Home > Coming Soon

Coming Soon

EulerWeave · EulerAgent · EulerAtlas — the next step of Eulerwa Inc.'s full-stack vision

The three products available today (EulerForge · EulerStack · EulerNPU) form the core axis from training to architecture research to FPGA NPU synthesis. The data pipeline (EulerWeave), deterministic agent execution (EulerAgent), and 8-domain robot behavioral learning (EulerAtlas) that connect this axis end-to-end are coming soon. All of them share the same "declarative YAML spec + CLI-first + local-first" philosophy.

Coming Soon

EulerWeave: The Data Engine

A comprehensive data processing system that bridges the gap between raw datasets and production-ready model training.

Open Source: Data Preprocessing

Designed for researchers and developers to refine and analyze data in local environments.

  • Smart Analysis: Initial data profiling using local LLMs.
  • Recursive Filtering: Auto-generation and application of domain-specific filter classes.
  • Metric Computation: PPL, Loss, and MinHash computation for deduplication.
  • Quality Scoring: Noise filtering scores via BERT-based models.

Enterprise: Orchestration

Business-critical features for scaling from a single GPU to cluster-level operations.

  • Scale-Down Validation: Automated 1-GPU LoRA/MoE testing.
  • Resource Estimation: AI-powered GPU-hour and cloud cost calculation.
  • Parameter Tuning: Bayesian optimization and grid search automation.
  • MLOps Integration: End-to-end pipeline from training launch to result synthesis.

EulerAgent: Deterministic CLI Agent Framework

A local-first agent framework with an 8-state machine (RUN_CREATED → CONTEXT → PLAN → PROPOSE → APPROVE → EXECUTE → RESULT → FINALIZED), Pattern/Graph orchestrators, a RAG pipeline, long-term memory (SQLite), MCP integration, a plugin system, 30+ CLI commands, and 65 fixtures. On top of deterministic gate nodes (kind: shell) that run verification as code rather than via the LLM, it ships a self-repairing coding agent (code.dev_loop.v2) that writes, tests, and fixes its own code.

8-State Machine & Orchestration

Every agent action passes through the 8-state machine and is executed only after human-in-the-loop (HITL) approval. The Pattern Orchestrator (12 canonical YAML patterns mixing LLM, judge, and deterministic shell gate nodes) and the Graph Orchestrator (LangGraph parallel execution) drive complex workflows. Bounded auto-approval (node.auto_approve) and a symbol gate (symbol_check) let fix→test loops run autonomously.

  • Long-Term Memory (LTM): SQLite-based vector search preserves context across sessions.
  • RAG Pipeline: Hybrid lexical/vector search with citation source tracking.
  • MCP Integration: Connects to external services such as Brave and Tavily.
  • Plugin System: Tool extensions and a multi-layer tool-permission chain.

30+ CLI Commands

euleragent init
euleragent new my-assistant --template code-assistant
euleragent run my-assistant --task "refactor" --mode plan

# RAG & memory
euleragent rag add --path ./docs/
euleragent memory search --q "previous decision"

# Pattern & MCP
euleragent pattern run review-code my-assistant
euleragent mcp sync

Built for developers who want autonomous capabilities without giving up control and security.

EulerAtlas: Plugin-Based Robot Behavioral Learning (first public: Car · Humanoid)

A plugin-based CLI robot behavioral learning framework running on an RL→IL pipeline that combines imitation learning (IL) with FastTD3 reinforcement learning (RL). The first two flagship domains we are releasing are car (EulerDrive — BEV autonomous driving, CARLA-verified) and humanoid (EulerWalk — RL→IL loco-manipulation), and both ship pretrained models so you can run them with no training at all. The unified schema is designed to cover 8 domains — car, drone, humanoid, robot dog, mobile manipulation, logistics, agriculture, shipyard — and domains keep expanding as plugins.

8-Domain Unified Schema

All modules communicate consistently through fixed obs/action dimension schemas per domain.

Classic (01-04) Car 4/2 · Drone 6/3 · Humanoid 33/14 (loco-manip) · Robot Dog 12/8
Industrial (05-08) Mobile Manipulation 18/8 · Warehouse AGV 14/4 · Agri-Robot 16/6 · Shipyard 20/9
Policy Models BC-MLP, BC-RNN, BC-CNN, ACT, Diffusion Policy + SOTA (BEVFuser, TemporalTransformer, WholeBodyACT) + RL Actor
Levels L0 Toy · L1 Intermediate · L2 Advanced (real backends: CARLA/MuJoCo/HumanoidBench)

CLI & Policy Models

euleratlas init --role road --level 0 --out config.yml
euleratlas train -c config.yml
euleratlas train-rl -c config.yml
euleratlas sim rollout -c config.yml --save-video

# Imitation learning + FastTD3 RL · RL→IL · Domain Plugin

Adds train-rl, data collect/generate-demos, and sim rollout --render/--save-video. Includes the Domain Plugin architecture and edge deployment.

See the three products available today first

Training (EulerForge) → architecture research (EulerStack) → FPGA NPU synthesis (EulerNPU). The upcoming products above are designed to run on top of this core axis.

EulerForge EulerStack EulerNPU Back to Home