aris-server 0.1.0__tar.gz

aris_server-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,37 @@
+# Publishes aris-server to PyPI when a version tag is pushed (git tag v0.1.0 && git push origin v0.1.0).
+# Trusted publishing: no token is stored anywhere. PyPI needs a matching (pending) publisher first:
+# project aris-server, this repository, workflow publish.yml, environment pypi.
+name: Publish to PyPI
+
+on:
+  push:
+    tags: ["v*"]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: astral-sh/setup-uv@v6
+      - name: Check the tag matches the package version
+        run: |
+          version=$(grep -m1 '^version = ' pyproject.toml | cut -d'"' -f2)
+          test "v$version" = "$GITHUB_REF_NAME" || { echo "tag $GITHUB_REF_NAME, version $version"; exit 1; }
+      - run: uv build
+      - uses: actions/upload-artifact@v4
+        with:
+          name: dist
+          path: dist/
+
+  publish:
+    needs: build
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write
+    steps:
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: dist/
+      - uses: pypa/gh-action-pypi-publish@release/v1

aris_server-0.1.0/.gitignore

@@ -0,0 +1,5 @@
+__pycache__/
+*.egg-info/
+.venv/
+.pytest_cache/
+dist/

aris_server-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.
+

aris_server-0.1.0/PKG-INFO

@@ -0,0 +1,132 @@
+Metadata-Version: 2.5
+Name: aris-server
+Version: 0.1.0
+Summary: Run open-weight models locally behind the Anthropic Messages API, for Claude Code and friends.
+License-Expression: Apache-2.0
+License-File: LICENSE
+Requires-Python: >=3.11
+Requires-Dist: mlx-lm==0.32.2
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Aris Server
+
+Run open-weight models on your Mac and use them from Claude Code, Aris Code, or anything else that
+speaks the Anthropic Messages API.
+
+```bash
+uv tool install git+https://github.com/kennysarnoski-jarvis/aris-server
+aris-server serve --model mlx-community/Qwen3.5-9B-MLX-8bit
+```
+
+Then point Claude Code at it:
+
+```bash
+ANTHROPIC_BASE_URL=http://127.0.0.1:8484 ANTHROPIC_AUTH_TOKEN=local claude
+```
+
+Claude Code assumes a 200k-token window and compacts its conversation about 33k tokens short of the
+window it's given. A local model's window is whatever fits beside its weights, so tell Claude Code
+what it is: the server logs it at startup, and `/v1/models` lists it as `context_window`. With
+`CLAUDE_CODE_MAX_CONTEXT_TOKENS` set to it, the conversation compacts before the server's limit:
+
+```bash
+CLAUDE_CODE_MAX_CONTEXT_TOKENS=124928 ANTHROPIC_BASE_URL=http://127.0.0.1:8484 ANTHROPIC_AUTH_TOKEN=local claude
+```
+
+## Aris 3.8-27B
+
+Aris 3.8-27B is built in as `aris-3.8-27b`. It's Aris's coding-agent fine-tune of
+[Arete-27B](https://huggingface.co/NousResearch/Arete-27B) by Nous Research, which is built on
+[Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) by the Qwen team at Alibaba Cloud. `pull`
+picks the best build this Mac can hold, before anything big downloads, and downloads it:
+
+```bash
+aris-server pull aris-3.8-27b
+aris-server serve --model aris-3.8-27b
+```
+
+The 8-bit build takes 27 GB, so it needs a Mac with 48 GB of memory or more, where it has about
+125k tokens of context. Its [model card](https://huggingface.co/YourAris/Aris-3.8-27B-MLX-8bit) has
+the details and evals.
+
+## Why not Ollama?
+
+Aris Server does one job: serve a local model to coding agents properly.
+
+- **Native `/v1/messages`.** Thinking, tool calls and text stream as real Anthropic events from
+  the first byte, with pings while a long prompt is read or a long tool call is written, so clients
+  never time out on silence, and a client that hangs up stops its generation.
+- **Effort that works.** Claude Code's effort setting reaches models that have trained effort
+  levels.
+- **A think budget.** Reasoning models that overthink get their thinking closed at the end of
+  the current line once they pass the budget for the requested effort, so they answer instead of
+  burning every token deliberating.
+- **Claude Code's tool search.** Deferred tools stay out of the prompt until the agent loads them.
+- **Fast on Apple Silicon.** Built on [MLX](https://github.com/ml-explore/mlx) and mlx-lm:
+  continuous batching and a prompt cache that keeps the system prompt warm across conversations.
+
+## Models
+
+Any MLX model folder or Hugging Face repo that mlx-lm can load works by name. To give a model a
+short name, effort mapping or think budgets, add it to `~/.aris-server/models.toml`:
+
+```toml
+[models."arete:27b"]
+path = "~/models/arete-27b-mlx-8bit"
+context = 131072
+effort_kwarg = "reasoning_effort"
+effort_map = { low = "low", medium = "medium", high = "medium", xhigh = "xhigh", max = "xhigh" }
+think_budget = { low = 1024, medium = 4096, high = 8192, xhigh = 16384, max = 0 }
+```
+
+```bash
+aris-server serve --model arete:27b
+```
+
+A fine-tuned model can ship as a LoRA adapter on top of its base: add `adapter = "~/adapters/expert1"`
+(a folder with `adapter_config.json` and `adapters.safetensors`, as mlx-lm's trainer writes them) to
+a model entry, or pass `--adapter`. Switching between a base model and its adapter is a restart.
+
+`kv_bits = 8` in a model entry (or `--kv-bits 8`) keeps the KV cache at 8 bits: about twice the context
+in the same memory. `--kv-bits 16` turns it back to full precision.
+
+To serve the best weights each Mac can hold, give `path` a list, best first. Before loading, the server
+works out how much context each would leave on this Mac and loads the first that leaves `min_context`
+tokens (65536 unless set), or else the one that leaves the most. Hugging Face repos are sized from the
+Hub before anything downloads, so a Mac only ever fetches weights it can run:
+
+```toml
+[models."arete:27b"]
+path = ["~/models/arete-27b-mlx-8bit", "~/models/arete-27b-mlx-4bit"]
+kv_bits = 8
+```
+
+With the 8-bit KV cache, Arete-27B's 8-bit weights leave about 124k tokens of context on a 48 GB Mac and
+more than the model's whole context on a 64 GB one. A 32 GB Mac can't hold them and gets the 4-bit
+weights, with about 63k.
+
+## Run it as a service
+
+```bash
+aris-server service install -- --model aris-3.8-27b
+aris-server service status
+aris-server service uninstall
+```
+
+`aris-server pull --json` reports each step of a download as a JSON line, for apps that set the
+server up for their users. `aris-server models` lists configured and built-in models.
+
+The service starts at login and restarts the server within seconds of any exit (it exits on purpose
+if the GPU runs out of memory). Saved prompt caches mean the conversation picks up where it left off;
+they take up to 20 GB of disk, all models together (`--disk-cache-gb`). Logs go to
+`~/.aris-server/server.log`.
+
+## Status
+
+Early. macOS on Apple Silicon only. See [docs/design.md](docs/design.md) for what's in and out.
+
+## License
+
+Apache-2.0

aris_server-0.1.0/README.md

@@ -0,0 +1,120 @@
+# Aris Server
+
+Run open-weight models on your Mac and use them from Claude Code, Aris Code, or anything else that
+speaks the Anthropic Messages API.
+
+```bash
+uv tool install git+https://github.com/kennysarnoski-jarvis/aris-server
+aris-server serve --model mlx-community/Qwen3.5-9B-MLX-8bit
+```
+
+Then point Claude Code at it:
+
+```bash
+ANTHROPIC_BASE_URL=http://127.0.0.1:8484 ANTHROPIC_AUTH_TOKEN=local claude
+```
+
+Claude Code assumes a 200k-token window and compacts its conversation about 33k tokens short of the
+window it's given. A local model's window is whatever fits beside its weights, so tell Claude Code
+what it is: the server logs it at startup, and `/v1/models` lists it as `context_window`. With
+`CLAUDE_CODE_MAX_CONTEXT_TOKENS` set to it, the conversation compacts before the server's limit:
+
+```bash
+CLAUDE_CODE_MAX_CONTEXT_TOKENS=124928 ANTHROPIC_BASE_URL=http://127.0.0.1:8484 ANTHROPIC_AUTH_TOKEN=local claude
+```
+
+## Aris 3.8-27B
+
+Aris 3.8-27B is built in as `aris-3.8-27b`. It's Aris's coding-agent fine-tune of
+[Arete-27B](https://huggingface.co/NousResearch/Arete-27B) by Nous Research, which is built on
+[Qwen3.8-27B](https://huggingface.co/Qwen/Qwen3.8-27B) by the Qwen team at Alibaba Cloud. `pull`
+picks the best build this Mac can hold, before anything big downloads, and downloads it:
+
+```bash
+aris-server pull aris-3.8-27b
+aris-server serve --model aris-3.8-27b
+```
+
+The 8-bit build takes 27 GB, so it needs a Mac with 48 GB of memory or more, where it has about
+125k tokens of context. Its [model card](https://huggingface.co/YourAris/Aris-3.8-27B-MLX-8bit) has
+the details and evals.
+
+## Why not Ollama?
+
+Aris Server does one job: serve a local model to coding agents properly.
+
+- **Native `/v1/messages`.** Thinking, tool calls and text stream as real Anthropic events from
+  the first byte, with pings while a long prompt is read or a long tool call is written, so clients
+  never time out on silence, and a client that hangs up stops its generation.
+- **Effort that works.** Claude Code's effort setting reaches models that have trained effort
+  levels.
+- **A think budget.** Reasoning models that overthink get their thinking closed at the end of
+  the current line once they pass the budget for the requested effort, so they answer instead of
+  burning every token deliberating.
+- **Claude Code's tool search.** Deferred tools stay out of the prompt until the agent loads them.
+- **Fast on Apple Silicon.** Built on [MLX](https://github.com/ml-explore/mlx) and mlx-lm:
+  continuous batching and a prompt cache that keeps the system prompt warm across conversations.
+
+## Models
+
+Any MLX model folder or Hugging Face repo that mlx-lm can load works by name. To give a model a
+short name, effort mapping or think budgets, add it to `~/.aris-server/models.toml`:
+
+```toml
+[models."arete:27b"]
+path = "~/models/arete-27b-mlx-8bit"
+context = 131072
+effort_kwarg = "reasoning_effort"
+effort_map = { low = "low", medium = "medium", high = "medium", xhigh = "xhigh", max = "xhigh" }
+think_budget = { low = 1024, medium = 4096, high = 8192, xhigh = 16384, max = 0 }
+```
+
+```bash
+aris-server serve --model arete:27b
+```
+
+A fine-tuned model can ship as a LoRA adapter on top of its base: add `adapter = "~/adapters/expert1"`
+(a folder with `adapter_config.json` and `adapters.safetensors`, as mlx-lm's trainer writes them) to
+a model entry, or pass `--adapter`. Switching between a base model and its adapter is a restart.
+
+`kv_bits = 8` in a model entry (or `--kv-bits 8`) keeps the KV cache at 8 bits: about twice the context
+in the same memory. `--kv-bits 16` turns it back to full precision.
+
+To serve the best weights each Mac can hold, give `path` a list, best first. Before loading, the server
+works out how much context each would leave on this Mac and loads the first that leaves `min_context`
+tokens (65536 unless set), or else the one that leaves the most. Hugging Face repos are sized from the
+Hub before anything downloads, so a Mac only ever fetches weights it can run:
+
+```toml
+[models."arete:27b"]
+path = ["~/models/arete-27b-mlx-8bit", "~/models/arete-27b-mlx-4bit"]
+kv_bits = 8
+```
+
+With the 8-bit KV cache, Arete-27B's 8-bit weights leave about 124k tokens of context on a 48 GB Mac and
+more than the model's whole context on a 64 GB one. A 32 GB Mac can't hold them and gets the 4-bit
+weights, with about 63k.
+
+## Run it as a service
+
+```bash
+aris-server service install -- --model aris-3.8-27b
+aris-server service status
+aris-server service uninstall
+```
+
+`aris-server pull --json` reports each step of a download as a JSON line, for apps that set the
+server up for their users. `aris-server models` lists configured and built-in models.
+
+The service starts at login and restarts the server within seconds of any exit (it exits on purpose
+if the GPU runs out of memory). Saved prompt caches mean the conversation picks up where it left off;
+they take up to 20 GB of disk, all models together (`--disk-cache-gb`). Logs go to
+`~/.aris-server/server.log`.
+
+## Status
+
+Early. macOS on Apple Silicon only. See [docs/design.md](docs/design.md) for what's in and out.
+
+## License
+
+Apache-2.0