🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strategies, and evolve them in a sandbox — every order through machine approval, the LLM never on the order path. Multi-market, audit-grade.
npx add-skill mirror29/inalpha🦊 Open-source professional quant agent framework. Agents pick the factors working now to time entries, write full strategies, and evolve them in a sandbox — every order through machine approval, the LLM never on the order path. Multi-market, audit-grade.
6 production AI agents — LangGraph multi-agent systems, RAG pipelines, PDF translation, lead capture SaaS, WhatsApp agent, and document intelligence with Docker + PostgreSQL + pgvector. Built with Python, FastAPI, LangChain, Claude API and OpenAI.
Stop re-explaining yourself to AI. MARM offers persistent memory, cross-agent context sharing, write queues, swarm-ready presets, and compaction for clean recall. Includes a live web dashboard for managing memories, logs, and sessions. MCP connects over HTTP & STDIO and works with major LLMs like Claude, Codex, Grok, Gemini, and other models.
A portable agent skill (SKILL.md + reference playbooks) for writing top-conference embodied-AI papers — distilled from 63 papers (CoRL/RSS/ICRA/IROS/Science Robotics, 2022–2026). Works with any LLM agent that loads markdown context.
A convention-over-configuration, general-purpose agent framework: you can define, compose, and extend your agents simply by adding/writing Markdown files for agents and skills.
Claude Code plugin that turns your local session history into a daily work report — session cards + a structured recap
Claude Skill for end-to-end testing of HephMind content guardrails (Guardrail Pools) via API. Run /guardrail-test in Claude Desktop.