The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visualization-of-Thought and Chain-of-Thought reasoning to elicit spatial reasoning and perception, emulates, plans and simulates synthetic HID interactions.

Situational Awareness Server compatible with TAK clients

[NeurIPS 2025 spotlight] Official implementation for "FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving"

Syzygy-of-thoughts

PyTAK is a Python package for rapid Team Awareness Kit (TAK) integration.

cot_reports is a Python library for fetching the Commitments of Trader reports of the Commodity Futures Trading Commission (CFTC). The following COT reports are supported: Legacy Futures-only, Legacy Futures-and-Options Combined, Supplemental Futures-and-Options Combined, Disaggregated Futures-only, Disaggregated Futures-and-Options Combined, Tr…

Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision

[ACL 2025] The code repository for "Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning" in PyTorch.

Display Aircraft in TAK - ADS-B to TAK Gateway

Lean implementation of various multi-agent LLM methods, including Iteration of Thought (IoT)

[NIPS 2025] Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search

aprscot - APRS to TAK Gateway.

This is an early exploration to introduce Interleaving Reasoning to Text-to-image Generation field and achieve the SoTA benchmark performance. It also significantly improves the quality, fine-grained details and aesthetic aspects of generated images.

Display Ships in TAK - AIS to TAK Gateway

Display Aircraft in TAK

Garmin inReach to Cursor on Target (CoT) Gateway, for TAK Products.

Code for the 2025 ACL publication "Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs"

超简单复现Deepseek-R1-Zero和Deepseek-R1，以「24点游戏」为例。通过zero-RL、SFT以及SFT+RL，以激发LLM的自主验证反思能力。 About Clean, minimal, accessible reproduction of DeepSeek R1-Zero, DeepSeek R1

Python Cursor on Target (CoT) is a Python Module for serializing CoT Events for use with TAK clients & servers

Official repository for "CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation"