Search

Zero-dependency context-window token counter for tiktoken-powered AI agents

A2UI LLM client — DeepSeek Generator for eval framework

Standalone Agent Client Protocol (ACP) server for DeepSeek Harness with real-time streaming, thought visibility, tool lifecycle updates, and session recovery.

Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wi

Channel-agnostic messaging bridge core for DeepSeek Harness (DSH): binds chat channels to DSH agents, streams replies, and pushes work summaries

Beav Creator for Xiaohongshu (RED/RedNote), social-media AI operations, content research, copywriting, images, audio, and video in DeepSeek Harness. 小红书与社媒AI运营。

DSH Mini TUI: a minimalist terminal interface plugin for DeepSeek Harness

TaskPack: an open, offline task-handoff container. Task Passport is the durable state; TaskPack is the box it travels in.

Privacy-first AI agent bridge with native Feishu Card 2.0 streaming

dom-miner — mine any site into a compact DOM map for QA test plans and AI agents

Auto-healing tools for your app. Connect to your favorite AI agents, forward your errors, and let the AI fix them for you.

See exactly what your AI agent did. Lightweight tracing + a local dashboard for debugging LangChain agent runs.

Simba Agent - a terminal coding agent that reads, edits and runs your code. Powered by OpenRouter.

Execution integrity and trajectory authenticity governance middleware for autonomous AI agents

AI Agent with intelligent planning and reasoning

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

LLM API pricing registry and cost estimation, shared by the DeepSeek Harness dsh-llm-cost plugin and Python agent systems.

Keep LLM transcripts valid. Tool-call pairing survives compaction, interruption, retry and provider swap.

Retrieval-Augmented Generation. A production-shaped reference stack for grounded chat over your own documents — FastAPI + LangChain agents, Qdrant vector search, and a Next.js 15 frontend with a deterministic calculator tool wired in.

Agent 规划与执行框架｜Plan 即运行时对象｜G4C 五要素 + TAO 步骤级执行 + Replan 自我修正 + 失败回溯 + 信任状态管理