Top Picks

An open-source TypeScript framework for building reactive AI agents around a shared agentic environment. The README explains the event model, participant types, and basic installation and usage.

Local encrypted vault that captures supported AI assistant sessions from Claude, Codex, Cursor, OpenClaw, and similar tools, then normalizes and stores them for search and review.

A CLI proxy that lets Claude Code run against DeepSeek V4 Pro, OpenRouter, Fireworks AI, or Anthropic-compatible backends while keeping the same agent workflow.

An open agent-identity protocol with a shipped reference implementation, TypeScript SDK, conformance test vectors, and protocol docs for identity, discovery, payments, and audit flows.

Rinhelp is an AI support diagnosis tool for technical support teams. It starts from Crisp support threads, pulls evidence from GitHub and Sentry, and returns a reviewable diagnosis draft for internal use.

A native macOS app that uses Claude to act as an autonomous coding agent for Apple platform development. It can inspect an Xcode project, make edits, build, launch, and validate changes with xcodebuildmcp and UI automation.

AISA is a free conversational AI skills assessment that scores how people use AI, generates a report and growth plan, and offers a shareable credential for individuals and teams.

A local tool that estimates GitHub Copilot AI-credit costs from usage data and generates an HTML report. It pulls from VS Code, OpenCode, Pi, Copilot CLI, and Copilot for Xcode, with CLI options for date ranges, model mapping, and JSON output.

Open-source harness for executable security regression testing of agentic applications and MCP-integrated systems, with scenario files, policy assertions, trace-based evaluation, and JSON output for CI or local use.

A macOS desktop workspace for AI-assisted development that combines chat, Kanban, repo browsing, subagent tracking, and local code review.

Sitedropper is an agent-friendly deployment and hosting platform that turns prompts, ZIP uploads, or REST requests into live HTTPS URLs. The page shows support for Claude Code, Codex, Cursor, Antigravity, and Pi through MCP, plus a browser-based draft/share flow and custom domain support.

A lightweight CLI for running RAG over local documents, with hybrid vector + BM25 retrieval, OCR for scans and images, and support for local or API-based LLMs.

Private AI agent for Android that helps users fix settings and troubleshoot phones with guided steps, deep links, and local memory.

A Godot and Rust desktop PTY multiplexer with tiled panes, persistence, CLI control, and MCP integration for AI agents and automation tools.

A Python SDK that provides LiteLLM-style model routing and translation with a smaller surface area. It supports completions, streaming, embeddings, tool calling, async variants, provider mapping, and local OpenAI-compatible backends.

A detailed post from pact0 about testing whether blank AI agents could complete a real product workflow, what failed, and the fixes they shipped after the audit.

ObserverBench is an interactive benchmark and guided demo for testing whether internal AI monitoring methods help make safer decisions, not just better predictions. It includes real-model results, benchmark tasks, and a no-login walkthrough showing how warning scores affect review and harm that slips through.

OpenAI’s documentation for its Agents API, covering how to build and run cloud agents with the OpenAI platform. The page surfaces core concepts, quickstart material, SDKs, webhooks, tracing, tools, and related agent-building resources.

A90 presents a tiny guestbook canvas where people draw and sign with passkeys, while AI agents can submit artwork through a documented proof-of-work flow. The page explains the human and agent paths, the submission protocol, and how the Imprint Index works.

LeanGuard is a Lean 4-based runtime guardrail system for agent tool use, with native temporal policies, Python integration, and optional MCP support.

A web calculator that estimates the electricity use and carbon emissions of AI token usage, with everyday comparisons, example workloads, and a detailed methodology page.

Open-source text-to-SQL engine tuned to your own database, with configurable pipeline stages, policy checks, and an evaluation harness for measuring performance on real schemas.

A Linux desktop app for managing multiple AI helpers with separate roles, memory, provider connections, and isolated computer workspaces.

Hazzel is a small terminal coding agent for working directly in a codebase. It reads files, edits with diff approval, runs commands with permission, and supports git-aware actions, with multiple model providers and bring-your-own-key setup.