Hunter Bown Claim this profile

Open-source, community-driven agent harness

Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converge on answers.

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

Unofficial Hermes Agent skill pack built from fantasy spell and skill names

No description.

RLM agent harness - built on Deep Agents

Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon

No description.

Logic architecture inspired by Toulmin. Forces LLMs into structured, sequential reasoning through Toulmin's argumentation model.

Deterministic domain encoders with embedding-space arithmetic (IEEE-754 semantics)

NVIDIA capability registry and Spark-aware routing layer for Hermes Agent and NemoClaw users

Logic architecture for abductive inference. Forces LLMs to make uncertainty visible through explicit hypothesis generation and Inference to Best Explanation.

A repository cleanup skill inspired by Marie Kondo's KonMari Method

Orchestrate coding agents remotely from your phone, desktop and CLI

Terminal-first control plane for NVIDIA Nemotron — agentic coding, RAG, doc-ops, and multi-model formations.

Apple Silicon MLX fine-tuning toolkit — SFT, DPO/ORPO, GRPO, distillation, and OpenAI-compatible serving.

No description.

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Multi-perspective reasoning harness: query multiple LLM CLIs in parallel with different perspectives

Agentic harness for keeping research-oriented LLM runs on-task with contracts, evidence, dialectics, verification, and anti-slop gates

MathCode: A Frontier Mathematical Coding Agent

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

EXO Gym is an open-source Python toolkit that facilitates distributed AI research.

Zig runtime for Recursive Language Model workflows, inspired by alexzhang13/rlm

Run frontier AI locally.

Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Qwen Code, iFlow as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 2.5 Pro, GPT 5, Claude, Qwen model through API

🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

Superlinked Inference Engine is an Open-source inference server and production cluster for embeddings, reranking, and extraction.

Hermes profile + skill pack for structured engineering work via the ten Orders of the Knights Radiant

No description.

OpenWarp is a free version of the open source client based on warp

No description.

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

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

Self-verifying agent workflow starter for real software projects.

A meta-harness for all your AI agents. Omnigent provides a common layer over Claude Code, Codex, Pi, and the agents you write yourself: swap or combine harnesses without rewriting, keep them in check with policies and sandboxing, and collaborate in real time on the same live session, from any device.

The agent that grows with you

No description.

No description.

DSPy reasoning harness for four-corner (P, not-P, both, neither) analysis of hard questions

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.

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.

MLX: An array framework for Apple silicon

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

[KernelGYM & Dr. Kernel] A distributed GPU environment and a collection of RL training methods to support RL for Kernel Generations

CAP — Capability Application Package: signed, content-addressed app bundle format (spec + CLI + runtime)

🙌 OpenHands: AI-Driven Development

OpenWiki is a CLI that writes and maintains agent documentation for your codebase.

🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Registry of agents implementing the Agent Client Protocol (ACP)

An open-source database of AI models.

Unified realtime agent trace database & search MCP

Terminal pixel-art office for AI coding agents

📦 The default bucket for Scoop.

Build and run agents you can see, understand and trust.

NeMo Data Designer-first synthetic data framework with DSPy compilation and GEPA optimization.

No description.

No description.

CUDA/Triton kernel optimization and runtime patching for LLM inference

Public repository for Agent Skills

You like pytorch? You like micrograd? You love tinygrad! ❤️

Train the smallest LM you can that fits in 16MB. Best model wins!

OpenShell is the safe, private runtime for autonomous AI agents.

No description.

Local CLI runtime adapters for DSPy — run DSPy programs through Codex, Qwen, and Claude CLIs with full GEPA optimizer support

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

DSPy: The framework for programming—not prompting—language models

MCP server for recursive market analysis. Yahoo Finance + CoinGecko + sandboxed Python + RLM sub-queries via claude/codex/gemini/copilot CLI. Zero API keys required.

General plug-and-play inference library for Recursive Language Models (RLMs), supporting various sandboxes.

Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.

LLM inference in C/C++

No description.

The open source coding agent.

slime is an LLM post-training framework for RL Scaling.

🦜🔗 The platform for reliable agents.

An Open-Source Asynchronous Coding Agent

A high-throughput and memory-efficient inference and serving engine for LLMs

No description.