Top Picks

Hotcell is a self-hostable sandbox SDK for AI agents that runs isolated sandboxes on local hardware or servers. The page shows setup, CLI commands, key handling, egress control, and support for containers or microVMs.

Browser automation CLI for AI agents with anti-bot handling, human takeover, parallel multi-session browsing, and isolated multi-account workflows.

Projektor is a self-hosted issue tracker and wiki built for AI agents as the primary client, with MCP-based agent access and Cloudflare-based deployment.

Open-source security research tool for auditing Python AI agents and codebases with AST analysis and Docker-based runtime verification.

A local-first Windows tool for indexing, searching, and loading large agent skill libraries without keeping full skill bodies in context. It supports SQLite FTS5 search, multiple ranking modes, CLI use, HTTP, and MCP stdio.

A CLI tool that keeps Claude Code and Codex configs in sync, with drift detection, backup-on-write, and a visual board for comparing host-side agents, skills, hooks, and MCP servers.

Open-source runtime action grounding framework for AI agents. It verifies proposed agent actions against live systems of record before execution and can return allow, hold-for-human, or block decisions.

A VS Code extension that organizes Claude Code and Codex sessions around Git worktrees, keeping sessions, terminals, changed files, and provider tabs in one cockpit.

A research project and interactive visualization on how agent-generated code behaves after merge in real-world open source repositories, with a paper, replication package, and data-driven findings.

A hosted MCP server for time and date utilities, including timezone lookup, calendar info, timestamp conversion, Unix time, and Alphadec conversion. The README says it works with Claude.ai, Claude iOS, Claude Code, OpenAI Codex, and any MCP-compatible client.

A command-line social media automation tool for developers and AI agents. It supports posting and scheduling across multiple networks, JSON output, schedule files in git, validation before publish, and integrations for CI and agent workflows.

Local-first macOS app for recording, live transcription, speaker labeling, and AI-assisted meeting notes. It connects to MCP clients so an AI can follow the conversation live and produce advice, action items, and recaps.

Self-hosted registry for AI agents and MCP servers that supports capability-based discovery, health checks, and simple JSON/HTTP registration.

A lightweight Flask-based LLM proxy that forwards Ollama, OpenAI, and llama.cpp-style requests to NVIDIA’s OpenAI-compatible API, with streaming support, retries, caching, auth, and usage stats.

A local Anthropic-compatible proxy that lets Claude Code work through ChatGPT, Kimi, Grok, or Cursor subscriptions, with provider routing, diagnostics, and model mapping.

AI translation workspace with memory for terminology, tone, glossaries, styleguides, and review workflows. Built for translators, content creators, and localization teams.

Open-source compiler that turns a SKILL.md into a typed, runnable agent harness. The page explains the architecture, the compile/run flow, and how it aims to make agent behavior more faithful across small, local, or frontier models.

A browser-driven tool that exports ChatGPT conversations and files from personal or Business/Team accounts into a local, searchable offline archive with a single-file HTML viewer.

Open-source input scanner for AI agents that strips hidden instructions and scans text, files, images, PDFs, QR codes, audio, and video before they reach an agent.

A macOS terminal app that lets AI agents “live” in a shared environment with the user, with customizable scenes, UI, and behavior packs.

Go-native CLI proxy that reduces noisy command output before it reaches an LLM context, with retention checks, exit-code preservation, and token-saving history.

A GitHub repository that auto-saves Claude Code sessions to a private repo, with plaintext transcripts for review and age-encrypted JSONL for full restore.

An interactive calculator for AI product unit economics. It models token costs, retries, prompt caching, model routing, infrastructure, support, and target gross margin, and can share scenarios through URL links.

CLI utility that counts LLM tokens in files or directories, with support for stdin, recursive scans, file-type grouping, profiles, JSON output, and multiple encodings.