legatolabs 0.1.0__tar.gz

legatolabs-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.

legatolabs-0.1.0/NOTICE

@@ -0,0 +1,28 @@
+Legato
+Copyright 2026 the Legato authors
+
+This product includes software from the following projects:
+
+- OSWorld (https://github.com/xlang-ai/OSWorld), Apache License 2.0.
+  `legato/rl/osworld_env.py` subclasses OSWorld's DesktopEnv. `LegatoDesktopEnv.step` is DesktopEnv.step from commit
+  8903ebeb0efdf74331bd7dc37ed91ccbbff22317, modified: the final fixed sleep before the observation is replaced by the
+  configured wait.
+
+- Anthropic computer-use demo (https://github.com/anthropics/claude-quickstarts, computer-use-demo), MIT License,
+  Copyright 2024 Anthropic, PBC. (computer-use-demo/LICENSE)
+  `legato/harness.py` (`REFERENCE_SYSTEM`) quotes two lines of the demo's system prompt. `Harness.reference`
+  re-implements the demo's loop behaviour: a 2 s screenshot delay, a screenshot per action, the screenshot sizes and
+  keep-all history. The MIT license text follows.
+
+  Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated
+  documentation files (the "Software"), to deal in the Software without restriction, including without limitation the
+  rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to
+  permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+  The above copyright notice and this permission notice shall be included in all copies or substantial portions of
+  the Software.
+
+  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
+  WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+  COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+  OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

legatolabs-0.1.0/PKG-INFO

@@ -0,0 +1,185 @@
+Metadata-Version: 2.4
+Name: legatolabs
+Version: 0.1.0
+Summary: Open computer-use harness for any OpenAI-compatible model (Qwen, DeepSeek, Claude, vLLM, OpenRouter): ready-wait instead of fixed sleeps, bounded calls, measured against the reference loops.
+Author: Legato authors
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://legato.computer
+Project-URL: Documentation, https://legato.computer/docs
+Project-URL: Benchmarks, https://legato.computer/docs/benchmarks
+Project-URL: Source, https://github.com/legatolabs/legato
+Project-URL: Issues, https://github.com/legatolabs/legato/issues
+Keywords: computer-use,computer use agent,gui agent,desktop agent,osworld,qwen,openrouter,vllm,e2b,llm agents,reinforcement learning,rollouts
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: httpx>=0.27
+Requires-Dist: Pillow>=10
+Provides-Extra: e2b
+Requires-Dist: e2b-desktop>=2.7; extra == "e2b"
+Provides-Extra: office
+Requires-Dist: python-pptx>=1.0; extra == "office"
+Requires-Dist: openpyxl>=3.1; extra == "office"
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.2; extra == "mcp"
+Provides-Extra: video
+Requires-Dist: imageio>=2.30; extra == "video"
+Requires-Dist: imageio-ffmpeg>=0.5; extra == "video"
+Requires-Dist: numpy; extra == "video"
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: mcp>=1.2; extra == "dev"
+Requires-Dist: python-pptx>=1.0; extra == "dev"
+Requires-Dist: openpyxl>=3.1; extra == "dev"
+Requires-Dist: imageio>=2.30; extra == "dev"
+Requires-Dist: imageio-ffmpeg>=0.5; extra == "dev"
+Requires-Dist: numpy; extra == "dev"
+Dynamic: license-file
+
+# Legato
+
+**Legato is an open-source computer-use harness for any OpenAI-compatible model** (Qwen, DeepSeek, Claude, or your
+own vLLM or SGLang server, directly or through OpenRouter). It drives a desktop sandbox (E2B, or any sandbox you can
+screenshot and send input to) with a Claude-style `computer` tool. It waits until the screen is ready instead of
+sleeping a fixed time, and it bounds every model call. Apache-2.0.
+
+```bash
+pip install "legatolabs[e2b]"      # the package is legatolabs on PyPI; you import it as `legato`
+```
+
+## Results
+
+Same model, same desktops, same tasks, all arms run at the same time. The tasks are 24 Excel-to-PowerPoint office
+workflows on real Ubuntu desktops (LibreOffice). Times are agent time: first screenshot to last model turn. Ranges are
+95% task-bootstrap intervals. Full method, raw data and losses: [docs/benchmarks.md](docs/benchmarks.md).
+
+| Model | Legato compared with | Time | Success |
+|---|---|---|---|
+| Claude Sonnet 5.5 | Anthropic's computer-use reference loop (re-implemented) | **1.48x faster** (0.678 [0.604, 0.757]) | 48/48 vs 48/48 |
+| Qwen3.8-27B | OSWorld's Qwen agent scaffold (`mm_agents/qwen`) | about the same (0.953 [0.798, 1.134]) | **71/96 vs 53/96** (74% vs 55%, two runs) |
+
+- **The Claude result** is one run. The saving is almost all fixed waiting: 14 s vs 45 s per task. Model time is the
+  same.
+- **The Qwen success gain** held on two independent task sets: +21 and +17 points.
+- **The Qwen speed result.** In the first run, OSWorld's agent let four rollouts generate up to 32,768 tokens in one
+  reply, so Legato looked 2.4x faster. On fresh tasks, without those runaways, the two are tied. We report the tie.
+- On OSWorld tasks with OSWorld's own harness (120 tasks, Qwen3.5-9B), Legato's ready-wait and fast reset cut task
+  time to 0.52 [0.43, 0.65] of the 5 s fixed-wait setting, at equal success. That is not an official OSWorld-Verified
+  submission.
+
+## Quickstart
+
+An open model through OpenRouter, on an E2B desktop:
+
+```python
+import os
+import legato
+from e2b_desktop import Sandbox
+
+agent = legato.Harness(model="qwen/qwen3.8-27b", base_url="https://openrouter.ai/api/v1",
+                       api_key=os.environ["OPENROUTER_API_KEY"])
+desk = Sandbox.create()                      # needs E2B_API_KEY
+try:
+    result = agent.run("Open the terminal and print the date", legato.attach(desk), max_steps=30)
+    print(result.report())                   # where the time went: model, actions, waiting for the screen
+finally:
+    desk.kill()
+```
+
+The same harness works with Claude: `legato.Harness(model="anthropic/claude-sonnet-5.5", ...)`. It switches to pixel
+coordinates and Anthropic's recommended screenshot size. It also works with your own server:
+`base_url="http://localhost:8000/v1"`. From the command line:
+
+```bash
+legato run "Open the terminal and print the date" --model qwen/qwen3.8-27b --base-url https://openrouter.ai/api/v1
+```
+
+Any sandbox, without E2B: pass a screenshot function and an action executor.
+
+```python
+env = legato.attach(screenshot=lambda: png_bytes(), execute=lambda action: send_input(action))
+```
+
+`action` is a `legato.Action` (`type` click / double_click / right_click / type / key / scroll / drag / wait, with
+pixel `x`, `y`, `text`, `keys`). More in [docs/sandboxes.md](docs/sandboxes.md) and [docs/models.md](docs/models.md).
+
+## What it does differently
+
+| | Legato | Typical reference loop |
+|---|---|---|
+| After each action | waits until the screen stops changing; on E2B the check runs inside the sandbox in one call | fixed sleep (Anthropic's demo: 2 s; OSWorld runners: 0–5 s) |
+| Actions per turn | up to 3, one screenshot after them | one per call, or all returned with a screenshot after each |
+| Screenshot history | old screenshots dropped 4 at a time past 8, so the provider's prompt cache keeps hitting | all kept, or one dropped per step |
+| Model calls | timeout, retry, 4,096-token budget; a reply cut off before acting gets a note on the next turn | often unbounded |
+| Timing | `result.report()` splits each run into model, action, waiting and screenshot time | none |
+
+`legato.Harness.reference(...)` is a re-implementation of Anthropic's reference loop on the same plumbing, so you can
+measure the difference on your own tasks.
+
+## Reproduce the benchmarks
+
+```bash
+pip install "legatolabs[office,video]"
+legato bench office generate --out bench --repeat 2          # 24 tasks: .xlsx data, .pptx decks, grader specs
+legato rl collect --tasks bench/tasks.json --harness legato --policy-url https://openrouter.ai/api/v1 \
+    --model qwen/qwen3.8-27b --api-key-env OPENROUTER_API_KEY --eval-only --osworld ~/OSWorld \
+    --version legato --out runs/legato --desktops 6 --group 2 --max-steps 25
+legato rl collect ... --harness qwen --no-ready-signal --fixed-wait 0 --version qwen-osworld --out runs/qwen-osworld
+legato bench h2h --tasks bench/tasks.json --arm qwen-osworld=runs/qwen-osworld --arm legato=runs/legato \
+    --ref qwen-osworld --out report
+```
+
+The desktops are OSWorld's Docker VMs, so you need a Linux host with KVM and an
+[OSWorld](https://github.com/xlang-ai/OSWorld) checkout. See [docs/benchmarks.md](docs/benchmarks.md).
+
+## Comparisons and migration
+
+- [Legato vs Anthropic's computer-use demo](docs/compare/anthropic-computer-use-demo.md)
+- [Legato vs OSWorld's Qwen agent](docs/compare/osworld-qwen-agent.md)
+- [Legato vs Agent S3](docs/compare/agent-s3.md)
+- [Legato vs UI-TARS-desktop](docs/compare/ui-tars-desktop.md)
+- [Migrating from cua-agent](docs/migrate/from-cua-agent.md) (cua-agent is no longer maintained)
+- [Migrating from Bytebot](docs/migrate/from-bytebot.md) (Bytebot is archived)
+
+## MCP server
+
+`legato mcp` gives Claude Code, Cursor or any MCP client a cloud desktop. Each action returns once the screen has
+settled, with the new screenshot. See [docs/mcp.md](docs/mcp.md).
+
+```bash
+pip install "legatolabs[e2b,mcp]"
+claude mcp add legato -e E2B_API_KEY=your_key -- legato mcp
+```
+
+## RL rollouts
+
+`legato rl` collects graded desktop rollouts for computer-use RL. It records token logprobs and token ids, runs
+GRPO-style groups with oversampling and straggler cancel, caps in-flight requests, and profiles each batch. You bring
+the model server and the trainer. See [docs/rl.md](docs/rl.md).
+
+## FAQ
+
+- **Why `pip install legatolabs` but `import legato`?** The PyPI name `legato` was taken, so the package is published as
+  `legatolabs`. The module, the command line tool and the docs all use `legato`.
+- **Is Legato an alternative to cua-agent or Bytebot?** Yes, for the agent loop. Both are no longer maintained; see
+  the migration guides above.
+- **Which models work?** Any model behind an OpenAI-compatible chat API that accepts images. Native tool calls are
+  used when the server supports them; otherwise JSON in the reply text is parsed. Measured so far: Claude Sonnet 5.5
+  and Qwen3.8-27B. See [docs/models.md](docs/models.md).
+- **Does it need a GPU?** No. Point it at a hosted API or your own server.
+- **Is there a hosted version?** Optional: [legato.computer](https://legato.computer) runs desktops with pause,
+  resume and fork. Nothing in this package requires it.
+
+More in [docs/faq.md](docs/faq.md). License: Apache-2.0.

legatolabs-0.1.0/README.md

@@ -0,0 +1,135 @@
+# Legato
+
+**Legato is an open-source computer-use harness for any OpenAI-compatible model** (Qwen, DeepSeek, Claude, or your
+own vLLM or SGLang server, directly or through OpenRouter). It drives a desktop sandbox (E2B, or any sandbox you can
+screenshot and send input to) with a Claude-style `computer` tool. It waits until the screen is ready instead of
+sleeping a fixed time, and it bounds every model call. Apache-2.0.
+
+```bash
+pip install "legatolabs[e2b]"      # the package is legatolabs on PyPI; you import it as `legato`
+```
+
+## Results
+
+Same model, same desktops, same tasks, all arms run at the same time. The tasks are 24 Excel-to-PowerPoint office
+workflows on real Ubuntu desktops (LibreOffice). Times are agent time: first screenshot to last model turn. Ranges are
+95% task-bootstrap intervals. Full method, raw data and losses: [docs/benchmarks.md](docs/benchmarks.md).
+
+| Model | Legato compared with | Time | Success |
+|---|---|---|---|
+| Claude Sonnet 5.5 | Anthropic's computer-use reference loop (re-implemented) | **1.48x faster** (0.678 [0.604, 0.757]) | 48/48 vs 48/48 |
+| Qwen3.8-27B | OSWorld's Qwen agent scaffold (`mm_agents/qwen`) | about the same (0.953 [0.798, 1.134]) | **71/96 vs 53/96** (74% vs 55%, two runs) |
+
+- **The Claude result** is one run. The saving is almost all fixed waiting: 14 s vs 45 s per task. Model time is the
+  same.
+- **The Qwen success gain** held on two independent task sets: +21 and +17 points.
+- **The Qwen speed result.** In the first run, OSWorld's agent let four rollouts generate up to 32,768 tokens in one
+  reply, so Legato looked 2.4x faster. On fresh tasks, without those runaways, the two are tied. We report the tie.
+- On OSWorld tasks with OSWorld's own harness (120 tasks, Qwen3.5-9B), Legato's ready-wait and fast reset cut task
+  time to 0.52 [0.43, 0.65] of the 5 s fixed-wait setting, at equal success. That is not an official OSWorld-Verified
+  submission.
+
+## Quickstart
+
+An open model through OpenRouter, on an E2B desktop:
+
+```python
+import os
+import legato
+from e2b_desktop import Sandbox
+
+agent = legato.Harness(model="qwen/qwen3.8-27b", base_url="https://openrouter.ai/api/v1",
+                       api_key=os.environ["OPENROUTER_API_KEY"])
+desk = Sandbox.create()                      # needs E2B_API_KEY
+try:
+    result = agent.run("Open the terminal and print the date", legato.attach(desk), max_steps=30)
+    print(result.report())                   # where the time went: model, actions, waiting for the screen
+finally:
+    desk.kill()
+```
+
+The same harness works with Claude: `legato.Harness(model="anthropic/claude-sonnet-5.5", ...)`. It switches to pixel
+coordinates and Anthropic's recommended screenshot size. It also works with your own server:
+`base_url="http://localhost:8000/v1"`. From the command line:
+
+```bash
+legato run "Open the terminal and print the date" --model qwen/qwen3.8-27b --base-url https://openrouter.ai/api/v1
+```
+
+Any sandbox, without E2B: pass a screenshot function and an action executor.
+
+```python
+env = legato.attach(screenshot=lambda: png_bytes(), execute=lambda action: send_input(action))
+```
+
+`action` is a `legato.Action` (`type` click / double_click / right_click / type / key / scroll / drag / wait, with
+pixel `x`, `y`, `text`, `keys`). More in [docs/sandboxes.md](docs/sandboxes.md) and [docs/models.md](docs/models.md).
+
+## What it does differently
+
+| | Legato | Typical reference loop |
+|---|---|---|
+| After each action | waits until the screen stops changing; on E2B the check runs inside the sandbox in one call | fixed sleep (Anthropic's demo: 2 s; OSWorld runners: 0–5 s) |
+| Actions per turn | up to 3, one screenshot after them | one per call, or all returned with a screenshot after each |
+| Screenshot history | old screenshots dropped 4 at a time past 8, so the provider's prompt cache keeps hitting | all kept, or one dropped per step |
+| Model calls | timeout, retry, 4,096-token budget; a reply cut off before acting gets a note on the next turn | often unbounded |
+| Timing | `result.report()` splits each run into model, action, waiting and screenshot time | none |
+
+`legato.Harness.reference(...)` is a re-implementation of Anthropic's reference loop on the same plumbing, so you can
+measure the difference on your own tasks.
+
+## Reproduce the benchmarks
+
+```bash
+pip install "legatolabs[office,video]"
+legato bench office generate --out bench --repeat 2          # 24 tasks: .xlsx data, .pptx decks, grader specs
+legato rl collect --tasks bench/tasks.json --harness legato --policy-url https://openrouter.ai/api/v1 \
+    --model qwen/qwen3.8-27b --api-key-env OPENROUTER_API_KEY --eval-only --osworld ~/OSWorld \
+    --version legato --out runs/legato --desktops 6 --group 2 --max-steps 25
+legato rl collect ... --harness qwen --no-ready-signal --fixed-wait 0 --version qwen-osworld --out runs/qwen-osworld
+legato bench h2h --tasks bench/tasks.json --arm qwen-osworld=runs/qwen-osworld --arm legato=runs/legato \
+    --ref qwen-osworld --out report
+```
+
+The desktops are OSWorld's Docker VMs, so you need a Linux host with KVM and an
+[OSWorld](https://github.com/xlang-ai/OSWorld) checkout. See [docs/benchmarks.md](docs/benchmarks.md).
+
+## Comparisons and migration
+
+- [Legato vs Anthropic's computer-use demo](docs/compare/anthropic-computer-use-demo.md)
+- [Legato vs OSWorld's Qwen agent](docs/compare/osworld-qwen-agent.md)
+- [Legato vs Agent S3](docs/compare/agent-s3.md)
+- [Legato vs UI-TARS-desktop](docs/compare/ui-tars-desktop.md)
+- [Migrating from cua-agent](docs/migrate/from-cua-agent.md) (cua-agent is no longer maintained)
+- [Migrating from Bytebot](docs/migrate/from-bytebot.md) (Bytebot is archived)
+
+## MCP server
+
+`legato mcp` gives Claude Code, Cursor or any MCP client a cloud desktop. Each action returns once the screen has
+settled, with the new screenshot. See [docs/mcp.md](docs/mcp.md).
+
+```bash
+pip install "legatolabs[e2b,mcp]"
+claude mcp add legato -e E2B_API_KEY=your_key -- legato mcp
+```
+
+## RL rollouts
+
+`legato rl` collects graded desktop rollouts for computer-use RL. It records token logprobs and token ids, runs
+GRPO-style groups with oversampling and straggler cancel, caps in-flight requests, and profiles each batch. You bring
+the model server and the trainer. See [docs/rl.md](docs/rl.md).
+
+## FAQ
+
+- **Why `pip install legatolabs` but `import legato`?** The PyPI name `legato` was taken, so the package is published as
+  `legatolabs`. The module, the command line tool and the docs all use `legato`.
+- **Is Legato an alternative to cua-agent or Bytebot?** Yes, for the agent loop. Both are no longer maintained; see
+  the migration guides above.
+- **Which models work?** Any model behind an OpenAI-compatible chat API that accepts images. Native tool calls are
+  used when the server supports them; otherwise JSON in the reply text is parsed. Measured so far: Claude Sonnet 5.5
+  and Qwen3.8-27B. See [docs/models.md](docs/models.md).
+- **Does it need a GPU?** No. Point it at a hosted API or your own server.
+- **Is there a hosted version?** Optional: [legato.computer](https://legato.computer) runs desktops with pause,
+  resume and fork. Nothing in this package requires it.
+
+More in [docs/faq.md](docs/faq.md). License: Apache-2.0.

legatolabs-0.1.0/legato/__init__.py

@@ -0,0 +1,16 @@
+"""legato: an open computer-use harness for any OpenAI-compatible model. https://legato.computer
+
+    agent = legato.Harness(model, base_url, api_key)
+    result = agent.run(task, legato.attach(sandbox))
+
+The optional hosted API (legato.computer) lives in `legato.hosted`.
+"""
+from legato import hosted
+from legato.actions import Action, parse
+from legato.env import Env, Obs, attach
+from legato.harness import Harness, RunResult, computer_tool
+from legato.settle import Waiter, wrap
+
+__all__ = ["Action", "Env", "Harness", "Obs", "RunResult", "Waiter", "attach", "computer_tool", "hosted", "parse",
+           "wrap"]
+__version__ = "0.1.0"

legatolabs-0.1.0/legato/__main__.py

@@ -0,0 +1,72 @@
+"""legato command line.
+
+  legato run "Add a Total row under the table and save" \\
+      --model qwen/qwen3-vl-235b-a22b-instruct --base-url https://openrouter.ai/api/v1 [--api-key-env OPENROUTER_API_KEY]
+      [--max-steps 30] [--coords norm1000|pixels] [--sandbox e2b]
+
+Runs the open harness on a fresh E2B Desktop sandbox (needs `pip install "legatolabs[e2b]"` and E2B_API_KEY) and prints
+where the time went.
+
+  legato bench office generate|report ...   the Legato Office Bench (Excel to PowerPoint tasks)
+  legato bench h2h --tasks ... --arm a=DIR --arm b=DIR --ref a --out DIR   compare harness runs
+  legato rl probe|collect|export|profile ... graded rollouts for RL (see docs/rl.md)
+  legato mcp                                 an MCP server: cloud desktops for any agent (see docs/mcp.md)
+"""
+from __future__ import annotations
+
+import argparse
+import os
+import sys
+
+
+def main(argv=None) -> int:
+    argv = sys.argv[1:] if argv is None else list(argv)
+    if argv[:1] == ["rl"]:
+        from legato.rl.__main__ import main as rl_main
+        return rl_main(argv[1:])
+    if argv[:1] == ["mcp"]:
+        from legato.mcp_server import main as mcp_main
+        return mcp_main(argv[1:])
+    if argv[:1] == ["bench"]:
+        which = argv[1] if len(argv) > 1 else ""
+        if which == "office":
+            from legato.rl.bench.office import main as office_main
+            return office_main(argv[2:])
+        if which == "h2h":
+            from legato.rl.bench.h2h import main as h2h_main
+            return h2h_main(argv[2:])
+        print("usage: legato bench office|h2h ...", file=sys.stderr)
+        return 2
+    ap = argparse.ArgumentParser(prog="legato", epilog="also: legato bench office|h2h ... (benchmarks), "
+                                 "legato rl probe|collect|export|profile ... (RL rollouts), legato mcp (MCP server)")
+    sub = ap.add_subparsers(dest="cmd", required=True)
+    r = sub.add_parser("run", help="run one task with the open harness on a fresh sandbox")
+    r.add_argument("task")
+    r.add_argument("--model", required=True)
+    r.add_argument("--base-url", required=True, help="OpenAI-compatible root, e.g. https://openrouter.ai/api/v1")
+    r.add_argument("--api-key-env", default="OPENROUTER_API_KEY")
+    r.add_argument("--max-steps", type=int, default=30)
+    r.add_argument("--coords", default=None, choices=["norm1000", "pixels"],
+                   help="default: pixels for Claude models, norm1000 (0-1000 grid) otherwise")
+    r.add_argument("--sandbox", default="e2b", choices=["e2b"])
+    a = ap.parse_args(argv)
+    from legato import Harness, attach
+    try:
+        from e2b_desktop import Sandbox
+    except ImportError:
+        print('E2B Desktop is not installed: pip install "legatolabs[e2b]"', file=sys.stderr)
+        return 2
+    agent = Harness(model=a.model, base_url=a.base_url, api_key=os.environ.get(a.api_key_env, ""), coords=a.coords)
+    desk = Sandbox.create()
+    try:
+        res = agent.run(a.task, attach(desk), max_steps=a.max_steps,
+                        on_step=lambda i, acts, t: print(f"turn {i + 1}: {', '.join(x.describe() for x in acts) or '-'} "
+                                                         f"(model {t['model_s']:.1f} s, waiting {t['settle_s']:.1f} s)"))
+    finally:
+        desk.kill()
+    print(res.report())
+    return 0 if res.done else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())