointer: all clients read/write same memory.db
Cloud-hosted memoryPrivacy + API fees + downtimeLocal-first: SQLite on your machine, zero cloud
Delete old memoriesCannot trace what was knownSupersession: old memories marked, never deleted
Single time axisCannot distinguish when true vs when learnedBi-temporal: dual T/T-prime axes with as-of queries
Equal treatment of memoriesUseful memories get buriedQ-Value: used memories rank higher
Single search pathMisses keyword matches4-path recall: vector + FTS5 + literal + entity graph
No concurrent protectionSimultaneous writes = data lossHubguard: file lock + atomic write

Feature comparison

FeatureMemTethermem0cogneezep
Local-firstYesNo (cloud)YesNo (cloud)
Cross-client sharedYes (23)NoNoNo
Source attributionYesNoNoYes
Bi-temporalYesNoNoYes
Q-Value rankingYesNoNoNo
SupersessionYesNoNoYes
4-factor re-rankingYesNoNoNo
ScaffoldsYesNoNoNo
MCP serverYesYesYesYes
Eval suite includedYesYesNoNo
No API key neededYesNoNoNo
REST APIYesYesYesYes
DockerYesYesYesYes
Full feature list
  • Cross-client shared memory: 23 adapters (Claude Code, Cursor, Windsurf, VS Code, Zed, JetBrains, Cline, Roo Code, Kilo Code, Continue, Cody, Amazon Q, Gemini CLI, Neovim, Claude Desktop, Codex, WorkBuddy CN/Intl, CodeBuddy, ZCode, DSH, OpenClaw, Agents-Neutral)
  • Source attribution: every memory knows which client wrote it
  • Bi-temporal: T (when true) + T-prime (when recorded), as-of queries
  • Supersession: old memories marked superseded, never deleted, full audit trail
  • Q-Value: usage-based ranking (0.3 + 0.7 x q_value multiplier)
  • 4-factor re-ranking: semantic (0.45) + recency (0.25) + frequency (0.05) + importance (0.10), blended 70/30 with RRF
  • Deterministic scaffolds: counting/temporal/comparison/aggregation prepended to top result
  • Consolidation index: 2708 topics + 315 chains + 37 standing instructions as bonus recall
  • FTS5 triggers: SQLite-level full-text sync (INSERT/DELETE/UPDATE triggers)
  • Hubguard: cross-process concurrent write lock + atomic write + format fallback
  • Conflict detection: 89 quantified conflict patterns
  • LLM auto-extraction: extract structured memories from conversation text
  • Projection: auto-generates MEMORY.md (3980 char budget) for context injection
  • Multi-path search: vector + FTS5 BM25 + literal + entity graph PPR, RRF fused
  • Three-layer dedup: supersession-aware, content exact, tag-signature
  • Low-confidence rejection: marks results when keyword empty AND vector < 0.50
  • TTL expiry: expired conclusions downweighted with annotation
  • Self-reference suppression: meta-discussion ranked below answers

Architecture

+---------+   +---------+   +---------+   +---------+|  Claude |   | Cursor  |   |Windsurf |   | VS Code |  ... 23 adapters|  Code   |   |         |   |         |   |         |+----+----+   +----+----+   +----+----+   +----+----+     |              |              |              |     +--------------+------+-------+--------------+                          |                   +------v------+                   |  MemTether  |                   | Memory Hub  |                   |             |                   | SQLite      |  <- one physical memory.db                   | FTS5        |  <- full-text search (triggers)                   | ChromaDB    |  <- vector search (bge-m3)                   | Bi-temporal |  <- T + T-prime dual time axes                   | Q-Value     |  <- usage-based ranking                   | Hubguard    |  <- concurrent write lock                   +-------------+
Tech stack
ComponentTechnologyPurpose
DatabaseSQLite (WAL mode)Single-file, zero-config
Full-textFTS5 trigram + triggersO(1) BM25, SQL-level sync
VectorChromaDB + bge-m3 (1024-dim)Semantic search, local
FusionReciprocal Rank Fusion (K=60)Merge multi-path results
Re-ranking4-factor (sem .45 + rec .25 + freq .05 + imp .10)Z-score + sigmoid
GovernanceSupersession + bi-temporal + conflictNever delete
ConcurrencyHubguard (file lock + atomic write)Cross-process safe
APIFastAPI REST + MCP serverAny language

Connect Your Clients

bash
python -m memtether connect --allpython -m memtether verifypython -m memtether detectpython -m memtether selftest

Supported (23): Claude Code, Cursor, Windsurf, VS Code, Zed, JetBrains, Cline, Roo Code, Kilo Code, Continue, Cody, Amazon Q, Gemini CLI, Neovim, Claude Desktop, Codex, WorkBuddy (CN + Intl), CodeBuddy, ZCode, DSH, OpenClaw, Agents-Neutral

Memory Operations

bash
python -m memtether remember "User prefers dark theme" --source claude-codepython -m memtether search "theme preference"python -m memtether correct <uid> "Updated text"python -m memtether retire <uid> "No longer relevant"python -m memtether statspython -m memtether as-of 2026-09-15 --kind knownpython -m memtether rebuild

Benchmarks

LongMemEval (500 questions, full run, 2026-10-02)

MetricScoreNotes
Strict match (global)62.6%209/334 applicable
LLM judge (global)54.6%263/482
Multi-session strict48.8%Above industry avg 27.9%
Multi-session LLM judge60.0%
E-Hybrid73.3%11/15 (small sample)
Per-type breakdown
TypenStrictLLM Judge
knowledge-update7876.6%64.4%
multi-session13348.8%58.4%
single-session-assistant5640.4%42.9%
single-session-preference30N/A33.3%
single-session-user7086.4%80.0%
temporal-reasoning13360.7%41.4%

Results use our own harness. Not directly comparable with mem0 reported numbers.

Test suite

TestResult
hard_bench62/62
asset_bench23/23
pytest31/31
e2e_verify13/13
refuse_bench26/26
concurrent_stress4/4 PASS

Known Limitations

  1. tether_connect detect may falsely report "not connected" for same-source-different-path configs. Use verify for accurate results.
  2. DSH cordis.patch.yml deep customizations cannot be safely rewritten. Use plan to preview.
  3. memory_hub (production) and memtether (open source) are two copies. Changes need directional sync.
  4. Semantic search requires optional deps (chromadb, onnxruntime). Without them, degrades to keyword search.
  5. Windows-first. macOS/Linux should work but not fully tested.

Relationship to Other Projects

  • mem0: managed memory with cloud API. MemTether is for people who want everything local.
  • cognee: knowledge graph + pipeline. MemTether is lightweight operational memory (SQLite, no Neo4j).
  • letta (MemGPT): agent framework. MemTether works with existing agents you already use.
  • engram: Go + SQLite + FTS5 + MCP. MemTether adds bi-temporal, source attribution, Q-Value, 23 adapters.

You can use MemTether alongside any of these.

License

Apache 2.0 - see LICENSE

Contributing

Issues and PRs welcome. See CONTRIBUTING.md.

Star History

[Star History Chart]

中文文档 | Security | Changelog

Source: README.md at commit 3852976

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.1.0a16LatestOct 3, 2026