CodeWhale. Open-source, community-driven agent harness
40kaleph. Skill + MCP server to turn your agent into an RLM. Load context, iterate with search/code/think tools, converge on answers.
206Hegelion. Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)
168Wizards-of-the-Ghosts. Unofficial Hermes Agent skill pack built from fantasy spell and skill names
97homebrew-deepseek-tui. Ruby
61rlmagents. RLM agent harness - built on Deep Agents
50ZMLX. Triton‑style kernel toolkit for MLX plus a small upstream incubator: prototype, benchmark, and upstream fusions for Apple Silicon
46MiniMax-CLI. Rust
26Toulmini. Logic architecture inspired by Toulmin. Forces LLMs into structured, sequential reasoning through Toulmin's argumentation model.
17FluxEM. Deterministic domain encoders with embedding-space arithmetic (IEEE-754 semantics)
11NemoHermes. NVIDIA capability registry and Spark-aware routing layer for Hermes Agent and NemoClaw users
8peircean-abduction. Logic architecture for abductive inference. Forces LLMs to make uncertainty visible through explicit hypothesis generation and Inference to Best Explanation.
6KonMari. A repository cleanup skill inspired by Marie Kondo's KonMari Method
6divinecomedy. Python
5MLXSmith. Apple Silicon MLX fine-tuning toolkit — SFT, DPO/ORPO, GRPO, distillation, and OpenAI-compatible serving.
5NeMoCode. Terminal-first control plane for NVIDIA Nemotron — agentic coding, RAG, doc-ops, and multi-model formations.
5midtry. Multi-perspective reasoning harness: query multiple LLM CLIs in parallel with different perspectives
4autodialectics. Agentic harness for keeping research-oriented LLM runs on-task with contracts, evidence, dialectics, verification, and anti-slop gates
4Butterfly. Block-structured attention acceleration for long-context inference
2taste. Shell
2knightsradiant. Hermes profile + skill pack for structured engineering work via the ten Orders of the Knights Radiant
2CAP. CAP — Capability Application Package: signed, content-addressed app bundle format (spec + CLI + runtime)
1chronow. An MCP server that gives AI agents correct timezone, scheduling, and interval operations
1bashful. Python
1clarify. Agent skill - clarifies and documents code for readability, intent, and comprehension while preserving functionality
1Trimtab. Self-verifying agent workflow starter for real software projects.
1tetraframe-dspy. DSPy reasoning harness for four-corner (P, not-P, both, neither) analysis of hard questions
1good-hunt. Python
1zigrlm. Zig runtime for Recursive Language Model workflows, inspired by alexzhang13/rlm
1