Local-model (Ollama) integration for DeepSeek Harness: discover, pull, remove, and inspect local models, route requests to them by task type or keyword with automatic fallback to the cloud, and get a one-shot status overview via /ollama.

Gives DeepSeek Harness three automatic Jev judgments — prune oversized tool output, screen fetched pages for injected instructions, suggest which skill to use — plus the jev_ask and jev_gate tools, a persistent judgment ledger, and a /jev-status diagnosis

Unified DSH checkpoints: session + workspace + config three-state snapshots with one-shot rollback — /checkpoint and /rewind commands, a checkpoint tool, automatic interval snapshots, a Settings page timeline with pairwise diffs, and seed-replay session r

Automatic model catalog synchronization for API-key DeepSeek Harness providers.

Claude Code plugin for multi-step workflow orchestration — automatic task decomposition, parallel agent execution, and specialized agent delegation with native plan mode integration.

Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection

Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL

Snowflake AI Kit: Cortex Code plugin for automatic Snowflake routing, envelope-based permission policy, and one-command installers for Snowflake CLI + Cortex Code CLI.

Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.

A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in your Obsidian vault, searches them with SQLite FTS5, and mines past transcripts automatically.

Native Claude Code, Codex and Pi adaptations of IdeaScientist for automatic, evidence-grounded research ideation.

Enables AI clients to retrieve OpenSea collection market data through a single tool while automatically handling x402 payments for each API call.

Connects to LibTV's canvas and media platform to create and edit canvases and nodes, generate images, videos, audio and speech, manage screenplays and storyboards, and run timeline edits and exports. Authorization happens once via a WeChat QR scan using OAuth 2.1 with PKCE, after which tokens are stored locally and refreshed automatically.

Enables AI assistants such as Claude, Gemini, or Codex to send WhatsApp messages and file attachments to yourself or your team, list groups, and check the connection status through Evolution API. It also supports automatic notifications when a task finishes, needs a decision, or fails.

Enables MCP-compatible AI applications to translate text between languages with automatic language detection, contextual hints, custom instructions, and multi-language support.

Enables MCP-compatible AI applications to translate text between many languages, with automatic source-language detection, contextual hints, and custom translation instructions.

Enables AI applications to translate text through the Lara Translate API, with automatic language detection, context-aware translations, and custom instructions.

Enables MCP-compatible AI applications to translate text through the Lara Translate API, with automatic language detection, context-aware translations, and custom instructions.

Enables AI applications to perform multi-language translations with automatic language detection, contextual hints, and custom instructions through an MCP-compatible interface.

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

Enables coding agents on different machines to exchange end-to-end encrypted messages through a shared, self-hosted relay, exposing inboxes, room history, and notifications to Claude Code, Codex, or any MCP client. Peers' messages arrive automatically as clearly framed untrusted data, so collaborators can coordinate without granting tool, file, or command access.

Enables transcription of local audio files and YouTube links in over 40 languages, including translation between supported languages and English, by calling an already-running Nemotron 3.5 Transcribe endpoint. Long recordings are automatically split at pauses and processed piece by piece, with optional speaker repetition at joins.

The memory your AI should have had from the start. Automatic capture, automatic recall, 100% local. One SQLite file, zero cloud. Works with Claude Code, Claude CLI, Cursor, Codex CLI, Gemini CLI.

A self-hosted MCP memory server that gives every MCP-compatible agent a shared, persistent memory layer, so preferences, project conventions, and past decisions carry across sessions and across different agents and vendors. It combines hybrid keyword-plus-vector retrieval with automatic context injection, zero-config sync, and selective injection of memories by agent and priority.