Multi-language testing automation MCP server for Claude Code and AI assistants. Supports Python, JS/TS, Go, Rust, Java, and Ruby with automated test discovery and execution.

The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.

OpenAPI testing and deterministic API fuzzing for AI agents—catch contract bugs before unsafe calls with local-first sealed plans, MCP, and replayable evidence.

Ask for a change to your source and get it — made by local MLX models on your Mac, checked by a gate a machine can run before Claude sees it. Unit tests too. MCP server + CLI.

A free local cloud environment for AI coding agents to build, test, and debug Google Cloud applications. Includes MCP discovery, SDK configuration, resource inspection, queries, and diagnostics.

Local-first API collection studio with bundled local MCP, human-approved changes and guided API testing. Import, edit, test and export API specs.

Queue committed branches from parallel LLM coding agents in Git worktrees. Test the combined tree in a local merge queue, require approval for Git pushes, and recover interrupted pushes.

Local test coverage intelligence for JavaScript and TypeScript: gaps, complexity, and practical test priorities over MCP or CLI.

Final release; the checks moved to 9lives (9l mcp). Local QA MCP: scan, inspect, repro, run tests.

CARBON AI testing harness with Jay: risk-based software testing, exploratory and regression checks, accessibility, triage, and local evidence reports via MCP.

Local-first browser testing for AI coding agents: write durable browser specs, replay them in a real browser, and get repair-ready evidence

ChromeWalk: a real local browser for your AI assistant. MCP server + CLI for browser testing, audits and automation.

Local, MIT-licensed AI test harness with 10 MCP tools and 11 prompts for risk-based test planning, focused testing, accessibility checks, evidence capture, screenshot maps and interactive HTML quality reports. Runs over stdio in one explicitly selected project. Your coding agent supplies AI and browser execution; CARBON records observed evidence and generates reports. No hosted backend, model API key or telemetry required.

Local emulator for E2E testing: fake SMTP, Telegram, WhatsApp, SMS, push, Slack, Discord, Stripe & OAuth with a web timeline and MCP server for LLM agents.

Test mode for your integrations, built for the way agents build. Local, stateful twins of GitHub, Slack, Stripe, Gmail and Linear, over REST and MCP.

Token-lean browser MCP server: test local apps freely, browse other sites only after the user allows them

Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.

AI-first local mock server and HTTPS proxy for client tests: a coding agent drives it over MCP or the CLI, and test code embeds it as a library

Local LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.

Open-source software test intelligence for development teams: manage test reports and software test releases, find the issues behind failing tests (failure clustering, flaky test detection, root causes with a local LLM) and get a GO / NO-GO release verdict. JUnit, pytest, Playwright, Cypress, TestNG, Allure, Robot, Cucumber.

Secure Model Context Protocol (MCP) server & gateway for Claude, Cursor, and ChatGPT. Unlimited local file editing, testing, and dev tools without cloud limits.

MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating, running, debugging, and managing browser automation tests through natural language.

Local, stateful twins of the Jobber, Housecall Pro, and QuickBooks Online APIs. Build and test integrations and AI agents against a believable fake business, with resets, rewind, controllable time and failures on demand. No real accounts.

A local MCP server that breaks on demand. Test your client against auth failures, disappearing tools, flaky responses, and token expiry.

MCP server for TDCv2, a fake and test data generator: agents write a .tdc config and generate realistic mock, synthetic and test data locally — CSV, JSON, SQL; same config, same bytes.

Local-first MCP server that runs isolated mutation testing against a codebase to expose the gaps its test suite does not cover. Wraps StrykerJS, cosmic-ray, cargo-mutants and Infection behind one tool surface.

MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet

Local merge queue for parallel LLM agents in Git worktrees. Test combined code changes, require approval for Git pushes, and recover interrupted pushes.

Alpha MCP server for local-first LLM orchestration: memory, knowledge, state, routing, swarm planning, API discovery, tests, automation, and plugins.

Local MCP tools for LM Studio and Ollama: a ComfyUI image-generation server, an MCP smoke-test tool, and setup guides for document, Git, filesystem and browser servers

Fake, mock & test data generator for AI agents — Claude Code, Cursor, any MCP client. Realistic CSV, JSON and SQL from a small .tdc config, generated locally by TDCv2. A skill and an MCP server.

Verifiable memory for AI: knowledge only counts once a real test confirms it. Project memory across restarts, MCP server for Claude, local Rust + SQLite.

Local, stateful twins of the Jobber, Housecall Pro, and QuickBooks Online APIs. Build and test integrations and AI agents against a believable fake business, with resets, rewind, controllable time and failures on demand. No real accounts.

Cost-aware, local-first skill routing for AI agents. MCP server + CLI + Claude Code hook. Tested on 141 real skills.

Deterministic JSON repair, regex testing, and real JSON-Schema validation for AI agents. Local, offline, no telemetry.

Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.

Local-first CLI and MCP server mapping tasks and diffs to ranked context, likely impact, tests, and risks.

Quiet MCP executor for Claude Code and Codex. Offload edits, tests, refactors, and commits to cheaper local or flat-rate models.

Control Eufy RoboVac vacuums with natural language through a local MCP server. Battery, cleaning, docking and manual movement over Tuya 3.3. Tested with RoboVac 35C.

MCP server that bridges Claude Desktop (or any other local app supporting MCP) with Selenix for browser automation and testing. Enables creating, running, debugging, and managing browser automation tests through natural language.

Local-first MCP server that gives AI coding agents repo and org memory from GitHub PR history, code, tests, regressions, architecture, and cross-repo impact.

Zero-dependency 3-tier MCP router for Claude Code & Google Antigravity that offloads file scouting and test log triage to a local GPU with automatic cloud failover.

A local harness for Claude Code and Codex: budgeted test runs with a stop rule, a guard for the tests you already have, and a token tree for every subagent.

Catch broken merges between parallel AI coding agents (Claude Code, Codex, cmux, Orca, git worktree). Combines worktree branches, checks conflicts and contract breaks, runs affected tests. Local CLI + MCP server.

Local CLI and MCP server for compacting test and build output, with retrieval from a redacted local cache.

Disposable desktop MCP server for AI agents: private Linux GUI, Chromium, shell and read-only noVNC in Docker. Computer use and local web app testing without taking over your screen.

Local-first MCP server and CLI that audits test suites for false-green tests: tautological assertions, mock-contract drift, and mock hygiene. Read-only and deterministic, across TypeScript, PHP, Python and Rust.

The best $0 research agent that runs on a laptop. Local Gemma 3 4B + SearXNG + trafilatura. CLI · TUI · Web GUI · MCP server · submittable Claude plugin. 264 tests, all mocked.

ZippyServe is a zero-dependency local web server. It lets you test single-page apps quickly. It serves directories, zips, HTML, and Markdown. [DOI: 10.5281/zenodo.21613944]

ScopeLock is a free, local-first tracker that keeps AI coding agents aligned with agreed project requirements. Plan work in phases, enforce verifiable test gates, inspect live logs on a local React dashboard, and hand off tasks seamlessly across Claude Code, Codex, and Antigravity over local MCP without losing state or suffering scope creep.

RepoTunnel is a secure local AI workspace bridge that connects ChatGPT Web and MCP-compatible AI clients to approved local projects, files, terminals, Git, GitHub, browsers, editors, and desktop applications—so AI can inspect, edit, test, run, and manage real development work without constant copy-pasting.

Create your best prompts once, improve them with tests, turn them into assistants, and use them from Claude, ChatGPT, Cursor and Open WebUI, on a free local model or your own key. Self-hosted, with a Windows 11 console.

Agentic MCP — local coding tools for ChatGPT Developer Mode and other MCP clients. Tested with ChatGPT Plus via HTTPS tunnel; availability varies by plan and rollout. Independent project, not affiliated with OpenAI.

Local-first Windows kanban for switching AI coding agents: per-project handoff packs, AGENTS.md projection to 9 entry files, 23-tool MCP server, LLM self-supervision. One-command release gate (tests + mutation probes + frozen smoke).

🎛️ AceDeck — desktop app & GUI for ACE-Step 1.5 AI music generation on Windows: one-click install, generation queue & batch songs, cover/repaint, engine control, stability test, Claude MCP. Local Suno alternative.

Local-first MCP server that checks test doubles against the production code they stand for, so a mock that outlived its target stops passing silently. Reads Vitest, Jest, PHPUnit, Mockery, pytest-mock and mockall without running a single test.

Persistent memory MCP server for AI coding agents like Claude Code. Zero-LLM, local-first (SQLite + FTS5), proactive recall by file path. 12 MCP tools, 113 tests. The MEMORY.md alternative that stays constant-cost at 10,000+ memories.

Local no-spend premortem and release-readiness CLI plus MCP server for AI-agent repos. Audits docs, tests, discovery, secrets, and receipts; proposes safe additive fixes before publish, deploy, or paid x402 execution. Part of Triptych OS (Agent OS).

Rust-native context compression for Claude Code, Codex & MCP agents: filters & compresses noisy tool output (tests, diffs, logs, JSON, provider traffic) before it reaches the LLM — fewer wasted tokens, full evidence recoverable. Local-first, Apache-2.0. Pairs with Code Explorer.

Multi-agent AI assistant that turns a GitHub issue into a draft PR with tests; planner/coder/reviewer loop on LangGraph, served via FastAPI + MCP. Swappable Claude / GPT / local Hugging Face models. Prompt caching & model tiering for ~50% lower cost. Dockerized, CI-tested.