Open source. Open possibilities.

Iris is a local-first MCP server that scores AI agent runs for quality, safety, and cost using 20 built-in deterministic rules, an optional LLM judge, and a web dashboard — all on your machine with no account or telemetry.

ECC is an agent harness operating system that provides a coordinated engineering system and toolbox for AI agents, enabling structured workflows like planning, testing, and reviewing.

Phronesis is a RETE rules engine that enforces project conventions for LLM agents outside the context window, preventing contextual drift in long sessions.

AgentLeak is an open-source privacy testing tool for AI agents. It detects data leaks across tool calls, memory, and logs using a local Python SDK, CLI, and MCP tools, providing redacted reports and CI gates without cloud dependencies.

MCP Arcade is a command-line testing tool that runs a small catalog of experiments, called atoms, against MCP servers, judging results by the JSON-RPC wire and sandbox file changes rather than by tool descriptions or model prose.

SUM is an open-source tool for verifying AI text transformations with cryptographic receipts. It checks what changed, what was preserved, and what was lost when AI rewrites text, with cross-runtime Ed25519 signatures and offline verification.

Playwright MCP is a Model Context Protocol server from Microsoft that gives LLM agents browser automation via Playwright, using structured accessibility snapshots instead of screenshots. It supports Chrome, Firefox, WebKit and Edge, persistent or isolated profiles, and many configuration options.

TraceFrugal is a local Go application that visualizes token usage for Claude Code and Codex, offering MCP result packing, cost regression gates, and optimization trials to help developers manage AI context efficiency and verify savings.

Reticle is a proxy and desktop UI for debugging MCP integrations. It intercepts, visualizes, and profiles MCP JSON-RPC traffic in real time with microsecond-level overhead, letting developers inspect messages, correlate request-response pairs, profile latency, capture server errors, and record sessions for export.

MCP server that lets AI coding agents inspect and control a live Chrome browser via Chrome DevTools, supporting performance traces, network inspection, screenshots, console logs, and Puppeteer-based automation.

Agent Interlock is an agentic AI security framework that declares the actors and trust boundaries of an AI agent system, wraps each actor's tools through an SDK or proxy, and enforces MCP tool threats M1–M9 across observe, shadow and enforce stages, recording every verdict in an append-only ledger.

Lintro is an MIT-licensed command-line tool that brings many linters, formatters, type checkers and security scanners together under one interface, with consistent reports, auto-fixing, Docker images and optional AI-assisted review using your own API key.

High-performance code intelligence MCP server that indexes codebases into a persistent knowledge graph for AI coding agents. Supports 162 languages via tree-sitter, sub-millisecond structural queries, 15 MCP tools, and ships as a single native binary with no runtime dependencies.