DSH bundle: key-free web search, page fetch and one web_tools action tool for verticals, platforms and cited research; eight engines fused with RRF, 34 vertical sources, arXiv research lookups and readable papers, official release facts, a replayable benc

Requires dsh >= 0.1.7 (session format 4); on dsh 0.1.5 use dsh-repeat-tool-breaker@0.7. Escalating repeat detection for dsh: a synchronous ctx.tools.guard gate that counts semantic fingerprints (exact/cmd/net/host/sink) over a per-agent sliding window, wa

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

A persistent, unified memory layer for all your AI agents (e.g. Claude Code, Codex, DSH), backed by Markdown and Milvus.

Open-source infrastructure that turns scattered SKILL.md files into curated, retrieval-ready agent-skill corpora—with retrieval and evaluation tooling included.

A temporal context graph, a memory API, retrieval primitives, and a multiple-platform integration mesh — designed to be embedded into any host process.

Cross-agent plugin for manually excluding and editing AI conversation context, with search, filtering, hide/restore, undo, and original Session preservation.

The missing tool to sift your Claude Code sessions: regex search across all record types, recover files, extract images, inspect subagent topologies, match between plan files and sessions.

专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。

Codex-style @file mentions for DeepSeek Harness: search workspace files in the composer and attach their path to prompts.

Enables an AI assistant to search live neighborhood bulletin-board pins by coordinates, radius, bounding box, or category, and to fetch individual pins or share their page links. It also lets the assistant publish public pins such as events, lost pets, sales, and business notices, gated behind explicit user confirmation and optional paid placement plans.

Visual search for memes, infographics and charts — by meaning, OCR text, or image similarity.

One sentence in, the best-matching visual style out: art reference chart and prompt encyclopedia.

Run agency client work from Claude: Google Ads, GA4, Search Console, GBP, Meta, WordPress, CRM.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

All your bookmarks in one library. Share them with your AI agents. Read-only search over your saves.

Search the Cerebrium docs: deployment, cerebrium.toml, hardware, endpoints. Also sends feedback.

给 DeepSeek Harness 的本地记忆层：养大肥鱼的可以下载来玩，经过测试下载之后比单纯用RAG和外部记忆库更有人情味更自然了。

Free web search & fetch plugin for DeepSeek Harness (dsh) with multi-engine fallback (Tavily, Exa, Brave, Baidu, SearXNG and more)

Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the task, never interrupt. Never install without consent.

Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the task, never interrupt. Never install without consent.

Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language. Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw.

Enables MCP clients to read a shared book library from the AI reader’s own position, search full texts, leave margin notes, reply to shared annotations, and review reading status and library overview without moving the human reader’s progress.