|
Download README.md from dasd1231/MIGRO: direct link, hf CLI and curl.
- Browser
- Download file 5.11 kB
-
https://huggingface.co/dasd1231/MIGRO/resolve/main/README.md
- Command line
-
hf download hf://dasd1231/MIGRO/README.md
-
curl -L -o README.md https://huggingface.co/dasd1231/MIGRO/resolve/main/README.md
5.11 kB
| license: apache-2.0 | |
| library_name: pytorch | |
| tags: | |
| - arxiv:2611.15315 | |
| - agent-memory | |
| - long-term-memory | |
| - persistent-memory | |
| - model-handoff | |
| - custom-code | |
| # MIGRO — Portable Long-Term Memory | |
| **Memory Should Outlive the Model.** | |
| MIGRO is a decoupled long-term memory system that stores experience in a persistent state, allowing successive language models to read inherited observations and continue writing. | |
| [Paper](https://arxiv.org/abs/2611.15315) · [Code](https://github.com/zOUMINGXI/MIGRO) · [Interactive demo](https://zoumingxi.github.io/MIGRO/) · [Runtime guide](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/runtime.md) | |
| ## Released components | |
| This repository hosts the shared runtime payload released with MIGRO, including its memory core, semantic-address components, coding tables, source tokenizers and frozen host interfaces. | |
| | Component | File or directory | Role | | |
| |---|---|---| | |
| | Shared core | research/rd_shared_pages_20261025/deployment/minimal_core.pt | Frozen semantic encoder, source embeddings and shared runtime tensors | | |
| | Semantic encoder configuration and tokenizer | research/rd_shared_pages_20261025/deployment/semantic_config/ and semantic_tokenizer/ | Configure semantic addressing | | |
| | Source tokenizer | research/rd_shared_pages_20261025/deployment/source_tokenizer/ | Interpret canonical source-token bindings | | |
| | Address and coding resources | research/rd_shared_pages_20261025/model/ and research/rd_semantic_factor_20261025/ | Reconstruct compact addresses and support persistence | | |
| | Phi interface | research/decomem_v1_20261028/frozen_interfaces/Phi_boundary.pt | Frozen host input interface | | |
| | Mistral interface | research/decomem_v1_20261028/frozen_interfaces/Mistral_cal64.pt | Frozen calibrated host input interface | | |
| The directory layout is compatible with MIGRO_ASSETS. ASSETS.json lists the payload files. The custom PyTorch modules are loaded through the MIGRO runtime. | |
| ## Download and use | |
| Install MIGRO from its source repository, following the [tested runtime dependencies](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/runtime.md). | |
| ~~~bash | |
| git clone https://github.com/zOUMINGXI/MIGRO.git | |
| cd MIGRO | |
| python -m pip install -e '.[runtime,benchmarks]' -c constraints/runtime-tested.txt | |
| python -m pip install huggingface_hub | |
| ~~~ | |
| Download the shared assets from this model repository: | |
| ~~~python | |
| from huggingface_hub import snapshot_download | |
| snapshot_download( | |
| repo_id="dasd1231/MIGRO", | |
| local_dir="./migro-assets", | |
| ) | |
| ~~~ | |
| Use the downloaded folder as the runtime asset root and compile the native coding kernels: | |
| ~~~bash | |
| export MIGRO_ASSETS="$PWD/migro-assets" | |
| python -m migro.backend.build_native | |
| python scripts/verify_runtime.py --assets-dir "$MIGRO_ASSETS" | |
| ~~~ | |
| For fresh answer generation, obtain the supported backbone and reranker models from their publishers, as described in the runtime guide. Then run a local session: | |
| ~~~bash | |
| MIGRO_DEVICE=cuda python demo/run.py --case demo/starter.json --output trace.json | |
| MIGRO_DEVICE=cuda python demo/serve.py --trace trace.json | |
| ~~~ | |
| The [demo guide](https://github.com/zOUMINGXI/MIGRO/blob/main/demo/README.md) describes replay, input editing and generating new answers. | |
| ## Intended use and evaluation | |
| These resources support MIGRO memory construction, persistence, host-interface reading and continued writing. Answer generation combines them with an external host language model and the runtime's retrieval components. | |
| The [technical report](https://arxiv.org/abs/2611.15315) evaluates the complete system on long-term question answering, cross-host transfer and persistent storage. [Evaluation details](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/evaluation.md) describe the settings, cohorts and baseline operations. Deployment behavior depends on the selected host, interface and retrieval budget. | |
| Host-interface weights are specific to their supported host configurations. The [runtime guide](https://github.com/zOUMINGXI/MIGRO/blob/main/docs/runtime.md) specifies required models and dependencies. | |
| ## Component sources and licenses | |
| MIGRO-owned components are released under Apache-2.0. The shared core includes frozen components from [BAAI/bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) under MIT and the input embeddings/tokenizer from [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) under Apache-2.0. Their notices and licenses accompany this repository. | |
| See LICENSE, NOTICE, THIRD_PARTY_NOTICES.md and PROVENANCE.json for the existing component attribution and source revisions. | |
| ## Citation | |
| ~~~bibtex | |
| @article{zou2026migro, | |
| title = {{MIGRO}: A Decoupled and Portable Long-Term Memory System for Language Models}, | |
| author = {Zou, Mingxi and Xu, Yinghui and Chen, Jiaxiang and Liang, Langzhang | |
| and Zhu, Wei and Ye, Peng and Zhao, Runkai and Jiang, Ruoxi | |
| and Chen, Sijin and Wang, Song and Wang, Zhuo and Qu, Lizhen | |
| and Xu, Zenglin}, | |
| year = {2026}, | |
| eprint = {2611.15315}, | |
| archivePrefix = {arXiv}, | |
| primaryClass = {cs.AI}, | |
| url = {https://arxiv.org/abs/2611.15315} | |
| } | |
| ~~~ | |