Development Tools

Worktrees isolate your agents. AVP integrates them: every change proven on the exact head of main before it lands.

Llama Windows brings llama.cpp to the Windows 11 system tray. Download open models from Hugging Face in one click, chat via Alt+Space, and let coding agents, editors and scripts share a local OpenAI-compatible API and model cache. Free and open source.

Mercury 3 is the most capable diffusion LLM released to date. It outperforms GPT-6 Luna and Claude Haiku 5.5 while running 4–8x faster at 1,000+ tokens per second.

Send webhooks reliably from your infrastructure. Retries, cryptographic signing, health tracking, payload transforms, recipes for Slack/Discord/PagerDuty, and a self-service portal — in one Go binary with PostgreSQL as the only dependency. Free, MIT.

Buddy Sandboxes give AI coding agents their own isolated Linux machines to build, run, test, and fix apps without touching your local setup. Each Sandbox has a persistent disk, root access, Docker, SSH, and a public URL. Create one per task, branch, or PR, then let your agents manage it through MCP, CLI, SDK, or API.

Kugel 3.5 beats four leading TTS models on 8 of 9 tests. It gets short words wrong at half the rate of the next-best model, reads long numbers exactly right 97.1% of the time and supports IPA. 5.25 cents a minute. Not on Kugel? Three lines to production.

OpenCode is an open source AI coding agent. It’s available as a terminal-based interface, desktop app, or web app.

API Claws is Buda's developer-facing Agent API. Create hosted AI agents with Drive memory, model routing, managed runtime, observability, sessions, and embeddable product experiences, without building the full agent infrastructure yourself.

ProcBoss is a lightweight production process and infrastructure management platform for running, deploying, and monitoring applications across servers. Run Node.js, Bun, Deno, & other runtimes with clustering, automatic restarts, health checks, dependencies, cron jobs, logs, metrics, and GitHub auto-deployments. ProcBoss Cloud adds centralized server monitoring, deployment management, alerts, and hosted status pages; giving developers one place to keep production applications running reliably.

Buddy Drop puts your site or app online in seconds. Just drop your folder, ZIP, or files and choose from a range of free domains or connect your own. Buddy takes care of the rest, from hosting and deployment to previews and versioning. No signup required.

Claude Opus 5.5 is Anthropic’s latest model for agentic coding and knowledge work, delivering major performance gains, clearer communication, stronger safety, and 40% lower cost than Opus 5 on typical workloads.

Solid’s AI agents build apps, automate workflows and tackle work you lack the time or expertise for. They pick and set up their own real machines, create accounts and pay for services. They use your apps through APIs or log in like a person. They build what’s missing and fix problems along the way. Think beyond personal agents like Grok Bot and Muse: Solid is built for complex, long-running work for you and your team. Close your laptop. Solid owns the job from start to finish.

Orchestrate coding agents from your iPhone. Pick up the same workspaces from your computer, review diffs, and merge PRs away from your desk. Works with Claude Code, Codex, and other terminal agents. Included with Superset Pro. First month free with code MOBILELAUNCH.

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.