muster-memory 0.1.0__tar.gz

muster_memory-0.1.0/.gitignore

@@ -0,0 +1,55 @@
+# credentials: never committed
+.keys.sh
+*.key
+*.pem
+.env
+.env.*
+*token*
+*secret*
+
+# benchmark data is fetched, never committed (root-level only: harness/beam/ holds the BEAM parquet builders)
+/data/
+/beam/
+*.parquet
+harness/buildtime_rtx/data/
+
+# run outputs, caches, ledgers
+results/
+bundle_out/
+cost_ledger/
+ce_cache*/
+extract_cache*/
+wts_cache/
+logs*/
+*.log
+*.jsonl.bak*
+
+# environments and build artifacts
+.venv/
+__pycache__/
+*.pyc
+.DS_Store
+
+# local notes
+private/
+
+# local tool settings
+CLAUDE.md
+.claude/
+
+# local page reviews
+docs/review/
+
+# local page drafts
+docs/index_*.html
+
+# benchmark repositories fetched by scripts/fetch_mab_repo.sh and scripts/fetch_beam_repo.sh: never committed
+harness/mab_repo/
+harness/beam/BEAM/
+
+# library build artifacts and stores the examples create
+dist/
+build/
+*.egg-info/
+*.muster
+*.muster.scores

muster_memory-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+

muster_memory-0.1.0/NOTICE

@@ -0,0 +1,6 @@
+MUSTER
+Copyright 2026 The MUSTER authors
+
+This product includes software developed by the MUSTER authors.
+The benchmarks it is evaluated on, the models it downloads and the systems it is compared with keep their own licences
+and are not redistributed here.

muster_memory-0.1.0/PKG-INFO

@@ -0,0 +1,203 @@
+Metadata-Version: 2.5
+Name: muster-memory
+Version: 0.1.0
+Summary: MUSTER: lossless long-term memory for agents, set by its own text, with no LLM calls to build or grow it
+Project-URL: Homepage, https://saintmachines.github.io/MUSTER/
+Project-URL: Repository, https://github.com/saintmachines/MUSTER
+Project-URL: Documentation, https://github.com/saintmachines/MUSTER/blob/main/docs/library/README.md
+Project-URL: Issues, https://github.com/saintmachines/MUSTER/issues
+Author: SAINT Machines
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: tiktoken>=0.7
+Provides-Extra: agents
+Requires-Dist: openai-agents<0.25,>=0.24; extra == 'agents'
+Provides-Extra: dev
+Requires-Dist: build; extra == 'dev'
+Requires-Dist: hatchling; extra == 'dev'
+Requires-Dist: hypothesis; extra == 'dev'
+Requires-Dist: pytest; extra == 'dev'
+Provides-Extra: langchain
+Requires-Dist: langchain-core<2,>=1.6; extra == 'langchain'
+Provides-Extra: langgraph
+Requires-Dist: langgraph<2,>=1.2; extra == 'langgraph'
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.2; extra == 'mcp'
+Provides-Extra: models
+Requires-Dist: nltk>=3.9.1; extra == 'models'
+Requires-Dist: numpy>=1.26; extra == 'models'
+Requires-Dist: rank-bm25==0.2.2; extra == 'models'
+Requires-Dist: sentence-transformers<6,>=5; extra == 'models'
+Requires-Dist: torch>=2.3; extra == 'models'
+Requires-Dist: transformers; extra == 'models'
+Provides-Extra: parquet
+Requires-Dist: pandas; extra == 'parquet'
+Requires-Dist: pyarrow; extra == 'parquet'
+Description-Content-Type: text/markdown
+
+# MUSTER memory library
+
+Long-term memory for agents that keeps every word. It reads its own text to decide how to cut, group and search it,
+and it makes no LLM call to build or grow the memory. This package is the method of the MUSTER paper as a library:
+the paper's runs are reproduced by it, question by question (see [Verification](#verification)).
+
+## Install
+
+Install `muster-memory` from PyPI. The basic install provides structure inspection.
+The commands below add local retrieval models and the optional MCP server.
+
+```bash
+pip install "muster-memory[models]"        # build, add and search (bge-m3 and bge-reranker-v2-m3, run locally)
+pip install "muster-memory[models,mcp]"    # also the MCP server
+muster fetch                                  # optional: tokenizer and sentence-splitter files for offline use
+```
+
+`pip install muster-memory` alone gives `muster derive` and `muster.derive()`, which need only `tiktoken`. The
+package imports as `muster`; `pip install muster` (without `-memory`) installs an unrelated 2017 project.
+The paper's harness and the tests run from a clone of the repository.
+
+```bash
+git clone https://github.com/saintmachines/MUSTER.git
+cd MUSTER
+pip install ".[models,mcp]"
+```
+
+## Try it on a file
+
+```bash
+muster query chat.jsonl "Where does Caroline live now?" --explain     # one JSON record per line, or a .txt file
+```
+
+## Use it in three lines
+
+```python
+import muster
+
+mem = muster.build([
+    {"speaker": "Caroline", "time": "2023-05-08", "text": "I moved to Lisbon last month for the new job."},
+    {"speaker": "Melanie",  "time": "2023-05-08", "text": "How do you like the city so far?"},
+    # ... thousands more
+])
+print(mem.context("Where does Caroline live now?").text)    # what your LLM reads, verbatim and grouped
+```
+
+`muster.build` derives the plan from the text: a numbered log (most lines start with `12. `), a record store (most of
+the text sits in short blank-line records, like a chat) or prose (books, documents). `print(muster.explain(mem.plan))`
+shows the decision and why. Nothing is tuned per dataset.
+
+The numbered branch reads a serial written in the log's own style (`Step 12: ...`, `#12 ...`, `(12) ...`) the same way as
+the paper's `12. ...`. It applies when 95% of the lines after the first carry a serial one above the previous line's and
+the median line is at most 20 tokens, and the reader sees each line as written. The check was added after the paper and
+its two thresholds were set on public benchmark logs; the paper's presets and `derive_collection` do not use it.
+
+## A memory that grows: `Store`
+
+```python
+store = muster.Store.open("agent.muster")                     # one SQLite file
+store.add({"speaker": "user", "text": "My daughter's name is Ana.", "time": "2026-10-20T09:12"})
+store.add(messages, request_id="turn-41")                     # a retried request is applied once
+ctx = store.context("What is my daughter's name?")
+```
+
+`add` writes records in one transaction and calls no model, so it is safe on a hot path. The next search builds the
+new version exactly as a fresh build of all records would be (tested), embedding only texts it has not seen before.
+Cached unit vectors and reranker scores survive restarts; new queries still run retrieval models.
+
+## Connect it
+
+**MCP** (Claude Desktop, Claude Code, Cursor, any MCP client):
+
+```bash
+muster mcp --store agent.muster
+```
+```json
+{"mcpServers": {"muster": {"command": "muster", "args": ["mcp", "--store", "/path/to/agent.muster"]}}}
+```
+Tools: `remember`, `remember_many`, `recall`, `search_memory`, `memory_info`.
+
+**HTTP** (any app, service or robot):
+
+```bash
+muster http --store agent.muster --port 8765
+curl -s localhost:8765/v1/add -d '{"records":[{"speaker":"robot","text":"Red mug on the kitchen table","time":"2026-10-20T10:02"}]}'
+curl -s localhost:8765/v1/context -d '{"query":"Where did I last see the red mug?"}'
+```
+
+**Python agents**: `Store.context(q).text` is a string; put it in the prompt. `ctx.messages(question)` builds a chat
+message list; `ctx.blocks` gives the groups with the ids of the passages in each.
+
+Examples: [examples/][examples] (agent loop, robot observation log, MCP client configuration, ROS 2 node).
+Reference: [api.md][api]. Checking it against the paper: [verify.md][verify], [exact.md][exact].
+
+## How it works, in one paragraph
+
+Units are the store's own records, packed up to a token budget (512 tokens for record stores, 1,024 for prose) and
+never split mid-record. Parents group about eight neighbouring units. A query is matched three ways: meaning (bge-m3),
+keywords (BM25) and an entity graph over parents. The read budget (`U` units, 10 by default, 40 for prose) is split
+between the three by reserved floors (4/3/3 per ten), so each signal always contributes; candidates are ordered by a
+cross-encoder. Selected units are shown verbatim, one block per parent, in stored order. On numbered logs the newest
+version of a slot replaces older ones.
+
+## Two modes
+
+- **native** (default): everything above, deterministic for given inputs and versions, with no hash seed and no pinned
+  environment. Use this in applications.
+- **exact**: the paper's harness, step for step, under one of nine presets (`muster presets`), for example
+  `muster.build(text, "beam.u20")`. Set sets are iterated as the harness iterated them, so it must run under
+  `PYTHONHASHSEED=0` with the gate's package versions. Use this to check a paper number.
+
+With the same plan, native mode departs from exact mode only where the harness's choice depended on hash or hardware order: canonical
+iteration over entity sets, and a stable sort for exact dense-score ties.
+
+Automatically derived non-numbered plans use the balanced method with immediate sibling candidates (`flrs`).
+The frozen paper presets retain each published run's policy, including `flr` where it was recorded; explicit or
+JSON-restored plans are not migrated. See [exact.md][exact] when choosing between automatic planning and replay.
+
+## Verification
+
+The library is checked against the paper's harness and its published outputs on the paper's data, CPU only, with no
+API call ([exact.md][exact] has every check, its script and its count). In short:
+
+| Check | Equal |
+|---|---|
+| Cut of every row of the 24 final legs vs the harness | 296 of 296 rows |
+| Render chain of the MemoryAgentBench board from the published dumps | 5,439 of 5,439 questions |
+| BEAM-100K search and R4 context vs the harness replay | 800 of 800 questions |
+| Other cells replayed, context = the published one | 6,753 of 6,753 questions |
+
+## Optional declared record input
+
+An experimental [declared record mode](https://github.com/saintmachines/MUSTER/blob/main/docs/library/declared-records.md) connects explicit
+source boundaries and order metadata to the SDK, CLI and an opt-in HTTP endpoint.
+It keeps all versions and does not change the default or paper replay paths.
+
+For a producer-declared record array, `record_format="serial"` reversibly reads prefixes such as
+`Step 12: ...`, `#12 ...`, `(12) ...`, `[12] ...`, or `12. ...` using the leading-serial lexer (the integer must end
+within the first 32 code points). Pass `declared_order=SourceOrder(...)` to `muster.build`, or use `"format": "serial"`
+in the declared-record CLI/HTTP envelope. Prefixes and metadata remain in `mem.ordered_records.roundtrip()`; the body
+is what retrieval and the reader receive. This explicit codec does not require the automatic detector's 95%/20-token
+conditions. Gaps, resets and repeated markers do not sort or delete records: declared source order and all versions
+are preserved, with supersession off. The existing `step` and `integer_dot` codecs remain strict and unchanged.
+
+For a record array or `Store`, automatic serial detection reads only the start of each record's `text`/`content`.
+An ID, time, or speaker field never supplies a serial. A literal body beginning `user: Step 1: ...` is not rewritten.
+Numbered records keep their serialized metadata in retrieval and reader text, while slots and revision order come
+from the body. Each record remains one unit. Multiline bodies are not split into invented records. Unmarked records
+keep their own occurrence and cannot enable structural replacement. Paper replay and valid, fully marked plain-text
+logs are unchanged. In native lead logs, an unmarked or out-of-bound line keeps its original position and has no
+inferred revision clock, and structural replacement is disabled.
+
+For structured records the continuity denominator is the original record pairs, including empty records as missing
+markers, and the length median counts each entire record body, including continuation lines. It does not scan for
+a serial in arbitrary words later in the body. Raw strings retain the existing line-based rule and thresholds.
+An unmarked record has no inferred revision clock. All-marked numbered inputs retain numeric serial display order,
+while an array containing unmarked records is displayed in original array order with structural replacement off.
+
+[examples]: https://github.com/saintmachines/MUSTER/tree/main/examples
+[api]: https://github.com/saintmachines/MUSTER/blob/main/docs/library/api.md
+[verify]: https://github.com/saintmachines/MUSTER/blob/main/docs/library/verify.md
+[exact]: https://github.com/saintmachines/MUSTER/blob/main/docs/library/exact.md