Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs

Normalized US-GAAP financial statements & fundamentals from SEC EDGAR, as MCP tools for LLM agents.

Claude Code plugin for autonomous AI research — multi-agent loops take a bare topic all the way to running experiments, with no human-written experimental code.

OneBot v11 hub for DeepSeek Harness: connects to an upstream OneBot v11 implementation (forward WebSocket client) and serves/dials downstream bot implementations with the same protocol, relaying events and actions verbatim so DSH can observe every message

Enterprise-grade, local-first Agent Workbench for people and agent teams. A unified multi-engine workspace for Codex Harness, DeepSeek Harness, and OpenCode, with unified plugins and Skills, multi-agent projects and tasks, and editable code, documents, presentations, design, and video.

Editor-facing ACP server for Zed and other ACP clients, composed from published DeepSeek Harness plugins. Community-maintained; not affiliated with DeepSeek.

Convex backend specialist. Use this agent for any code inside a `convex/` directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form function syntax, validator patterns, reso

Build any crypto agent: x402, ERC-8004, wallets. Does a server take your key? Hosted? Maintained?

Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs

Convex backend specialist. Use this agent for any code inside a `convex/` directory — function definitions, schemas, indexes, queries, mutations, actions, HTTP endpoints, cron jobs, file storage, auth wiring, and component installation. Knows the object-form function syntax, validator patterns, reso

Remote-first terminal UI for DeepSeek Harness with SSH reconnect, Windows/ConPTY and incremental ANSI rendering.

Agent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view projection, drift diff, CI architecture tests, whiteboard derasterize, interactive HTML/PPTX/Mermaid exports.

Claude Code skill that delegates implementation to GPT-5.6 Sol via Codex CLI, Claude plans and reviews the diff, Sol writes the code. Multi-model AI coding where the model that wrote the diff never grades it.

A CRM with AI agents that take B2B inquiries to a signed contract. Contacts, deals, forms, bookings.

Scored, maintainable locators from a live page for AI coding agents, with checks and repairs.

Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.

The Fintech Builder algorithm library — canonical, cross-language reference implementations of market-data, corporate-action, index, breadth, candlestick and technical-indicator algorithms, exposed as provider-agnostic subpath modules.

Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

A unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.

An official Qdrant Model Context Protocol (MCP) server implementation

A local, stdio-based MCP server that lets AI agents create and maintain a brand project through typed tools covering identity, palette, typography, voice, assets and guide chapters, then validate it and export a self-contained, client-facing static guidelines site that can be hosted anywhere.

Exposes 16 local stdio MCP tools that give Codex-style clients project-isolated persistent memory, local ONNX-based semantic search, and durable task tracking that survives across sessions and concurrent clients, without executing agents, hosting a model, or contacting model providers.

A gateway MCP server that lets agents reach any upstream MCP server through one endpoint while enforcing policy rules, holding risky tool calls for human approval, containing prompt-injected sessions, and logging every call.