Reasoning: open-source projects on GitHub
20 repositories on Reasoning, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
Vectorless RAG Index
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
★ 32,176 · PythonLLM FROM SCRATCH IN PYTORCH
The reasoning-from-scratch project shows how to build a Reasoning LLM from scratch in PyTorch, step by step. Implemented in Jupyter notebooks: architecture, training with
★ 5,831 · Jupyter NotebookSKYWORK-R1V VISION LANGUAGE AI
The Skywork-R1V model series combines vision and language for complex reasoning. Available in Python and already has over 3k stars.
★ 3,173 · PythonOPEN ONTOLOGIES AI ENGINE
Rust-based MCP server for creating, validating, and reasoning over RDF/OWL ontologies. Built-in Oxigraph, tabular reasoner, and SHACL.
★ 2,905 · RustRL FOR LARGE MODELS
Overview of modern reinforcement learning methods for large reasoning models, including theories and practical approaches.
★ 2,502 · TeXWFGY 5.0 POLARIS PROTOCOL
WFGY 5.0 — major open-source release for AI reasoning, RAG, agents and real-world workflows. 1752 ⭐
★ 1,752 · Jupyter NotebookSTARTLUX‑DECISION: AI DECISIONS
Open decision models from 0.8B to 27B give calibrated probability for each option in one pass and a short thought only when unsure. They serve as the available inference
★ 1,745 · PythonAI AGENTS: NEW PAPERS
A collection of the latest articles about AI agents, updated every two weeks. All implemented in Python.
★ 1,731 · PythonHAFT: SMART SOLUTION ENGINE
haft is an engineering solutions engine that tracks their obsolescence and maintains consistency through evidence decay and parity checking.
★ 1,338 · GoОБЗОР MULTIMODAL CHAIN-OF-THOUGHT
Обзор мультиmodal Chain-of-Thought: анализ методов, данных и benchmark для LLM и VLM. Включает таксономию, оценку и рекомендации.
★ 1,029 · TeXAWESOME AGENTIC DEEP RESEARCH
A collection of the best resources on agentic deep research from ACL 2026 KnowFM. Helps find cutting-edge methods and tools.
★ 876Nucleoid Logic for LLM
Nucleoid — a Rust logic language for building neuro-symbolic AI that learns and reasons alongside LLMs.
★ 770 · RustRELEVANT PAPERS ON REASONING LLM
Collection of the latest papers and benchmarks on reasoning with foundation models. Enables quick discovery of cutting-edge research and comparison of their performance.
★ 663RandOpt: Task Experts Optimization
Code for ICML 2026: diverse task experts are densest around pretrained weights.
★ 590 · PythonMATHCODE: MATHEMATICS CODES ITSELF
MathCode is a Shell agent that generates mathematical code and solves problems in real time. Ideal for researchers and engineers.
★ 509 · ShellNEUROARXIV: AI CHECKS ARXIV BEFORE CODING
A skill that eliminates the need to write code from scratch: Claude searches real papers on arXiv before proposing a new architecture. This reduces the risk of reinventin
★ 438 · TypeScriptGEOVISTA WEB-AUGMENTED AI FOR GEOLOCATION
GeoVista — official implementation of web‑augmented agentic visual reasoning for the geolocalization. In Python it combines the multimodal LLM and the web search, enablin
★ 281 · PythonONTOSPHERE – BROWSER RDF EDITOR
Ontology editor in the browser: load RDF from files, URL or SPARQL, draw nodes and edges, run OWL‑RL reasoning and apply various layout algorithms with clustering. Everyt
★ 265 · TypeScriptBENCHMARKS FOR CODE FROM LLM
Awesome-Code-Benchmark — an overview of key benchmarks for evaluating language models' coding abilities.
★ 250NYT Connections: LLM Benchmark
A benchmark based on 759 NYT Connections puzzles with additional trick words for evaluating LLMs.
★ 250 · PythonNew projects on this topic in Telegram
Telegram →