Software Engineering

Start with a working TypeScript AI app with built-in inference and a multi-agent runtime. In-app agents can research, read local files, understand documents and compose specialist models. Works offline, no API keys or complicated setup for your users. Customize and ship it to desktop, web or terminal in minutes 🚀

A coding agent you can talk to — in your terminal or on your phone. 1. Voice, both ways. Read one sentence (~10 sec) to enroll your voice. Consent-first; the delete key is yours. 2. 404 models on one account — Claude, GPT, Gemini, DeepSeek and more. OpenAI- and Anthropic-compatible. 3. MIT open source: github.com/yukihamada/sente Japan-built: Tokyo region, JPY billing. Honest limits: metered, not unlimited. Monthly credits; top up if you go over. We never clone a voice that isn't yours.

Gemini 4 Argon is Google’s frontier AI model for complex, long-horizon professional work. It combines advanced reasoning, coding, multimodal understanding, and cybersecurity-defense capabilities, with support for up to 1 million output tokens. Designed for software engineering, finance, legal work, and enterprise research, it helps solve multi-step problems while Google gradually expands access through trusted testing and safety safeguards.

Vantage is a free, open-source cost and usage monitor, guardrail and session log for coding agents.

Meet Aurick, your autonomous AI QA teammate. No test scripts, no manual recordings, and absolutely zero maintenance.Just give Aurick your application URL. Hundreds of AI agents will explore your product in real-time, test every single flow, and monitor your staging environment to catch bugs before production. Aurick reasons and adapts dynamically as your app changes, delivering comprehensive test coverage and rich debugging context automatically.

Context Goblin reviews pull requests. Register a second repo and it maps how your services are wired together, so the reviewer sees everything downstream that has an opinion about the change. You pick the reviewers with customizable subagents, prompts and MCPs. Install the GitHub App and your next PR gets reviewed. Free and instant for the first signed-up teams.

With UserWants, your users tell you what they actually want. Collect their feedback, let them vote, and focus on building the stuff that actually matters. Simple, minimal, no unnecessary features, just what you need to ship faster.

The AI control plane to understand how AI is used, define what it can access, and enforce security policy across every agent, MCP server, and Skill in your enterprise.

Tadata is the AI employee that lives in your Slack. It connects to your tools, learns your company and your preferences, and does work for your team.

Airuncode is a local-first agent runtime for serious software work. Run multiple coding agents on your machine, bring your own API keys, switch between cloud and local models, and pay providers directly with zero token markup. It scans your codebase, debates solutions across agents, edits files, runs tests and self-heals failures. It also ships with V-CORE, a native Vulkan 3D runtime for AI-assisted game development. Available on Windows, macOS and Linux.

Bob's CLI runs on your own hardware with zero API costs, zero data leaving your machine. Bob lives in your terminal, sees your actual files, and writes code only with your explicit approval. What makes it different: auto-detect local AI models, behavioral DNA profiling that adapts to how YOU work, autonomous code review + auto-fix, conversation forking, deep dives, and SovereignLink — remote execution from any device while your code stays home. Free to start. Sovereign by design.

Host apps and websites, spin up Sandboxes, manage domains, run tests, deploy to any cloud, and automate delivery with pipelines, all in one platform. Configure everything through the UI, YAML, or code, or let Claude Code, Cursor, Copilot, and other AI agents operate Buddy directly through MCP or CLI, including deployments, infrastructure, and logs.

Decawork is how IT teams take employee-built AI agents live and control every one of them from one place. An employee builds an agent on Claude Code, Codex, or any vibecoding tool; we take it in, put it on company accounts, and run it as a company asset. From there, IT team manages the agent like an employee: access, oversight, retirement.

Docker manager for one host or a whole fleet. - Manage local, remote TLS, and NAT'd/VPS hosts from one UI - Deploy & update Compose stacks, incl. from Git with auto-sync - Live logs, metrics, and an in-browser container shell - Scan every image for CVEs (Grype/Trivy) before it ships - Inject secrets from 1Password, Vault, Infisical, Doppler - Encrypted backups to local, S3, or GCS - Semver update badges with release notes - SSO, LDAP, and role-based access Hardened and free.

Stop managing AI agents one at a time. Vibe Sensei is a native desktop cockpit for orchestrating Claude, Codex, Gemini, Cursor, and other coding agents in parallel. Every agent works inside a visible terminal, isolated by Git worktrees and coordinated through missions, squads, live handoffs, and shared tasks. It runs locally on your machine using your own provider accounts, so your code, tokens, and workflow stay under your control.

CodeSpace is where developers showcase their projects, skills and live demos in one premium profile.

ngrok AI Gateway provides one hosted gateway for every model: public providers, custom endpoints, and the models you run yourself. Use one key and one URL to route across OpenAI, Anthropic, and self-hosted models with observability, access control, and fallbacks built in. Your private models connect through ngrok’s network, so they sit beside hosted providers without being exposed to the public internet.

Infrastream is the production ready platform for running AI agents in your cloud. Deploy, monitor and govern AI agents with infrastructure, identity and security built in, so you can move from prototype to production without rebuilding.

The faster your team ships with AI, the harder it becomes to keep production stable. Not anymore. Coldtea is an agentic IDE where your coding agents build, visual QA agents catch regressions, and AI monitoring watches production, so your team can keep moving at agent speed without breaking anything

Run codex in a sandbox with full computer use