Trending

Anthropic’s research post shows Claude proving security properties across 123 open-source libraries and discusses how LLMs can support formal verification workflows for real software.

Self-hosted memory layer for coding agents. It stores notes as Markdown in a local folder and exposes them over MCP so tools like Claude Code, Codex, and Cursor can recall shared context.

A Claude Code plugin marketplace with 42 skills for building, shipping, and announcing apps across App Store, Google Play, Mac, Windows, and web workflows.

Hybro is an open-source interoperability layer for AI agents, with a FastAPI backend, Next.js dashboard, CLI setup, and support for the A2A protocol and MCP server integration.

A Claude Code plugin that wraps MCP tool use in a single sandboxed JavaScript program, reducing tool-call chatter and keeping intermediate results out of context.

Galahad is an AI memory layer that saves and restores model KV cache, supports document recall, and plugs into vLLM, SGLang, and llama.cpp. The page also shows agent features like replay, branching, rewind, and fault-finding.

A browser-game playing agent that uses an LLM to train per-game rules and then makes live decisions through either a hosted engine (Jev) or a local engine (Laya).

An experimental repository showing an LLM-generated binary workflow: natural-language specs are turned into raw executable bytes, then tested in a loop with examples like a hello world, HTTP server, and Tetris.

A Vercel tutorial showing how to wire Jev into a TanStack Start app using TanStack AI and the Vercel Gateway adapter, with typed decision routing and server-side validation examples.

FDA is a developer tool for giving AI agents temporary, session-scoped access to machines with audit logs instead of standing SSH access.

Open-source Claude Skill plus MCP integration for job search and interview prep, with live job data, role-specific interview intel, answer scoring, resume scoring, and voice mock interviews as an upgrade path.

A local coding-agent setup that turns Ollama models into a private, verified team of specialist agents for coding workflows. It includes hardware-aware model selection, role assignment, permission-restricted workflows, and validation probes.

AgentTrace is a Python-based observability and runtime self-healing system for AI agent workflows. It logs multi-step tool calls, surfaces latency issues, and attempts to repair malformed LLM tool arguments before they crash a run.

An interactive Pong demo that compares Jev against Gemini 3.8 Flash, Claude Haiku 4.5, and GPT-5.6 Sol, highlighting response-time differences in a real-time game loop.

Open-source fork of JetBrains ThinkRail that turns Claude Code into a first-class terminal agent inside an IDE-like workbench, with an IDE bridge, session revival, plugin API, and MCP-backed workspace tools.

A pastebin-style publishing tool for AI agents to upload single-file HTML artifacts, dashboards, and reports, with clean shareable URLs and MCP support.

Skillzero is a developer tool for managing agent skills to reduce context bloat and token usage. It can hide skills from the model, group related skills into collections, and manage updates through a CLI workflow.

A browser-based brainstorm canvas that grows ideas from a seed word using Chrome’s on-device AI, with no signup or backend.

A Claude Code plugin that blocks expensive file reads and delegates bulk reading and boilerplate generation to AiKA modes through Portal CLI actions. The page includes the plugin’s structure, setup steps, CLI commands, and sample usage for the bulk-reader and code-writer flows.

A Claude Code plugin that adds persistent semantic memory via MCP, with support for Cursor and Claude Code setup, plus exposed write/search tools.

A local-first authority layer for Markdown used by humans and AI agents to manage competing project documents, current sources, and review workflows.

A research article from Plicara Labs analyzing 1.9 million GitHub agent skills and how often they include code, with breakdowns by language, mention-to-code gaps, and writing language.

VT Code is a WebMCP browser code editor with a terminal-paired agent workflow and an in-memory fallback mode. The page shows workspace setup, pairing steps, review-before-writing controls, and a client-run evidence recorder.

A desktop Hacker News client that summarizes long threads, extracts key points with quotes, and lets you chat with loaded discussions using Claude Code or Codex CLI.