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.
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.
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: decide something with one, ask another later, it knows. Switch agents or models; the memory stays. Which ones
- 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. Tell the AI "let my other PCs use this memory", paste the code it gives you to the AI on the other PC. 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
Does it work?
Same 40 questions, same answer model, same official judge, pre-registered before anyone looked:
| accuracy | model tokens spent saving memory | |
|---|---|---|
| Graph-MIND | 85.0% | 0 |
| MemPalace 3.10.0 | 57.5% | 0 |
| Mem0 2.2.1 (open source) | 52.5% | ~640,000 per question |
On all 500 LongMemEval questions: 88.8%. Against agentmemory on the same 499, its own published retrieval (95.2% R@5) handed to the same answer model and judge:
| accuracy | text the answer model reads, per question | |
|---|---|---|
| Graph-MIND | 89.0% | 3.4k tokens |
| agentmemory (its 5 sessions) | 80.4% | ~16.5k tokens |
Every question, answer and verdict is in research/runs/; method, failures and
how to rerun it: docs/benchmarks.md.
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 0.9.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| graph_mind_memory-0.9.5.tar.gz | 185.8 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| graph_mind_memory-0.9.5-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 339.9 kB
Release files / graph_mind_memory-0.9.5.tar.gz
| Download URL | graph_mind_memory-0.9.5.tar.gz |
|---|---|
| Size | 185.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b180484a404e03ef66bff61bbcaa58353535b89ac1fb583755742200a7969d12
|
|
BLAKE2b-256 checksum How to use checksums |
87b85eefa55503f3ef5979936e26ff6fff0436c3091cecfce2bfd5474d72c176
|
| 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 19, 2026.
Transparency logRelease files / graph_mind_memory-0.9.5-py3-none-any.whl
| Download URL | graph_mind_memory-0.9.5-py3-none-any.whl |
|---|---|
| Size | 154.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
bb6f5f4366484952fb457d0ab45632c08e611b740ddf104adec04ed95703ab74
|
|
BLAKE2b-256 checksum How to use checksums |
1a76099ac4467e8341d25b100df3d57095df354a55bd7982d131f789a22b63ba
|
| 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 19, 2026.
Transparency log
