Development Tools

Give AI agents secure access to your infrastructure and workflow. With Buddy MCP agents can run pipelines, inspect logs, deploy apps, create sandboxes, publish artifacts and manage domains. Control exactly what they can access with workspace permissions and tool scopes. Works with Claude Code, Cursor, Codex, Copilot and other MCP clients.

QApilot MCP automates tests on real Android devices and emulators by talking to Claude, Cursor or Codex. Describe a test flow in plain English, no Appium code required. Your agent lays out the steps. QApilot runs the steps. It finds the elements, waits for the screen to settle, retries when something moves, and caches what it learns so repeat runs are faster. Every pass saves a Gherkin feature file and becomes a replayable test case. Needs Node, Java and the Android SDK.

The gap between 1.5x and 100x isn't speed, it's trust!! AI agents generate code 100x faster than humans write it. But your team can't review it all. EasySpecs documents undocumented codebases and turns them into trustworthy specifications, so spec review becomes your new merge request review. Ground your agents in reality. Scale agentic development without babysitting. Document the foundation once. Review specs including Oracles and Rubrics and Ship code you actually verified.

MiniCPM5-2B is OpenBMB's dense 2B follow-up to MiniCPM5-1B. It is built for on-device and local use, leads the 2B open-source class, and stays competitive with larger 4B models on coding, math, long context, and agent tasks. Apache 2.0 weights, GGUF, and MLX are up.

Ponytail is a plugin that makes coding agents write the least code that works. Before adding anything, it checks whether the change is needed, already exists, or can use the stdlib or a native API. Same behavior, fewer lines to own.

Gemini 3.8 Flash is Google's most intelligent workhorse yet. Third Flash drop in 6 weeks, with big jumps from 3.7 on software engineering, agents, and multi-step reasoning. It sits with larger frontier models on DeepSWE v1.1 for long-horizon coding, leads Terminal-bench 2.1 at 89.4% and HLE-Verified at 54.9%, and ships at the same intro price as 3.7: $0.75/$3.75 per million tokens through Dec 31. Live today in the Gemini app (Pro/Ultra), AI Studio, Antigravity, Gemini Enterprise, and the API.

Blume watches your coding agent sessions locally and turns what it learns into better agent context. Repeated corrections become rules, workflows become skills, and your agents stop making the same mistakes. Claude code, Codex and Cursor.

Superset Mobile puts your coding agents in your pocket. Kick off new tasks, watch what every agent is doing, and get notified the moment one needs you. Review diffs and send follow-ups from anywhere, then pick the session back up on your desktop. Works with your existing Superset workspaces on your own machines or in the cloud.

An orchestration layer that guides Claude Code to deliver your coding tasks without requiring your constant supervision. It fetches your context from Jira, Github, Notion and Slack, writes your prompts and verifies that claude code completes tasks correctly.

Not only can AI agents build your UI, they can now test what it actually looks like. Buddy Visual Tests captures every UI change, compares it pixel by pixel with an approved baseline, and brings visual regression testing straight into your delivery flow. With CLI, MCP and Skills support, agents can spot visual bugs, fix them, rerun tests, and hand over intentional changes for human approval.

n8n is a fair-code workflow automation platform that lets you visually build and control AI agents and business processes. It solves the problem of rigid, limited automation by combining a visual canvas with custom code, enabling limitless logic and seamless data movement between 400+ apps. It's built for technical teams like IT Ops, Sec Ops, and developers who need powerful, transparent, and self-hostable automation.

APILayer is a unified platform that provides access to over 40 high-productivity APIs through a single account and API key. It solves the problem of developers needing to manage multiple accounts, keys, and integrations across different API providers by consolidating essential services like geolocation, finance, weather, and developer tools into one hub. It's designed for developers, engineering teams, and businesses who want to build applications faster by integrating reliable, well-documented APIs without infrastructure headaches.

GLM-5.3 is Z.ai's latest model built for complex, long-horizon coding tasks. Through massive post-training scaling, it achieves open-source SOTA in agentic coding and demonstrates emergent capabilities in vulnerability discovery and cyber defense.

Spec Kit is an extensible toolkit that structures and automates Spec-Driven Development (SDD) or any custom business process. It solves the problem of ad-hoc, unstructured AI agent interactions by providing a phased workflow (Spec→Plan→Tasks→Implement) with rich templates and quality checks, producing linked Markdown artifacts. It's for developers and teams who want to use AI coding agents (like Copilot, Claude, or Gemini) more effectively within a defined SDLC, offering 35+ integrations and 138+ community extensions to tailor the process.

DeepSeek Harness is an open-source agent runtime where models, tools, prompts, storage, the agent loop, and even the UI are plugins. You compose profiles and agent presets, run programmatic tool calling, and keep a full event log for recovery and replay.

Hoplite deploys your local coding agent setup to the cloud, no reconfiguration needed. We migrate your sessions, MCP servers, dependencies, and CLIs during onboarding, so your agents pick up exactly where you left off. Run multiple agents in parallel without laptop crashes, git worktree wrangling, or port juggling. Instant previews of everything your agents build. Prompt from anywhere with iMessage.

Today, we’re building on the progress of our widely used Flash series by introducing Gemini 3.7 Flash, our most intelligent workhorse model yet for coding and agents.

Unsloth Desktop is an open-source app to run and train AI models locally. Run LLMs, image/video diffusion, and audio. Connect agents like Claude Code or Codex to your local GPU with one command, and fine-tune models with no-code workflows.

This repository is a comprehensive study guide for system design, crucial for building large-scale applications. It helps software engineers and architects prepare for system design interviews by providing foundational knowledge, real-world examples, and practical resources like Anki flashcards. It's an essential resource for anyone aiming to understand the principles behind scalable, reliable, and efficient system architecture.

70,000 people use LumiChats in a browser and kept asking for the one thing a browser cannot do: touch their files. So we built the desktop one. It runs commands on your machine, writes real documents, and you pay only for the work you run.

70,000 people use LumiChats in a browser and kept asking for the one thing a browser cannot do: touch their files. So we built the desktop one. It runs commands on your machine, writes real documents, and you pay only for the work you run.