Search

AI identity layer for Claude Code, Codex and Cursor — stores who you are, not just what you did. Local-first, MCP-compatible.

Scanner engine for the agentic-security Claude Code plugin — SAST, SCA (function-level reachability + CISA KEV), secrets, IaC, prompt-injection, MCP/agent-tool audit, auth/authZ deep analysis, attack chains, PoC generation, business logic, toxic-combinati

Unified LLM API with automatic model discovery and provider configuration

ClawTouch MCP server — exposes a real USB-HID keyboard/mouse (Raspberry Pi Pico 2) as Model Context Protocol tools for any LLM agent. MIT.

Local transformers.js embedding provider for @vivantel/rag-core

Cut your LLM prompt size by 40-70% in one line of code -- semantic chunking + extractive summarization that preserves meaning, instructions, and key entities.

Compression with a quality contract — cache-aware, causally-pruned context compression for agentic runtimes, gated by a statistical non-inferiority test.

Upstash AgentKit adapter for the Vercel AI SDK: chat history, memory tools, Redis-Search tools, rate limiting, and cached tools.

你的随身 AI 剪辑搭档 | Pocket AI co-editor for video montage — AI video editing plugin & MCP server for Claude Code, Codex, Hermes & OpenCode

Local-first engine for scheduled, LLM-generated email digests that read your own data and never leave your machine.

NestJS-native primitives for building production AI agents.

Vercel AI SDK agent runner for Pikku

CHAP adapter for AG2 (AutoGen): record a human-decision envelope at the human-input turn.

Deterministic schema validation gates and circuit breakers for LLM function calling

Benzi is a coding AI agent + harness grounded in a live code map.

Reserved for LastSearch — verified search infrastructure for AI agents. Full release imminent. https://lastsearch.ai

Make consequential AI-agent actions safe to execute.

Claude Code and Codex exchange letters, one shared bag. No daemon, no polling, no hooks.

AI Space: agents-course/text-to-image

AI Space: AgentVerse/agentVerse