memahead 0.1.0__tar.gz

memahead-0.1.0/.env.example

@@ -0,0 +1,8 @@
+# Copy to .env and fill in your values. .env is gitignored.
+# Get a PyPI token: https://pypi.org/manage/account/token/
+
+TWINE_USERNAME=__token__
+TWINE_PASSWORD=pypi-your-token-here
+
+# Optional: upload to TestPyPI first
+# TWINE_REPOSITORY_URL=https://test.pypi.org/legacy/

memahead-0.1.0/.gitignore

@@ -0,0 +1,70 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Environments
+.env
+.pypirc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Editors / IDEs
+.idea/
+.vscode/
+*.swp
+*.swo
+.DS_Store
+
+# Type checkers / linters
+.mypy_cache/
+.dmypy.json
+dmypy.json
+.ruff_cache/
+.pyright/
+
+# Model / embedding caches
+.cache/
+*.pt
+*.bin

memahead-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 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 2026 memahead contributors
+
+   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.

memahead-0.1.0/NOTICE

@@ -0,0 +1,49 @@
+memahead
+Copyright 2026 memahead contributors
+
+This product includes software developed by the memahead contributors,
+licensed under the Apache License, Version 2.0.
+
+------------------------------------------------------------------------
+Academic foundations
+------------------------------------------------------------------------
+
+memahead productizes findings from the following research. memahead is an
+independent implementation and is not affiliated with, endorsed by, or
+released by the authors of these works. All credit for the underlying
+ideas belongs to the respective authors.
+
+1. PAACE: Plan-Aware Agent Context Engineering
+   Yuksel et al., December 2025
+   arXiv:2512.16970
+   https://arxiv.org/abs/2512.16970
+
+   memahead's forward-looking retention scoring — scoring each context
+   chunk against the *remaining* steps of a plan rather than greedily
+   against past history — is inspired by the plan-aware compression
+   approach described in this paper.
+
+2. ACON: Agent Context Optimization
+   Kang et al., Microsoft, 2025
+   arXiv:2510.00615
+   https://arxiv.org/abs/2510.00615
+
+   memahead's chunk-level retention and tool-schema filtering draw on
+   the context optimization techniques described in this paper.
+
+------------------------------------------------------------------------
+Third-party dependencies
+------------------------------------------------------------------------
+
+memahead builds on top of, and gives full credit to:
+
+- Headroom (headroom-ai), Apache-2.0
+  https://pypi.org/project/headroom-ai/
+  Headroom performs the underlying compression mechanics. memahead adds
+  a plan-aware retention scoring layer on top of it.
+
+- sentence-transformers, Apache-2.0
+  https://www.sbert.net/
+
+- NumPy, BSD-3-Clause
+  https://numpy.org/

memahead-0.1.0/PKG-INFO

@@ -0,0 +1,147 @@
+Metadata-Version: 2.4
+Name: memahead
+Version: 0.1.0
+Summary: Agent memory optimized for what's ahead: plan-aware, forward-looking context compression for LLM agents.
+Project-URL: Homepage, https://github.com/memahead/memahead
+Project-URL: Repository, https://github.com/memahead/memahead
+Project-URL: Issues, https://github.com/memahead/memahead/issues
+Author: memahead contributors
+License: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: agent,compression,context,headroom,llm,memory,plan,retention,tokens
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Requires-Dist: headroom-ai>=0.5
+Requires-Dist: numpy>=1.23
+Requires-Dist: sentence-transformers>=2.2
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Requires-Dist: tiktoken>=0.5; extra == 'dev'
+Provides-Extra: tokenizers
+Requires-Dist: tiktoken>=0.5; extra == 'tokenizers'
+Description-Content-Type: text/markdown
+
+# memahead
+
+**Agent memory optimized for what's ahead.**
+
+memahead compresses an LLM agent's context at *each step* of a multi-step
+workflow using forward-looking, plan-aware retention. Unlike tools that
+compress greedily based on what already happened, memahead scores every chunk
+of context against the **remaining steps in the plan** and drops what future
+steps won't need — dramatically fewer tokens per agent call, without losing the
+information that matters downstream.
+
+memahead sits on top of [Headroom](https://pypi.org/project/headroom-ai/)
+(`pip install headroom-ai`), which performs the underlying compression
+mechanics. memahead adds the plan-aware retention scoring layer.
+
+## Install
+
+```bash
+pip install memahead
+```
+
+This pulls in `headroom-ai`, `sentence-transformers`, and `numpy`. For more
+accurate token accounting, also install the optional extra:
+
+```bash
+pip install "memahead[tokenizers]"   # adds tiktoken
+```
+
+## Quick example
+
+```python
+from memahead import Plan, Step, PlanAwareCompressor
+
+plan = Plan([
+    Step("research", "Search and gather raw facts about the topic"),
+    Step("synthesize", "Identify key themes across the research"),
+    Step("draft", "Write a structured first draft"),
+    Step("revise", "Produce the final polished output"),
+])
+
+compressor = PlanAwareCompressor(quality=0.85)
+
+compressed = compressor.compress(
+    history=prior_messages,      # your prior chat messages
+    tools=all_tool_schemas,      # the full tool catalog
+    plan=plan,
+    current_step="synthesize",   # the step about to run
+)
+
+response = llm.call(
+    messages=compressed.messages,
+    tools=compressed.tools,
+)
+
+print(compressed.report)
+# TokenReport(before=12400, after=3100, saved=9300, compression_ratio=0.75)
+```
+
+## How it works
+
+For the step about to run, memahead:
+
+1. **Splits** the conversation history into chunks (one per message).
+2. **Scores** each chunk against the *remaining* plan steps with a
+   `RetentionScorer` — embedding both with `all-MiniLM-L6-v2` and taking the
+   cosine similarity. A chunk is valuable if a future step is likely to need it.
+3. **Drops** chunks that future steps won't need (system messages and the
+   current turn's input are always retained).
+4. **Filters** the tool catalog down to schemas relevant to the current step —
+   deterministically, with no extra LLM call (`tool_filter`).
+5. **Hands** the survivors to Headroom for the actual mechanical compression.
+6. **Returns** a `CompressedContext` with lean `messages`, filtered `tools`,
+   and a `TokenReport` of exactly what was saved.
+
+The `quality` dial (0.0–1.0) trades tokens for retention: higher keeps more
+context, lower compresses more aggressively. Pass an explicit
+`retention_threshold` for fully reproducible runs.
+
+## Public API
+
+| Symbol | Purpose |
+| --- | --- |
+| `Step`, `Plan`, `PlanGraph` | Model linear or branching workflows; `plan.remaining_from(step)` is the forward horizon. |
+| `RetentionScorer` | Forward-looking chunk scoring (the core novelty). |
+| `ToolFilter`, `filter_tools` | Deterministic, LLM-free tool-schema filtering. |
+| `PlanAwareCompressor` | The full pipeline. |
+| `CompressedContext`, `TokenReport` | Results and savings accounting. |
+
+The embedding backend is swappable: pass any callable
+`list[str] -> np.ndarray` (or an object with `.encode`) as `embedder=` to
+`RetentionScorer`, `ToolFilter`, or `PlanAwareCompressor`. This makes memahead
+fully testable offline.
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+## Academic foundations
+
+memahead productizes findings from two papers that did not ship a usable
+library. It is an independent implementation and is not affiliated with or
+endorsed by the original authors.
+
+- **PAACE** — Yuksel et al., *Plan-Aware Agent Context Engineering*,
+  arXiv:[2512.16970](https://arxiv.org/abs/2512.16970) (Dec 2025).
+- **ACON** — Kang et al. (Microsoft), *Agent Context Optimization*,
+  arXiv:[2510.00615](https://arxiv.org/abs/2510.00615) (2025).
+
+See [`NOTICE`](./NOTICE) for full attribution.
+
+## License
+
+[Apache-2.0](./LICENSE).

memahead-0.1.0/README.md

@@ -0,0 +1,116 @@
+# memahead
+
+**Agent memory optimized for what's ahead.**
+
+memahead compresses an LLM agent's context at *each step* of a multi-step
+workflow using forward-looking, plan-aware retention. Unlike tools that
+compress greedily based on what already happened, memahead scores every chunk
+of context against the **remaining steps in the plan** and drops what future
+steps won't need — dramatically fewer tokens per agent call, without losing the
+information that matters downstream.
+
+memahead sits on top of [Headroom](https://pypi.org/project/headroom-ai/)
+(`pip install headroom-ai`), which performs the underlying compression
+mechanics. memahead adds the plan-aware retention scoring layer.
+
+## Install
+
+```bash
+pip install memahead
+```
+
+This pulls in `headroom-ai`, `sentence-transformers`, and `numpy`. For more
+accurate token accounting, also install the optional extra:
+
+```bash
+pip install "memahead[tokenizers]"   # adds tiktoken
+```
+
+## Quick example
+
+```python
+from memahead import Plan, Step, PlanAwareCompressor
+
+plan = Plan([
+    Step("research", "Search and gather raw facts about the topic"),
+    Step("synthesize", "Identify key themes across the research"),
+    Step("draft", "Write a structured first draft"),
+    Step("revise", "Produce the final polished output"),
+])
+
+compressor = PlanAwareCompressor(quality=0.85)
+
+compressed = compressor.compress(
+    history=prior_messages,      # your prior chat messages
+    tools=all_tool_schemas,      # the full tool catalog
+    plan=plan,
+    current_step="synthesize",   # the step about to run
+)
+
+response = llm.call(
+    messages=compressed.messages,
+    tools=compressed.tools,
+)
+
+print(compressed.report)
+# TokenReport(before=12400, after=3100, saved=9300, compression_ratio=0.75)
+```
+
+## How it works
+
+For the step about to run, memahead:
+
+1. **Splits** the conversation history into chunks (one per message).
+2. **Scores** each chunk against the *remaining* plan steps with a
+   `RetentionScorer` — embedding both with `all-MiniLM-L6-v2` and taking the
+   cosine similarity. A chunk is valuable if a future step is likely to need it.
+3. **Drops** chunks that future steps won't need (system messages and the
+   current turn's input are always retained).
+4. **Filters** the tool catalog down to schemas relevant to the current step —
+   deterministically, with no extra LLM call (`tool_filter`).
+5. **Hands** the survivors to Headroom for the actual mechanical compression.
+6. **Returns** a `CompressedContext` with lean `messages`, filtered `tools`,
+   and a `TokenReport` of exactly what was saved.
+
+The `quality` dial (0.0–1.0) trades tokens for retention: higher keeps more
+context, lower compresses more aggressively. Pass an explicit
+`retention_threshold` for fully reproducible runs.
+
+## Public API
+
+| Symbol | Purpose |
+| --- | --- |
+| `Step`, `Plan`, `PlanGraph` | Model linear or branching workflows; `plan.remaining_from(step)` is the forward horizon. |
+| `RetentionScorer` | Forward-looking chunk scoring (the core novelty). |
+| `ToolFilter`, `filter_tools` | Deterministic, LLM-free tool-schema filtering. |
+| `PlanAwareCompressor` | The full pipeline. |
+| `CompressedContext`, `TokenReport` | Results and savings accounting. |
+
+The embedding backend is swappable: pass any callable
+`list[str] -> np.ndarray` (or an object with `.encode`) as `embedder=` to
+`RetentionScorer`, `ToolFilter`, or `PlanAwareCompressor`. This makes memahead
+fully testable offline.
+
+## Development
+
+```bash
+pip install -e ".[dev]"
+pytest
+```
+
+## Academic foundations
+
+memahead productizes findings from two papers that did not ship a usable
+library. It is an independent implementation and is not affiliated with or
+endorsed by the original authors.
+
+- **PAACE** — Yuksel et al., *Plan-Aware Agent Context Engineering*,
+  arXiv:[2512.16970](https://arxiv.org/abs/2512.16970) (Dec 2025).
+- **ACON** — Kang et al. (Microsoft), *Agent Context Optimization*,
+  arXiv:[2510.00615](https://arxiv.org/abs/2510.00615) (2025).
+
+See [`NOTICE`](./NOTICE) for full attribution.
+
+## License
+
+[Apache-2.0](./LICENSE).