Use ChatGPT Developer Mode as a local coding agent for your repo through MCP.

Secure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.

Let any AI coding tool — Claude Code, Cursor, Codex — drive your real Chrome. One-prompt setup, muscle memory, local-first.

A Whistle proxy management tool based on Model Context Protocol that allows AI assistants to directly control local Whistle proxy servers, simplifying network debugging, API testing, and proxy rule configuration through natural language interaction.

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP tools for codegen, browser control, and recordings.

A local MCP runtime that attacks what you own and only reports what it proved. 17 CVEs across 9 projects came out of this repo. Install: npx -y hacker-bob@latest install /path/to/project, then run /bob-evaluate target.com

Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.

Drive your real, logged-in Chrome from any AI agent (Claude Code, Codex, Cursor, VS Code) — works where headless dies. Reads emailed login codes from your Gmail, 40 tools, up to 20 concurrent sessions. MIT, local-only.

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

let any ai agent use the local browser

Cross-language-safe code-intelligence MCP for AI agents -- 13 languages, family-gated call graph (CodeGraph 745 vs TSA 6 cross-language mis-wires, v1.21.0 same-session -- ~124x by count, ~390x by rate; re-verifying vs current develop). Run miswire-audit on your repo. 8 facade tools, TOON output, 100% local. Python.

Local Figma MCP server with no REST rate limits, no metered tool-call quotas, and a verification loop. Drop-in alternative to Figma's Dev Mode MCP and Framelink for Claude Code, Cursor, Windsurf — works on every plan including Free.

💻 Give AI models complete control of your computer (probably a bad idea)

Minimal Coding Agent Harness on MCP for ChatGPT, Claude, Hermes, Grok Bot, OpenClaw

Rust MCP server for comprehensive code intelligence - 90 tools, 32 languages, security scanning, call graphs, and more

An MCP server for parallel browser automation by AI agents with multiple cloud providers

LeanCTX — Context Intelligence for AI systems.

Paused Codex App auth-split proxy experiment; future work would need a Responses-to-Chat-Completions adapter.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

Vestige enhances agents by deterministic root-cause retrieval that reaches backward through time to find the quiet change, decision, or service that caused today’s failure, not the lookalike.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.