This article provides a hands-on coding guide to explore nanobot, a lightweight personal AI agent framework. It details recreating core subsystems like the agent loop, tool execution, memory persistence, skills loading, session management, subagent spawning, and cron scheduling. The tutorial uses OpenAI’s gpt-4o-mini and demonstrates building a multi-step research pipeline capable of file operations, long-term memory storage, and concurrent background tasks. The goal is to understand not just how to *use* nanobot, but how to *extend* it with custom tools and architectures.
This research introduces a novel robot operating system (ROS) framework designed to seamlessly integrate large language models (LLMs) into embodied artificial intelligence. The framework enables robots to interpret and execute natural language instructions with greater versatility and reliability.
Key features include automatic translation of LLM outputs into robot actions, support for both code-based and behavior tree execution modes, and the ability to learn new skills through imitation and automated optimization.
Extensive experiments demonstrate the robustness and scalability of the framework across diverse scenarios, including complex tasks like coffee making and remote control. The complete implementation is available as open-source code, utilizing open-source pretrained LLMs.
Key features include automatic translation of LLM outputs into robot actions, support for both code-based and behavior tree execution modes, and the ability to learn new skills through imitation and automated optimization.
Extensive experiments demonstrate the robustness and scalability of the framework across diverse scenarios, including complex tasks like coffee making and remote control. The complete implementation is available as open-source code, utilizing open-source pretrained LLMs.
In 1988, while reading a book about UFOs at Xerox PARC, Rob Tow overheard a discussion about embedding barcodes in documents to link them to digital files. He found this idea visually unappealing and instead had an epiphany: he could embed digital data within halftone images in a way that was imperceptible to the human eye.
Tow's idea involved using tiny, angled halftone dots to represent binary data, with left-leaning dots for zeros and right-leaning dots for ones. This method allowed for the embedding of significant amounts of data without affecting the image's appearance. He calculated that this approach could store kilobits of data in a small area, far more than traditional barcodes.
Tow submitted an invention disclosure for this concept and later developed a variant that utilized color and intensity variations below the threshold of human perception. Both ideas were patented. The technology, named "DataGlyph," was developed further with additional features like binary morphology image conditioning and error correction.
The term "DataGlyph" was derived from "Glyph," a term popularized by the musician Prince to denote his identity after a legal dispute. The technology became a real product offered by Xerox under the name "Smart Paper."
Several patents were issued for the DataGlyph technology, including a basic patent (U.S. Patent no. 5,315,098) and others related to adaptive scaling and self-clocking glyph codes.
Tow's idea involved using tiny, angled halftone dots to represent binary data, with left-leaning dots for zeros and right-leaning dots for ones. This method allowed for the embedding of significant amounts of data without affecting the image's appearance. He calculated that this approach could store kilobits of data in a small area, far more than traditional barcodes.
Tow submitted an invention disclosure for this concept and later developed a variant that utilized color and intensity variations below the threshold of human perception. Both ideas were patented. The technology, named "DataGlyph," was developed further with additional features like binary morphology image conditioning and error correction.
The term "DataGlyph" was derived from "Glyph," a term popularized by the musician Prince to denote his identity after a legal dispute. The technology became a real product offered by Xerox under the name "Smart Paper."
Several patents were issued for the DataGlyph technology, including a basic patent (U.S. Patent no. 5,315,098) and others related to adaptive scaling and self-clocking glyph codes.
Paul Sawers writes that Zed has launched Delta, a collaborative development platform now in public beta that replaces pull requests with shared threads preserving the full conversation between developers and coding agents. The move responds to both volume pressure on GitHub — monthly commits jumped from roughly 1 billion in 2025 to 2.9 billion by August 2026 — and a structural mismatch: when much of the reasoning behind a change happens inside an agent conversation, a bare diff gives reviewers little context. Zed has already disabled pull requests on Delta's own repository, where 33 developers have landed 570 changes to main through threads, and co-founder Nathan Sobo expects the company to fully leave GitHub within a few months.
- DeltaDB, the version control layer beneath Delta, records individual edits and conversation events between Git commits, a finer granularity than Git's commit-based model; Zed calls these individual records "deltas."
- Sobo predicts the thread will replace the commit or branch as the fundamental unit of software development, with commits remaining only as checkpoints.
- Competitors share the thesis: SpaceX-owned Cursor launched Origin in August 2026, and GitLab has Project Switch in private beta.
- Delta works with existing Git repositories, so contributors who don't adopt it can still submit conventional pull requests; the platform is free during public beta with paid plans to follow.
- Zed raised $32 million from Sequoia Capital in August 2025, a round that also teased DeltaDB.
- DeltaDB, the version control layer beneath Delta, records individual edits and conversation events between Git commits, a finer granularity than Git's commit-based model; Zed calls these individual records "deltas."
- Sobo predicts the thread will replace the commit or branch as the fundamental unit of software development, with commits remaining only as checkpoints.
- Competitors share the thesis: SpaceX-owned Cursor launched Origin in August 2026, and GitLab has Project Switch in private beta.
- Delta works with existing Git repositories, so contributors who don't adopt it can still submit conventional pull requests; the platform is free during public beta with paid plans to follow.
- Zed raised $32 million from Sequoia Capital in August 2025, a round that also teased DeltaDB.
This paper details the reconstruction and execution of the Logic Theorist (LT), considered the first artificial intelligence program, originally created in 1955-1956. The authors built a new IPL-V interpreter in Common Lisp and faithfully reanimated LT from code transcribed from a 1963 RAND technical report. The reanimated LT successfully proved 16 of 23 theorems from Principia Mathematica, consistent with the original system's behavior. This work demonstrates "executable archaeology" as a method for understanding early AI systems, highlighting the challenges and insights gained from reconstructing and running historical code.
