Back to the ticker

PalmClaw is an open-source agent framework that runs natively on Android phones

Modality Dance has released PalmClaw, an open-source framework that manages sessions, memory, skills, tools and the agent loop directly on an Android phone. It exposes device capabilities as structured tools with explicit arguments and defined execution boundaries instead of driving the screen through GUI actions. The paper is listed as an EMNLP 2026 system demonstration.

PalmClaw architecture overview showing on-device agent components, device tool execution, and resources & capabilities

The language model does not run locally. In the evaluation, a Xiaomi Redmi phone with Android 13 calls DeepSeek-V4-Flash through a remote API. On 70 adapted phone tasks covering calendar, weather, contacts, audio, notes, files, Bluetooth and media, PalmClaw reaches 97.1% task success, an 11.5% relative gain over the strongest baseline. Tasks take 17.7 seconds on average, a 94.9% reduction, and need 2.8 actions each against 103.9 for the GUI-based ApkClaw.

The exposed tools cover device status and permissions, media, Bluetooth, calendar, contacts, workspace files, web access, memory, communication and scheduled automation. On a 19-task AssistantBench subset for web information seeking, PalmClaw scores 36.85%. The authors name a modest task set without third-party GUI workflows, a single model backbone and one run per task as limitations. The code is on GitHub and the paper carries a CC BY-NC-SA 4.0 license.

  1. Graphcore runs Llama 3.2 11B Vision on a Pixel 8a with 2.7-bit quantisation
  2. Online-SDFT reports 70.28% routing accuracy and updates a LoRA adapter on the phone
  3. ClawMobile tries system commands before screen taps and finishes all six test tasks