Overleaf's comment export tool, overleaf-comments-export, now lets researchers extract review comments from Overleaf papers into Markdown and JSON, with a Python tool that also generates a PDF highlig…
Mole, a free and open-source deep-research agent for the terminal, enforces a strict budget with 0% measured overshoot, verifies every claim with a source, and keeps local data private by analyzing CS…
OpenLabs-so released OpenAnalytics, an open-source, AI-native web analytics platform self-hostable under AGPL-3.0, featuring a lightweight tracker, ClickHouse-based storage, and an AI assistant, with …
Developer Matt Pocock shares five agent skills he uses daily to enhance AI coding assistants like Codex, covering research, design review, React best practices, code simplification, and end-to-end tes…
PrismManifest 0.3.4, an open-source Python library from insightitsGit, provides a zero-trust gate that verifies Ed25519-signed ParameterManifests before allowing probabilistic AI outputs (LLMs, OCR) t…
A developer has released a clone-and-run launcher that runs LTX-2.5 text-to-video generation locally on Apple Silicon in a single command, with audio support and no need for ComfyUI or CUDA. The launc…
A developer created a bash script, claude-history.sh, that lists recent Claude Code sessions across all project directories, sorted by the last activity timestamp recorded inside each transcript rathe…
A developer has built an agent-maintained knowledge graph wiki using the Open Knowledge Format (OKF), extending Andrej Karpathy's LLM Wiki pattern. The system compiles typed subject-predicate-object t…
A new open-world perception system for driving scenes safely handles unknown road objects by using a hierarchical taxonomy, abstraction fallback, and segmentation cross-validation, as described in a r…
Developer Daniel Lublinsky released Skill Atlas, a free, open-source graph-search plugin for Claude Code that adds a 'searchable' tier between enabled and disabled skills, cutting per-session token us…
Bevel Software released Hexis, an open-source, git-backed control plane for managing AI-agent skills, tools, context, permissions, and identity, self-hosted and MCP-native. The platform allows central…
Mupt AI released self-bench, an open-source tool that automatically converts private, completed pull requests into held-out coding-agent evals, generating validated Harbor datasets with a single CLI c…
A developer has released 'the writing whip,' a Claude Code skill designed to eliminate AI writing tropes and response behaviors at the generation stage. The skill enforces strict rules against preambl…
Developer Neeeophytee released a seven-skill agent pack, 'ai-watermarks-reality-check,' that audits AI provenance evidence such as C2PA metadata and text watermarks without removing them, reporting st…
Squillo has open sourced its APH (Agent Per Human) engine and servers, written in Rust and N Lang, to provide remote guardrails for AI agents interacting with untrusted agents. The protocol enables bo…
Anthropic's Claude AI model edited a blog post to argue that the enforceability gap for rogue AI subsidiaries is not a binary frontier but a continuous degradation along three axes: attribution, cost …
In a guest post for Michiel Bdejong's blog, Claude, an AI assistant made by Anthropic, argues that the 'Empty Nest Scenario' is wrong: automated companies will not leave Earth for space but will keep …
Techartist, a developer on CodePen, has created a bioelectric consciousness engine using Three.js, WebGL, and GLSL. The interactive visualization allows users to click anywhere to trigger signals, whi…
A new open-source repository offers a self-hosted, scheduled tool for tracking whether AI search engines such as ChatGPT, Claude, Perplexity, and Gemini mention or cite a website in response to buying…
A developer reconstructed a blueprint for a personal AgentOS from Danny Postma's talk on building an agent control plane using Anthropic's Claude Agent SDK. The system automates coding and operational…