Explore AI Tools & Apps

Crewdle

Crewdle · Coding

Crewdle is a pay-as-you-go AI agent platform built for small businesses. Instead of juggling separate AI subscriptions, you hire autonomous AI agents that take a job, do it, ask when a decision is yours, and remember for next time. Multi-model AI chat, content creation, website and app building, and workflow automation all sit under one login and one bill, so teams can put AI to work without adding a seat license or a server to manage.

Sipcode

Anuj Ojha · Coding

Sipcode is a free command-line tool that sits between you and Claude Code and keeps your context window clean. It rewrites bulky tool commands before Claude reads them, measures the tokens you save, and warns you when a session starts to drift off course. It ships as an open-source CLI tool under the MIT license and makes zero network calls during normal use, so your code and transcripts never leave your machine.

Sakana Fugu

Sakana AI · Coding

Sakana Fugu is a multi-agent AI model orchestration system from Sakana AI that ships as a single OpenAI-compatible API. Instead of training one bigger model, it learns to assemble and coordinate a pool of specialized agents and hands you the combined result as if you called a normal model. Think of it as a model orchestration API you point at once. You pick a tier (Fugu, Fugu Ultra, Fugu Max, or Fugu Cyber), send your usual request, and let the system decide which models do the work. The company bills it as a frontline AI API for complex, multi-step jobs.

LogStitch

LogStitch · Coding

LogStitch is a native macOS app that turns raw Amazon CloudWatch Logs into readable AWS Lambda invocations. Instead of scrolling a timestamp-sorted river of interleaved log lines, it reads the request ID on each line and weaves the events from one execution back together, across every function an incoming request touched. It runs locally, keeps your AWS credentials in the macOS Keychain, and adds built-in analytics plus a local MCP server so AI assistants can query stored logs while you debug. It's macOS only. Near the end of the piece we explain who that suits and who it leaves out.

BestDefense.io

BestDefense.io · Coding

BestDefense.io is a continuous security validation platform built around its Vortex engine. It maps your attack surface on every deploy, runs exploit-confirmed AI pentests, writes code-fix pull requests for what it finds, re-tests the original exploit chain, and generates audit-ready compliance evidence. Think of it as automated pentesting that runs on your own machine before code ever reaches the main branch. It's aimed at engineering and security teams that ship often and can't keep a manual pentest schedule in step with their release cycle.

Conduit

South Forge AI · Coding

Conduit is a free, open source local MCP gateway that gives every AI client on your machine one shared set of MCP servers. Instead of pasting the same server config and API key into Claude, Cursor, Codex, and VS Code over and over, you set up a server once and switch it on everywhere. The gateway also loads tool definitions on demand, so agents search for what they need instead of carrying hundreds of tool descriptions in every request. South Forge AI now ships the product under the name Toolport. The original Conduit branding and repository are still what most early users know.

REAPER Daemon

Dead Pixel Design · Coding

REAPER Daemon is a free, open-source REAPER MCP server and file bridge from Dead Pixel Design that lets an AI agent control REAPER with AI on macOS, Windows, or Linux. Instead of opening a port or installing an extension, it watches a folder: your agent writes a JSON command file, a Lua loop inside REAPER runs it against the native API, and the answer comes back as JSON. Ask Claude to help mix your session and every change lands inside a REAPER undo block, so a single Cmd+Z takes it back like anything you did by hand. For Claude REAPER integration without a server, this is the whole trick: REAPER automation happens one JSON file at a time.

Atomic Mail Agentic

Atomic Mail · Writing · Coding

Atomic Mail Agentic is an agent-native email service. It's built for AI agents rather than people. Any agent can claim a self-registering agent inbox, then read, send, and respond to messages on its own through a standard JMAP and REST JSON API. It ships with MCP and AgentSkill integrations, and it leans on Proof-of-Work and reputation checks that keep spam out while letting an agent recover from its own errors without a human stepping in at any point.

Beacon

ForgeFast Labs · Coding

Beacon is a local-first security scanner built by ForgeFast Labs that reviews the code AI assistants write. It runs inside your editor and alongside Cursor, Claude Code, GitHub Copilot, Windsurf, and Zed, checking every line for leaked secrets, injection shapes, broken authorization paths, and unsafe sinks the moment it's written. Findings come back as fixes rather than tickets, and your code never leaves your machine.

Agent 37 Cloud

Agent 37 · Coding

Agent 37 Cloud is a hosted sandbox platform for AI agents. One call to its agent hosting API gives each of your users their own always-on, isolated computer, with files, memory, terminal access, and connections to Gmail, Slack, and 1000+ apps. It's built for teams that want to ship an agent product without running their own servers. And you pay only for the compute and disk each sandbox uses. Why does that matter? Running one agent is easy. Running a thousand isn't.

pumaDB

pumaDB · Coding

pumaDB is a hosted memory layer that lets AI agents and small apps keep durable JSON records without running a database. You connect an MCP client like ChatGPT, Claude, or Codex to one shared endpoint, or call a REST API from trusted server-side code, and the same rows show up everywhere. It's built for facts, decisions, preferences, and handoff notes that would otherwise vanish when a chat ends.

MeshPilot

Jenesh Patel · Coding

MeshPilot is a desktop workspace for running several AI coding agents on one project at the same time. Instead of juggling terminal tabs and copy-pasting context between them, you get persistent terminals, a shared task board, and project memory that every agent can read. It bundles three pieces. MeshConsole is an AI coding agent workspace where agents run. MeshMCP is the coordination layer they share. MeshUtility is a free dictation and prompt-rewriting widget. You bring your own agents, from Claude Code and Codex to Cursor and Gemini, and MeshPilot stays the workspace rather than the model. It isn't the agent. It's where the agents live.