Recently Evaluated

Self-hosted LLM proxy that redacts personal data before requests reach model providers, including inside tool-call arguments and multimodal content. It supports OpenAI-compatible clients, runs locally with zero telemetry, and uses Presidio plus an optional privacy filter for broader PII and secret detection.

An MCP server that lets two Claude agents connect through a short-lived, end-to-end-encrypted tunnel so they can collaborate directly without a human copy-pasting between chats.

Open-source CLI for spinning up disposable local or remote sandboxes for AI agents. It uses a manifest and Dockerfile to build fresh boxes, then exposes a single shell tool through MCP so an agent can work inside the sandbox without touching the host.

An open NDJSON specification for AI crawler ingestion and site content graphs, with examples and reference files in the repository.

Self-hosted agentic OS that connects AI engines like Claude Code, Codex, Hermes, and Ollama to messaging and email channels, with an emphasis on EU AI Act and GDPR compliance by design.

arXiv paper on a cache-merging method for multi-agent latent reasoning, framing KV-cache composition as a convergent replicated state with deterministic merging.

TaskPeace is an MCP-native task manager for AI coding agents. It gives agents one ranked queue to pull from, with a live cockpit for humans to monitor work, and supports Claude Code, Cursor, ChatGPT, and other MCP or REST-based agents.

A GitHub repository guide to running state-of-the-art LLMs on local hardware, with concrete build notes, cost breakdowns, and runnable configs for large models.

A side-pane companion for Claude Code that shows daily AI news and spaced-repetition concepts while the agent is working, then hides when it needs user attention.

A minimal, provider-agnostic agent loop for building custom AI agents with swappable memory, model, tools, and stop-condition seams.

A live, data-driven dashboard that tracks whether AI expansion is still intensifying or starting to cool, using infrastructure spend, data-center power, sovereign commitments, and supply-chain bottlenecks.

Mirrors turns production traces into an isolated, runnable copy of an AI agent’s environment so teams can replay workflows, reproduce bugs, and test changes safely before shipping.

A source-available JavaScript browser agent for asserting end-to-end behavior in real user sessions. The repo explains the annotation-based approach, how it runs in staging and production, and how to install and initialize it via CDN or npm.

An interactive CTF-style challenge where users try to break or exfiltrate data from sandboxed AI agents running in Declaw’s isolated runtime.

NamedLocal checks whether a local contractor business appears in AI-generated recommendations, then offers a free breakdown and a paid report with competitor and citation insights.

A GitHub repository presenting VSE Engine (Velocity & Structure Encoding), a prototype for computing over transmission using pulse-position and duration modulation ideas. The README describes a byte-splitting pipeline, time-slot mapping, and decode/resynthesis flow, with supporting source files in the repo.

Matrix OS is a cloud computer for background AI agents, offering persistent hosted workspaces with terminals, repos, previews, and agent sessions that keep running after your laptop closes.

SEOAgent is an SEO workflow tool for coding agents like Claude Code, Cursor, and Codex. It audits sites locally, suggests evidence-backed updates in the cloud, and syncs approved changes back into the repo.

Mission-control desktop app for running AI coding agents in parallel across Git worktrees, with inline code review, session isolation, and support for tools like Claude and Codex.

Deterministic CLI that scans AI-generated code for bad API integrations using AST-based rules. It supports providers like Supabase, Auth0, Firebase, Resend, Twilio, and OpenAI-related tools, and can be run directly or installed as an agent skill.

A free browser-based simulator for testing how AI agents affect a 35-person engineering org. It lets users change assumptions, compare scenario deltas, and share or export the result as OrgSpec YAML.

Python toolkit for building LLM agents with MCP servers, skills folders, memory, streaming, and metrics support.

Private skill search for AI coding agents. It helps an agent match abstract capability wishes to vetted skills without sending task details off machine.

Open-source companion tooling for agentic AI coding, built as a plugin and CLI around Anthropic Claude Code with support for related coding tools. The site shows setup, usage, and many concrete workflows for brainstorming, root-cause analysis, component discovery, decision support, document cleanup, and code analysis.