Sticky, a transparent AI Agent Studio, released v1.0.0 of its Windows desktop application that orchestrates a team of AI agents to build web pages with local backend execution.…
A developer released World Model MCP, a memory layer for AI coding agents that uses a temporal knowledge graph to prevent repeated mistakes, achieving a +10.2 point improvement on the SWE-bench Verifi…
Cisco released AI Defense Skill Scanner, a best-effort security scanner for AI agent skills that detects prompt injection, data exfiltration, and malicious code patterns using multi-engine detection i…
Developer Lore released Wayfinder, an open-source LLM router that determines whether to send a prompt to a local or cloud model by analyzing structural features like length, headings, and code, withou…
A developer starred a collection of GitHub repositories including snarktank/ai-dev-tasks (7766 stars), a task management system for AI dev agents, and FFmpeg/asm-lessons (12083 stars), which teaches a…
Age of Agents, a new open-source tool from Agents Mill, visualizes AI coding agent sessions as a real-time strategy game, turning each session into a settler in a pixel-art realm. The tool runs locall…
Veilus Digital released the cryptographic core of its Phantom Chat messenger as source-available code on GitHub, allowing independent verification of its post-quantum security claims. The package incl…
Deltatensors, a new open-source tool, compresses fine-tuned neural network model deltas into small .wdelta files, achieving near-lossless compression with sub-1% perplexity difference. Tested on Qwen2…
An open-source repository containing 817 structured cybersecurity skills for AI agents has been released, covering 29 security domains and mapping to six industry frameworks including MITRE ATT&CK and…
A new Claude Code skill called 'crispy-comments' automatically prunes verbose code comments, removing incidental history, defensive justifications, commented-out code, and ASCII-art banners to keep on…
Sakana AI launched Fugu, a multi-agent system delivered as a single model that dynamically orchestrates frontier models to tackle complex multi-step tasks. The system is accessible via the Sakana API …
A June 2026 research survey of six coding agents—Codex CLI, Kimi Code CLI, MiMo Code, Cursor, Antigravity CLI, and OpenCode—found that while all support a project-level AGENTS.md file, global instruct…
A developer released 'claudemax', a launcher for the Claude Code harness that restores extended-thinking summaries on Opus 4.7/4.8, re-enables the context-usage icon in VS Code, and adds a 'Copy as Ma…
A developer created a launcher script to run GLM 5.2 in the Claude Code harness, enabling the use of the GLM model via Anthropic's API. The script loads the API key from a private file, sets environme…
Ions, an open protocol for publishing and traversing evidence-backed claims called Cognitive Building Blocks (CBBs), has been launched. In a test, an 8B parameter model using the Ions network matched …
Developer Monish released NOVA-VAD, an open-source voice activity detector that achieves 93% accuracy on noisy audio, outperforming Silero, Pyannote, and WebRTC while remaining lightweight and explain…
A developer created a time-awareness hook for LLM agents like Claude Code that injects timestamps at a human-like cadence, keeping the agent oriented in time without filling the context window with no…
Researchers released DiffusionBench, a unified codebase for holistic evaluation of generative diffusion transformers across tasks like ImageNet and text-to-image generation. The benchmark supports tra…
Arabian Sand Boa is a Python script that rewrites if/elif conditions at the AST level, sending string conditions to an LLM for evaluation. The tool allows natural-language clauses to control program f…
Reachpad, an open-source markdown sharing platform for companies and AI agents, launched on Show HN. The platform allows AI agents to write documents via API or MCP while humans read rendered pages an…