18 projects
zigrlm
Python adapter for zigrlm, a Zig runtime for Recursive Language Model workflows.
aleph-rlm
MCP server for recursive LLM reasoning—load context, iterate with search/code/think tools, converge on answers
nemocode
Terminal-first control plane for NVIDIA Nemotron 3 — agentic coding, RAG, doc-ops, and multi-model formations.
zmlx
ZMLX: Metal-kernel toolkit and optimization lab for MLX on Apple Silicon. Fused MoE decode (+2-12% on LFM2/Qwen3.5), custom GPU kernels in one line, 70+ kernel catalog.
hegelion
Prompt-driven dialectical reasoning and autocoding for LLMs (thesis -> antithesis -> synthesis)
chronow
Chronow deterministic temporal engine Python bindings (CLI bridge)
rlmagents
RLM-enhanced agent harness with planning, filesystem, sub-agents, and profile-driven context isolation tools
MiniMax-CLI
Unofficial MiniMax CLI - downloads and runs the Rust binary
mlxsmith
Apple Silicon MLX fine-tuning toolkit — SFT, DPO/ORPO, GRPO, distillation, and OpenAI-compatible serving.
stash-rlm
External memory for AI agents - a mini RLM
midtry
Multi-perspective reasoning harness for coding decisions.
fluxem
Algebraic embeddings for deterministic neural computation across scientific domains
kytchen-rlm
Kytchen RLM - Recursive Language Models with BYOLLM pantry storage + sandboxed prep + sauce (audit trail)
kytchen-sdk
Python SDK for Kytchen - BYOLLM Context Orchestration
demyst
Scientific integrity linter for academic code
peircean-abduction
A Logic Harness for abductive inference. Anomaly in → Hypothesis out.
toulmini
Argumentation model: 7 components, 4 phases. Bad logic crashes. Good logic flows.
ariadne-router
Intelligent quantum simulator router with automatic backend selection
