What changed
The Pathiel repository, developed in Python, has recently seen its latest release, version v0.4.1, on November 13, 2026. This release marks a fresh update for the AI trading agent, which is built to operate on the Hyperliquid platform. The agent leverages Anthropic's Claude model to execute trades for perpetual futures. A key feature is its adherence to the MCP (Multi-Collateralized Positions) framework, ensuring that every order is placed with an exact stop-loss and take-profit target. By default, the agent employs a risk management strategy of 3x leverage or a 1% risk per trade, reflecting a structured approach to managing capital. The project also incorporates "oil and metals desk briefs," suggesting a focus on commodity markets. Additionally, a free Claude Code plugin is provided, enhancing its utility for developers.
Why it matters for builders
For developers and traders interested in algorithmic trading, Pathiel offers a concrete example of an AI agent integrated with a specific trading platform (Hyperliquid) and a sophisticated AI model (Claude). The emphasis on precise risk parameters and the inclusion of a dedicated plugin for AI code generation lowers the barrier to entry for those looking to experiment with or build upon AI-driven trading systems. The project's structure, including its Python base and package management files like pyproject.toml and requirements.txt, provides a clear blueprint for similar agent development.
Practical impact
Builders can explore the Pathiel repository to understand the implementation of an AI trading agent that combines LLM capabilities with structured trading protocols. The availability of the Claude Code plugin suggests potential for rapid prototyping and iteration of trading strategies. The project's recent release indicates ongoing development and support. Interested parties can examine the code, particularly the MCP integration and risk management logic, to adapt it for their own trading environments or to contribute to the project. The repository has 36 stars and 10 forks, indicating a level of community interest.
Caveats and source limits
The provided metadata indicates a recent release and a focus on specific trading functionalities. However, details regarding performance benchmarks, specific backtesting results, or comprehensive usage guides are not present in the repository summary. The exact nature and scope of the "oil and metals desk briefs" are not elaborated upon. Furthermore, while the project is open-source under the MIT license, information on community support channels beyond GitHub issues, or detailed documentation beyond the README, is limited. The metadata does not specify the exact version of Claude or the Claude Code plugin used, nor does it detail the specific requirements for running the agent beyond the presence of a Dockerfile and requirements.txt.
Sources
Claim check: 10/10 supported claims - 10 evidence links - 100% avg confidence
- Pathiel is an AI trading agent for Hyperliquid that uses Claude to trade perpetuals via MCP.supported - github.com
- The agent places orders with an exact stop and target.supported - github.com
- The default risk setting is 3x leverage / 1% risk per trade.supported - github.com
- The project includes oil and metals desk briefs.supported - github.com
- A free Claude Code plugin is available.supported - github.com
- The project is written in Python.supported - github.com
- The latest release was on November 13, 2026.supported - github.com
- The repository has 36 stars.supported - github.com
- The repository has 10 forks.supported - github.com
- The project is licensed under MIT.supported - github.com
Caveats
- Single-source caution: verify critical details at the linked source.
Radar score 86/100 - how it was calculated
- Reliability 82: GitHub metadata supports source trust
- Freshness 100: Fresh GitHub release date
- Novelty 73: Fresh GitHub release
- Technical 77: Repository technical metadata
- Developer 96: Developer tooling signals
- Ecosystem 72: Fresh GitHub release
- Confidence 100: Claims have reliable evidence
Discussion
Loading comments...