Project memory and workflows for Claude Code and Codex. Keep stories, plans, handovers, and review evidence in your repo. Resume across sessions and follow progress in the Mac app.

Enables AI assistants to read and write a local-first SQLite memory vault from inside a chat — orienting on inherited context, searching and fetching past decisions and notes, wandering linked memories, and recording new ones on demand. All data stays on the user's machine, shared across local and cloud tools via MCP.

Run local AI across all your computers. Toskar's MCP server lets Claude, Cursor, and other clients ask your own local models and search your connected knowledge, with nothing leaving your machines.

Provides AI coding tools with one local SQLite memory and rules store they can read over MCP, REST or the CLI, so facts, sessions and goals persist across sessions and shared rules are written into each tool's own instruction file. Runs entirely on your machine with no account, telemetry or network calls by default.

Enables multiple DSH plugin/session agents to share trust-labeled Markdown memory and query on-demand cross-plugin digests, with write access isolated per channel so untrusted third-party content cannot become instructions.

Extension manager for AI coding agents — install skills, subagents, MCP servers, rules, hooks, knowledge, and packs across Claude Code, Codex, Cursor, Copilot, and more.

Enables MCP-capable coding agents to act as a deterministic technical art director and multi-engine pipeline builder, locking AI-generated 2D/2.5D game assets to consistent camera angles, palettes, rigs, atlases, and exports across Blender, ComfyUI, UniRig, LibreSprite, Godot 4, Unity, and Unreal Engine 5.

Exposes local recommendation tools over MCP so clients can rank groceries with explainable scoring across nutrition, price, promotions and close-to-expiry offers. Also supports configurable offer monitoring, weekly plan digests and deduplicated notifications backed by SQLite state.

Enables AI coding agents to save, recall, read, list, and forget plain Markdown memories shared across tools and sessions, so facts are retrieved on demand instead of being repeated.

Enables Claude Code users to inventory the MCP servers, skills, commands, agents and plugins installed on their machine, estimate how many tokens each one adds to every request, and switch them off per project or globally, including across other AI coding tools. It also monitors live sessions to report real token usage and the savings achieved from disabled items.

Enables reading, creating, editing, and exporting Google Docs, Sheets, and Slides across multiple independently authenticated Google accounts, with dry-run previews and revision checks for content-changing operations.

Enables Claude to search, download, upload, trash, rename, move, and share Google Drive files across multiple independently authenticated Google accounts through one local stdio connection, with scoped access and confirmation safeguards.

Enables Claude to read and manage Google Calendar across several independently authenticated Google accounts through one local connection, with dry-run previews for all writes.

Drives the local Doubao desktop client through its DevTools interface, letting an agent read and send chats, run task-mode work, hand off a project directory and take it back, and call Doubao-only capabilities like image generation and step traces. Also borrows Doubao's built-in skill set for cross-checking and project handoff, with a UI badge showing which side currently owns the work.

Provides a shared, repo-local memory that lets coding agents recall relevant decisions, conventions, gotchas, and open threads, save new entries, coordinate file claims, and cache file summaries across tools and sessions.

Connects a real ChatGPT Dot to QQ through QQBridge and SnowLuma, letting it receive wake events, read text and image messages, and send replies, images, and forwarded media within whitelisted conversations. Supports event subscriptions, per-conversation claiming, and explicit turn completion across private and group chats.

Enables mining Amazon product reviews for one ASIN per request — fetching paginated reviews, surfacing complaint signals from critical reviews, summarizing sentiment and rating trends over time, ranking complaint themes, and producing a combined per-ASIN report across 14 marketplaces.

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.

Enables MCP hosts to spawn, supervise, and collect results from parallel panels of pinned-model OpenCode v2 agents for delegated tasks, reviews, and cross-model comparisons. Supports per-member roles, models, permissions, follow-up prompts, cancellation, and persisted result retrieval.

Enables keyword search across source-traceable evidence chunks, listing opportunities linked to supporting evidence, and deterministic ROI calculations with model-proposed inputs and TypeScript-computed dollar figures.

Enables coding agents to record product demos, changelog GIFs, help-center guides, and bug repros by driving a signed-in browser or Mac window, then rendering branded MP4 and GIF outputs with delivery checks.

Gives any MCP client read-only access to Hyperliquid HIP-4 outcome market data from every deployer, including order books, fair lines with their sources, rule comparisons across deployers listing the same question, and the newest listings. Also surfaces fee-adjusted edge figures and listing order so users can scan markets, price questions, and check rule consistency.

Enables AI applications to perform text translation across numerous language pairs with automatic source-language detection, contextual hints, and custom instructions.

Experimental Windows-first MCP server for Adobe Photoshop, with guarded brush-based painting and direct document and layer tools through a local UXP bridge. Requires local Photoshop on Windows for execution; Linux supports MCP catalog introspection only.