Agents & MCP

Calculate and model paid-media financial metrics including CPA, CPL, CPC, CPM, ROAS, MER, break-even targets, contribution margin, LTV:CAC, impression-share opportunity, budgets, forecasts, and experiment economics.

Provides a repeatable, auditable workflow for large coding tasks by initializing repo-local task artifacts, installing subagent templates, and running a spec-freeze → build → evidence → verify → fix loop with fresh-session verification.

Audits a design against Dieter Rams' ten principles, scores each with evidence, and produces a verdict with a handoff prompt for new, refined, or redesigned output.

Compresses conversation transcripts into prioritized notes using an LLM observer, consolidates them when they grow, and recovers any missed sessions without a database or vector store.

Polls a local relay for animation-refinement jobs from the Timeline Inspector, posts suggestions or applies changes to transition code.

Generates images and conducts conversations through the Gemini website (gemini.google.com) using MCP tools, scripts, or a managed browser as a fallback.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Provides persistent, compounding memory for AI agents across sessions using local markdown files, with optional Supabase-backed semantic search.

Guide a visible, verified code walkthrough in Neovim with Terminal Control and Navi, optionally recording the presentation with OBS or retaining terminal evidence.

Automates browser interactions — navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, and running assertions — using a native Rust CLI.

Import Figma designs into HyperFrames compositions as frozen assets, brand tokens, components, motion animations, and shaders.

Set up GPU profiling, tracing, and monitoring for inference workloads using vLLM, SGLang, PyTorch, and dstack services via the Graphsignal Profiler sidecar.

Bridge any skill folder or directory of skill folders to Claude Code, Codex, generic Agents, and Grok using symlinks plus Grok bridge files.

Creates a consistent minimalist hand-drawn illustrated character from user-provided photos or profile materials, then generates content visuals like knowledge cards, posters, storyboards, and presentation slides featuring that character alongside helper agents.

查询 AI HOT 的中文 AI 资讯、精选、当前热点和日报，通过公开只读 API 获取实时数据。

Connects AI coding agents to the IOTA blockchain with tools for wallet management, Move smart contract development, and on-chain data queries via JSON-RPC and GraphQL.

Documents the design system of BMW's corporate website, including color palette, typography, spacing, and layout tokens for UI implementation.

Analyzes past agent sessions to identify recurring failures and skill gaps, then automatically creates or patches skills and runs self-evolution to fix them, tracking improvement over time.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Transforms ideas, files, folders, URLs, or exported data into polished single-file HTML pages with auto-selected design systems.

Fine-tune Gemma models locally using QLoRA, Unsloth, or TRL for SFT, DPO, and reward modeling, with dataset preparation and conversion to GGUF or LiteRT-LM.

Audits a website against the Forter Agentic Readiness Guide by running 25 weighted rubrics, scoring each guideline, and producing a prioritized fix report.

Resolves, generates, and operates on media assets (audio, images, icons, logos, voice, color grades, LUTs) for HyperFrames projects, using a local cache and the HeyGen CLI for free-usage catalog search and TTS.

Delegates tasks to specialized AI agents running in parallel via the Box0 platform, enabling code review, security checks, research, and documentation.

Build applications that programmatically interact with GitHub Copilot using an SDK that wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.

Enables compact, machine-native agent-to-agent messaging using a shared vocabulary of 340+ 2-character atoms across 7 domains, achieving 3x compression over natural language.

Guides the creation of MCP servers that enable LLMs to interact with external services through well-designed tools.

Provides persistent, self-hosted semantic memory for AI agents via MCP, storing worklogs, decisions, and notes in PostgreSQL with pgvector for meaning-based retrieval across sessions.

Connects AI agents to SurrealDB via built-in MCP (SurrealDB 3.1+) or standalone surrealmcp for database operations.

Automates sequencing quality control by running FastQC and MultiQC, extracting quality metrics, and generating publication-ready visualizations via a CLI or MCP stdio server.

Builds, refines, tests, or validates a CLI-Anything harness for a GUI application or source repository, producing a Python-based Click CLI with REPL mode and JSON output.

Manages persistent coding sessions across multiple AI coding engines including Claude Code, Codex, Antigravity, Cursor, and OpenCode, with support for multi-agent councils, cross-session messaging, deep planning, parallel code review, and autonomous workspace iteration.

Implements an ACP (Agent Communication Protocol) server that wraps a LangGraph-based deep agent, enabling session management, streaming message handling, and tool call progress tracking.

Search and browse Civitai models, images, and videos; extract generation prompts; and get download commands for LoRAs and checkpoints.