592 RESULTS · “llm”
v4.0.0 · MIT
Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.
— · Apache-2.0
Claude Code and Claude Agent SDK integration package for MLflow Tracing
v1.108.402 · no license
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client.
v0.9.4 · MIT
BioMCP: Biomedical Model Context Protocol
— · MIT
39 MCP servers (488 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, laws, tax, crypto, stocks, news and more. Prices in Toman.
v0.104.0 · MIT
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
v2.15.0 · Apache-2.0
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman collections, specifications, and environments via Model Context Protocol (MCP)
v0.6.0 · MIT
你的随身 AI 剪辑搭档 | Pocket AI co-editor for video montage — AI video editing plugin & MCP server for Claude Code, Codex, Hermes & OpenCode
The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 14 agents · 21 skills · 8 workflows. Fail-closed gates, test honesty, anti-anchored review.
v0.7.0 · MIT
Make AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.
v0.6.0 · LGPL-3.0-or-later
Email MCP server with IMAP + SMTP support
36 MCP servers (469 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, qavanin.ir laws, tax, news and more. Prices in Toman.
v1.7.2 · MIT
DSH插件市场 / DSH Plugin Marketplace: 在 DeepSeek Harness Web GUI 中一键浏览、安装与更新 GitHub topic:dsh-plugin 的全部插件 | browse, install & update all GitHub dsh-plugin plugins in the DSH Web GUI
v0.3.0 · MIT
Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
v2.2.0 · MIT
Stop re-teaching your agent. Make your agent's memory work like a brain. Hippo is long-term memory for coding agents. It's a critical layer for your AI harness that connects across your different tools (Cursor, Claude Code, Codex). It keeps your proprietary data completely local, and it actually learns over time.
UI/UX system for Claude Code: 71 plugins, 93 agents, 74 skills. Design mastery, archetypal design, accessibility, and frontend workflows in one validated plugin marketplace.
Self improving agents through iterations
Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results
v3.0.0 · Apache-2.0
Content-aware output compression for AI coding assistants. 36 specialized processors cut CLI output tokens by 60-99% (git, pytest, npm, terraform, kubectl, docker, and more) without losing errors, diffs, or stack traces.
Personal Context Manager for Claude Code. Your life in walnuts.
v0.73.0 · MIT
Workflow control for AI coding agents
v4.0.0-rc.7 · MIT
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
v0.15.0 · Apache-2.0
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).
v1.1.72-dsh021rc2.4 · MIT
dsh-purge 社区适配版:上游已停更,这里让它继续跑在 DeepSeek Harness 0.2.1-rc.2 上(基于 1.1.72)