Agents

Keyoku

The harness with muscle memory — activity tracing, pattern detection, and one-command workflow execution for Claude Code, Cursor, and Codex

Opena2a

One scan for AI risk. `opena2a review` checks an AI project across credentials, shadow agents, MCP servers, and dependencies, returns a scor...

Core

Connect Chromium to LLM agents via token-efficient DOM compression. 50-200 tokens per page.

AgentLoom

Simple, flexible workflow orchestration for multi-agent AI apps, with YAML configuration, runtime safety, observability, and resume support.

Skills

Pluggable MCP tool modules that give agent workflows their capabilities — GitHub, GitLab, Sentry, Slack, Jira, Notion, memory, datasets, and...

Agentic Chatops

3-tier agentic ChatOps (n8n + GPT-4o + Claude Code) implementing all 21 patterns from "Agentic Design Patterns" — solo operator managing 137...

Hcifootprint

Turn a web app's interaction surface into a typed, traversable skill graph an LLM can plan over — the frontend sibling of footprintjs.

Gitmem

Institutional memory for AI coding agents. Scars, wins, and patterns that persist across sessions. MCP server for Claude Code, Cursor, OpenC...

Fava Trails

🫛👣 FAVA Trails — Git-native, curated memory for AI agents via MCP. Draft isolation, promotion gate, thought lifecycle hooks, memory curati...

T2000

Agentic finance infrastructure.

BrowseAI Dev

Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination...

0xarchive MCP

Typed 0xArchive market data tools for MCP clients (111 tools). Hyperliquid (perps, HIP-3, HIP-4, Spot) and Lighter.xyz: L4 depth, L3 depth,...