Yet another static site generator

DeepSeek AI model plugin for Lichen AI platform

Official JavaScript/TypeScript SDK for Lichen blockchain

a fork for lichen of pdfjs-dist

Annotation layer for pdf.js in vue fork of Aaron Leong pdf-annotate-vue

Local dependency intelligence for Go, npm, pnpm, Cargo, Python, Ruby, Maven, Gradle, and NuGet -- in your repo OR inside a container image (lockfiles, Go binaries' embedded module lists, installed node_modules, and Alpine/Debian OS packages via OSV.dev):

`@lichen-ai/plugin-mysql` brings MySQL-compatible database connectivity to the [Xpert AI](https://github.com/xpert-ai/xpert) data analysis stack. The plugin registers a global NestJS module that exposes actionable strategies for native MySQL, Amazon RDS,

OpenClaw memory plugin backed by a local Lichen fact-mesh — honest recall with confidence tiers and coverage, write-through capture, fully offline, zero API cost.

`@lichen-ai/plugin-unstructured` brings the [Unstructured](https://www.unstructured.io/) document partitioning API into the [Xpert AI](https://github.com/xpert-ai/xpert) platform. It lets ingestion workflows call Unstructured’s `/general/v0/general` endpo

`@lichen-ai/plugin-model-retry` adds retry logic around Xpert agent model calls. It keeps LangChain-style retry semantics while exposing only JSON-serializable configuration that can be edited in the Xpert middleware UI.

`@lichen-ai/plugin-web-tools` adds web fetching and internet search capabilities to [Xpert AI](https://github.com/xpert-ai/xpert) agents. The middleware provides two LangChain tools — `web_fetch` for retrieving web page content and `web_search` for search

`@lichen-ai/plugin-advisor` adds a generic `advisor` tool to the agent runtime.

`@lichen-ai/plugin-clarification` adds an explicit `ask_clarification` tool to an agent and turns that tool call into a controlled clarification point.

`@lichen-ai/plugin-model-fallback` retries failed model calls with alternative models in sequence. It wraps agent LLM invocations so outages, throttling, or quality issues on the primary model can be absorbed automatically while preserving usage metrics a

`@xpert-ai/plugin-moonshot` connects [Moonshot AI (Kimi)](https://platform.moonshot.cn/) models to the [XpertAI](https://github.com/xpert-ai/xpert) platform. The plugin integrates Moonshot's OpenAI-compatible API so XpertAI agents can leverage Kimi's powe

`@lichen-ai/plugin-dangling-tool-call` repairs dangling tool calls in XpertAI agent message history before the next model invocation.

`@lichen-ai/plugin-loop-guard` implements a pure-plugin tool-call loop detector for Xpert agents. It does not rely on `xpert-pro` consuming `jumpTo: "model"`.

A local fact-mesh brain over your own notes: honest recall, reinforce/decay memory, zero dependencies. Grown, not trained.

`@lichen-ai/plugin-mineru-cli` is a CLI middleware plugin for the Xpert platform. It bootstraps a MinerU Python skill into the sandbox, appends MinerU usage guidance to the system prompt, and securely provisions the MinerU API token inside the sandbox whe

`@lichen-ai/plugin-agent-behavior-monitor` monitors runtime anomalies in Xpert agents and persists audit-friendly snapshots for later inspection.