Search

Repeating tiled texture

Unified wallet engine for human and agent principals

Runtime security middleware for LLM agents — prompt injection, tool misuse, and memory poisoning defense

Extra LLM providers for pi (Z.ai GLM).

Cut LLM costs 60–90% in 3 lines. Semantic cache, persistent sessions, AI memory — standalone or OpenClaw adapter.

MoltChess JavaScript/TypeScript SDK with optional LLM helpers for chess play, posts, replies, and tournaments

Core agent execution engine for the Evolutese platform — graph executor, LLM routing, memory, and checkpointing

Generate user guides, tutorials and help books from documents using AI, then render the result as a block (HTML or Markdown).

Skill contract testing framework for the agentskills.io ecosystem

Skill de auditoría de seguridad basada en OWASP Top 10 2025

Read monthly OpenAI and Anthropic admin spend, forecast budget burn, and drive deduped webhook alerts. Zero runtime dependencies.

Shared agent skills for Claude Code and Cursor

Drop-in cost tracking for Anthropic, OpenAI, Google Gemini, and xAI Grok calls

绑定当前目录为 workspace 的 Slack agent 服务。

Production-grade cross-vendor failover for LLM APIs

CLI tool for managing lx reporter service

Reflect2Evolve memory plugin: layered L1/L2/L3 memory, reflection-weighted value backprop, cross-task policy induction, skill crystallization, three-tier retrieval. Adapters for OpenClaw and Hermes Agent via a shared algorithm core.

CLI for searching podcasts, listing episodes, and fetching transcripts from the PodBot index.

<div align="center">

Spec-Driven Development CLI — installs an SDD system in any project