Tag
This documentation describes the assertion language in the Ciao Prolog system, which allows annotating code with type and instantiation mode declarations for debugging, testing, optimization, and autodocumentation.
Documentation for integrating Voice AI with VICIdial, showing that existing dialer infrastructure can be used with AI voice agents rather than requiring a full replacement.
New documentation page for rendering Agent Traces on the Hugging Face Hub has been released.
Moxie Docs provides living documentation and MCP context for GitHub repositories.
Anthropic published a detailed engineering overview of the sandbox techniques used to contain Claude across its products including Claude.ai, Claude Code, and Claude Cowork, covering process sandboxes, VMs, filesystem boundaries, and egress controls. The article explains the rationale and technologies (gVisor, Seatbelt, Bubblewrap) and mentions the srt open-source tool.
Aden is a referential context compiler that creates a traversable knowledge graph from source code and documentation, enabling AI coding assistants to have surgical context instead of information overload.
Matt Pocock recommends writing Architecture Decision Records (ADRs) for agents to capture non-obvious decisions, making agents in the stack smarter with minimal documentation.
MIT researchers compiled the 2025 AI Agent Index, documenting 30 deployed AI agents from major labs, yet only 4 had public documentation explaining what the agent does, its limitations, and failure modes, revealing major transparency gaps.
DSPy has a new front page and documentation for easier onboarding, and is approaching a major DSPy 4.0 release with radical new ideas.
A tweet by Matt Pocock emphasizing that a tool or library is well-documented and portable.
It is recommended to directly view the official Hermes Agent architecture documentation and use Codex or Claude Code to open the project codebase, letting the Agent explain the code for deeper understanding.
User shares agreement with the views from YC's video on AI-native company organizational structure, including burning tokens instead of heads, letting AI fully autonomously execute tasks, and the importance of documents as core assets.
AgentLantern is an open-source devtool for AI agent projects that helps document, analyze, validate, and visualize agent workflows, with initial support for CrewAI and plans to extend to other frameworks.
This paper presents Reversa, a multi-agent framework that converts legacy software into traceable operational specifications for AI agents, enabling safer modifications and migrations. It includes an exploratory case study on migrating an ATM from COBOL to Go.
Matt Pocock proposes documenting agreed test seams in apps, arguing that AI agents cannot be trusted to make good testing decisions, often leading to fragile tests that break on implementation changes.
This article explores why GitHub is a better foundation for knowledge collaboration than traditional documentation systems in the AI agent era, due to its advantages such as open collaboration, AI model familiarity, local full context, and structured raw data.
PRD-Manager is an open-source Claude Skill that assists Vibe Coding. It uses 8 structured documents to convert vague ideas into AI-consumable requirements, preventing AI from deviating.
dari-docs is a CLI tool that tests documentation quality by simulating AI agents performing tasks, identifying where agents get stuck, and optionally generating proposed edits to improve doc clarity.
Nanobot announced collaboration with Atomic Chat HQ to simplify local-first agent workflows, with updated docs for running nanobot with local models on a user's own machine.
Owlish is a product that uses AI agents trained on your documentation to reduce support volume.