Graph-MIND
Your AI forgets everything when the session ends. This one remembers, and it never calls an LLM to do it.
88.8% on LongMemEval. Zero model tokens spent saving memory. Runs on your own PC.
Decide something with one agent on Monday. Ask another on Wednesday. It knows.
English · 한국어
Install
Windows: download Graph-MIND-Setup.cmd and double-click it, or in PowerShell:
irm https://raw.githubusercontent.com/goyohan0611-png/graph-mind/main/scripts/install.ps1 | iex
macOS / Linux:
curl -LsSf https://raw.githubusercontent.com/goyohan0611-png/graph-mind/main/scripts/install.sh | sh
No Python needed; nothing else to set up. Restart your AI apps afterwards. Already have Python?
pip install graph-mind-memory && graph-mind-install. More: docs/install.md.
Connecting an MCP client by hand
After pip install graph-mind-memory:
{
"mcpServers": {
"graph-mind-memory": {
"command": "python",
"args": ["-m", "graph_mind.mcp_server"]
}
}
}
Claude Code: claude mcp add graph-mind-memory -- python -m graph_mind.mcp_server. This gives the
tools only; graph-mind-install also saves every conversation automatically.
Try it
Work as usual for a while, then open a new session, another app, or another model and ask:
- "Where did we leave off yesterday?"
- "Which database did we pick for the billing service, and why?"
- "What did you change in the auth middleware last week?"
- "What's my dog's name?" (any fact you mentioned once, in passing)
Nothing to tag or save by hand: every turn is already stored, and the agent pulls back the few that answer the question.
What it does
- One shared brain for every agent in your terminal. Whichever coding agent or model you run, they all read and write the same memory. Switch agents or models; the memory stays.
- Remembers conversations word for word, on your own PC. Saving is a database write: no model call, no tokens. When a question depends on the past, the agent gets back the few thousand tokens that answer it. Korean and English.
- One memory across your PCs. Run
graph-mind folder share, thengraph-mind folder <code>on the other PC (the AI tells you the command; it never moves your memory by itself, so a web page cannot either). Office network or Tailscale, over TLS, every line encrypted before it leaves a PC. - Yours. No account, no cloud of its own, no telemetry. Secrets are masked before anything is stored, and "delete the password I typed earlier" deletes it everywhere. docs/privacy.md
- Teams, if you want them. Share a project's decisions and progress with teammates' AIs, never your personal memory; files stay in Slack and GitHub. docs/teams.md
Works with
The installer finds these and connects them; run it again after installing a new one.
| app | conversations saved | how |
|---|---|---|
| Claude Code | every turn | reads its transcripts |
| Codex CLI | every turn | reads its transcripts |
| Cursor | every turn | reads its transcripts |
| Copilot CLI | every turn | reads its transcripts |
| Claude Desktop (Cowork) | every turn | reads its session files |
| Gemini CLI | every turn | hooks; also adds relevant memory before each answer |
| OpenCode | every turn | plugin; also adds relevant memory before each answer, for any model |
| Claude Desktop chat, Windsurf, VS Code Copilot, Cline, LM Studio | what the model saves | MCP tools |
Any other MCP client works through the tools: see the hand-written config above.
How it works
flowchart LR
A["Claude Code · Codex · Cursor<br/>Gemini CLI · OpenCode · ..."] -- "transcripts, hooks, plugin" --> C["capture service<br/>(runs in the background)"]
C -- "verbatim turns,<br/>secrets masked" --> S[("your memory<br/>on this PC")]
S --> I["local search<br/>words + meaning + time"]
A -- "a question that needs the past" --> I
I -- "the few turns that answer it<br/>(~3k tokens)" --> A
- Saving costs nothing. Turns are stored as they were said. No model summarises or extracts anything at write time, so nothing is lost or invented on the way in, and no tokens are spent.
- Search runs on your PC. Word search, a multilingual embedding model (mpnet, int8; ONNX, no GPU) and when things were said are combined; the agent gets a short packet with the source turns, not a dump of history.
- The model you already use does the thinking. Graph-MIND hands it evidence; it answers. When models get better, the answers get better without changing the memory.
Does it work?
LongMemEval is the public benchmark for long-term chat memory: 500 questions over about 50 past sessions each. Every system below got the same answer model (gpt-5-mini), the same prompt and the official gpt-4o judge; only the memory differs.
| accuracy | model tokens spent saving memory | text the answer model reads | |
|---|---|---|---|
| Graph-MIND | 88.8% (all 500) | 0 | 3.4k tokens |
| agentmemory | 80.4% (same 499) | — | ~16.5k tokens |
| MemPalace 3.10.0 | 57.5% (40 questions) | 0 | — |
| Mem0 2.2.1 (open source) | 52.5% (40 questions) | ~640,000 per question | — |
On agentmemory's 499 Graph-MIND scored 89.0%; on the 40, 85.0%. Retrieval alone, on agentmemory's own measure (an answer session among the first 5 retrieved): Graph-MIND 98.5%, agentmemory 95.2%. These runs used the embedding model of 0.9.9 and before; on a 100-question sample the current one finds the answer session as often or more (among the first 5: 99.0% against 97.9%).
Every question, answer and verdict is in research/runs/; method, failures and
how to rerun it: docs/benchmarks.md.
FAQ
Will it slow my PC down? The background service uses about 2% of one CPU core when nothing new is coming in and about 650 MB of memory, most of it the search model. A memory search takes about 20 ms (41 ms at the 95th percentile on a GitHub runner); the first one after an app starts, about 1.3 s. After an update that changes the search model, it reads the memory again once, at half pace (about an hour for 11,000 pieces).
What does it cost? Nothing. No API key and no model calls of its own; your AI app reads a packet of about 3k tokens when a question needs the past.
Does anything leave my PC? No, unless you share the memory with your own other PCs or a team. No telemetry. Secrets (API keys, passwords, card numbers...) are masked before storing.
How is this different from CLAUDE.md or an app's built-in memory? Those keep notes a model wrote, one app at a time. Graph-MIND keeps every turn as it was said and shares it across every app and model on the PC.
Korean? Yes: Korean and English conversations, and questions in either language. A Korean question about something said only in English is found most of the time, not always.
How do I remove it? graph-mind-uninstall disconnects every app and stops the service; the
memory stays in ~/.graph-mind unless you add --purge.
More
MCP tools · See your memory in 3D
(graph-mind-view) · Changelog · Security ·
Development: pip install -r requirements.txt, then python -m unittest discover -s tests
Contributions are welcome under the CLA. License: AGPL-3.0; a commercial license is available for products that cannot publish their changes.
1 maintainer
Metadata
1 maintainer
Release files for graph-mind-memory 0.9.13
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| graph_mind_memory-0.9.13.tar.gz | 201.4 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| graph_mind_memory-0.9.13-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 365.9 kB
Release files / graph_mind_memory-0.9.13.tar.gz
| Download URL | graph_mind_memory-0.9.13.tar.gz |
|---|---|
| Size | 201.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
de5b4a910e5c1a575ff75a3c43e87180bfe9b4c5df58ecf4dab669cd9610ff07
|
|
BLAKE2b-256 checksum How to use checksums |
8bf5a65aafc170e7092cc630ac551f9d1831ffa1659f92cfeb1a3839add7d077
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logRelease files / graph_mind_memory-0.9.13-py3-none-any.whl
| Download URL | graph_mind_memory-0.9.13-py3-none-any.whl |
|---|---|
| Size | 164.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
35dfdcbf74f8c5b435f7ef962af10c25cd193e97d324cacf515462866f5fc2dd
|
|
BLAKE2b-256 checksum How to use checksums |
8a5ce3ab5c4761556dd12c25cd9bf891dc42917b8da500aa884555faea579494
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logSecurity for graph-mind-memory 0.9.13
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for graph_mind_memory-0.9.13.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 20, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
