v0.3.0 · MIT
Three-tier memory control plane for DeepSeek Harness: persistent runtime context, searchable project documents, pluggable long-term memory, smart routing, supervised agent workflows, WebUI, and headless tools.
v0.1.4 · MIT
AnySearch web search provider and advanced search tools for DeepSeek Harness (DSH)
v0.4.12 · MIT
Free web search provider for DeepSeek Harness - DuckDuckGo backend, no API key needed
— · Apache-2.0
An autonomous agent that conducts deep research on any data using any LLM providers
v0.7.2 · Apache-2.0
Agent memory with no API key, no LLM, and no embedding provider. Serves MCP over stdio against a local SQLite store, or Cloudflare Workers + D1. Drop-in for @modelcontextprotocol/server-memory; every memory keeps its source, its scope, and the evidence th
v0.2.3 · MIT
Community plugin — NOT affiliated with DeepSeek AI. Extensible multi-provider web search for DSH — built-in DashScope and MiMo, easy to add more.
— · Apache-2.0
Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.