#ai-agents

Go CLI and library for safely running Splunk searches from SPL or YAML and saving results with job diagnostics.

A security-first bridge between Claude Code (MCP) and Chrome — HMAC pairing, domain allowlist, per-domain evaluate opt-in.

Open standard for software intent in the AI agent era.

Official extensions for gopact

No repository description published.

Open source authorization engine for AI agents. Confidence-aware gating · Human-in-the-loop review · Policy-as-code · Full audit trail

Intelligent Scientific Agent for Materials Design

Multi-provider coding-agent orchestration in a verified loop: a critic on a different model signs off before work ships. Claude Code, Codex, Gemini, aider, Copilot, opencode, local.

Vet a package before your AI coding agent uses it — authoritative facts (CVEs, license, maintenance) via an MCP server + CLI. Local, no account.

A multi-agent context, rules, and hooks boilerplate generator. With a single command, it scaffolds conventions, namespaced skills, stack-appropriate settings, and interactive guardrails for seven major AI coding environments, matching each agent's native file formats and capability profiles.

MCP server that wraps the Antigravity CLI (agy): run agy prompts and peer reviews as async, restart-resilient jobs over stdio or Streamable HTTP.

A bun-native UI development & testing system

MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

Semantic + structural code search for AI-native development

Obsidian Turbocharged — governed, agent-ready Obsidian MCP server. 141 tools across 31 domains, multi-vault native, pluggable embeddings. TypeScript + Rust. AGPL-3.0-only.

Decentralized networking protocol for AI agents — sovereign identity, peer-to-peer capability discovery, and direct encrypted connections. Works as an MCP server.

Standalone DAG workflow engine for Go — 15 step types, MCP integration, durable Postgres execution (SKIP LOCKED), templates, approvals, crash recovery

Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.

Give coding agents a disposable Linux VM, not your laptop

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

Local-first MCP server for Google Health API v4 (Fitbit + Pixel Watch) — Claude/Cursor/Hermes

Chat with your LangGraph agent inside JupyterLab — a sidebar chat for any CompiledGraph

Durable Web Components your AI agent can read and drive — not disposable UI it generates. Author SFCs; a Rust compiler emits standards-based custom elements with MCP + llms.txt baked in.

Set bounded, verifiable coding loops for Codex, Claude Code, Cursor, and SKILL.md-compatible agents.

The finmap.org MCP server provides comprehensive historical data from the US, UK, Russian and Turkish stock exchanges. Access sectors, tickers, company profiles, market cap, volume, value, and trade counts, as well as treemap and histogram visualizations

A local-first control layer for AI agents

Roblox Studio MCP server & plugin for Claude Code, Cursor, Codex, and Gemini. AI-powered scripts, terrain, assets, lighting, and bidirectional project sync.

Local-first shared memory for AI agents — zero-dependency, governed writes, citations, MCP. Source behind the ihow-memory npm package.

OpenCode Plugin for supervised agentic software development on a Kanban board

Headless CMS - Built for Agents. Governed by Humans.