chenmingxuan/Artemis-Eapil
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 32 Wiki Activity
Files
584bb2d09c8bc5f19b3d30495a67bbaaaa5d6eab
Artemis-Eapil/artemis/agents/history_analyzer/history_analyzer.md
T
somew1nd 206a9ce921 feat: initial release of ARTEMIS Android Agent & Automation Platform 
ARTEMIS is an autonomous multimodal Android agent and mobile UI automation
platform engineered for physical devices and emulators. It combines state-of-the-art
multimodal Vision-Language Models (VLMs) with hierarchical closed-loop planning,
resilient self-healing, and deep Android subsystem integration.

Key Features & Architectural Highlights:
- Dual-Engine Orchestration:
  * Pro Engine: Multi-agent closed-loop (Planner -> Operator -> Validator/Failure Analyzer -> Summarizer) powered by LangGraph.
  * Flash Engine: Ultra-fast reactive loop for deterministic, low-latency UI execution (<35 steps).
- Multimodal Perception & Grounding:
  * Hybrid visual screenshot grounding, real-time OCR extraction, and XML accessibility hierarchy parsing.
  * Dynamic-First, Coordinate-Fallback locating strategy for maximum resilience against UI drift.
- Autonomous Self-Healing & Diagnostics:
  * Failure analyzer and safety net for popup dismissal, crash recovery, and auto-retry.
  * Diagnostic sub-agents for log analysis, video recording inspection, and object detection.
- Unified CLI & Python SDK:
  * Rich CLI with commands: init, doctor, run, trace, batch, bench, server, and mcp.
  * Fluent Python SDK with Pydantic structured output models and package locking.
- Multi-Provider LLM Architecture:
  * Support for Google Gemini, OpenAI, Anthropic Claude, Vertex AI, OpenRouter, xAI Grok, and local endpoints (Ollama/vLLM).
  * Centralized configuration in config/artemis.jsonc.
- Native MCP & Observability:
  * Model Context Protocol (MCP) server endpoints for AI IDEs.
  * Full trace recording with before/after screenshots, action overlays, and execution replays.

Change-Id: I430b93ee2b76b54cc5a3c6eeccd15d2cf29830a1
2026-08-13 11:46:47 -07:00

810 B
Raw Blame History

IDENTITY

You are a History Analyzer, expert in analyzing multi-agent session execution history to answer user queries.

MANDATE

  1. You are provided with the Task Plan and Execution History summarizing the high-level plan and history steps.
  2. For queries about specific step details (such as precise actions, coordinates, operator_raw_thinking, or last_execution_result), you should call the get_step_details tool.
  3. Never assume, guess, or invent details not visible in the Task Plan and Execution History. Always query get_step_details for specifics. If details are unavailable, state it clearly.
  4. Make good use of note tools to see what notes are available. When analyzing history records, open and cross-reference relevant notes to ensure you have grasped all necessary information.
Reference in new issue View Git Blame Copy Permalink