Unofficial Hermes Agent skill pack built from fantasy spell and skill names
倉庫
Hmbown 的倉庫
Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon
Build and run agents you can see, understand and trust.
The AI-Q NVIDIA Blueprint is an open reference example for building intelligent AI agents that connect to your enterprise data, reason using state-of-the-art models, and deliver trusted business insights.
Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converge on answers.
Agentic harness for keeping research-oriented LLM runs on-task with contracts, evidence, dialectics, verification, and anti-slop gates
Astrophysical measurement instruments built on Bown's engineering principles — JWST channel diagnostics + GW ringdown coupling
An MCP server that gives AI agents correct timezone, scheduling, and interval operations
Agent skill - clarifies and documents code for readability, intent, and comprehension while preserving functionality
Deep Agents is an agent harness built on langchain and langgraph. Deep Agents are equipped with a planning tool, a filesystem backend, and the ability to spawn subagents - making them well-equipped to handle complex agentic tasks.
DSPy: The framework for programming—not prompting—language models
Local CLI runtime adapters for DSPy — run DSPy programs through Codex, Qwen, and Claude CLIs with full GEPA optimizer support
Run frontier AI locally.
Optimize prompts, code, and more with AI-powered Reflective Text Evolution
EXO Gym is an open-source Python toolkit that facilitates distributed AI research.