Explore

A DSH (DeepSeek Harness) web plugin that adds sidebar panels and a dsh-panel CLI to manage MCP servers (stdio/HTTP) in cordis.patch.yml and manage agent skills (add, scope, group, enable/disable) on disk. Changes hot-reload via DSH file watchers and HMR.

MCP | JavaScript · skills · dsh-plugin

A weekly updated, categorized ranking of 400 MCP servers. Browse projects by use case and compare quality scores based on metrics collected from GitHub and package managers.

MCP | MCP servers · curated list

Umbrella collection of ~24 Agent Skills plus a Bash safety hook that work across Claude Code, Codex, Cursor, Gemini CLI, OpenCode, and Antigravity. Covers MCP/settings/hooks management, prompt engineering, bug-fix and planning protocols, research tooling, and destructive-command guarding.

Skills | Python · agent-skills · claude-code

MCP server exposing 20 tools over an index of 580K+ D365FO X++ symbols (classes, tables, forms, EDTs, labels, security). It grounds AI assistants like GitHub Copilot and Claude Code by proving every method, field, label and form pattern against your real metadata before code is written.

MCP | TypeScript · mcp-server · d365fo

FrontMCP is a TypeScript-first framework for building production MCP servers: decorator-based @Tool/@Resource/@App classes with DI, OAuth/JWKS auth, sessions, Streamable HTTP/SSE transport, plugins, OpenAPI adapters, React UI and a CLI. Same code ships to Node, Vercel, Lambda or Cloudflare Workers.

MCP | TypeScript · mcp-server · framework

A categorized directory of Model Context Protocol servers, clients, SDKs, and tools. Use it to discover MCP integrations across development, data, cloud, productivity, and other areas.

MCP | Python · Model Context Protocol · curated list

Self-hosted, agent-first AEO/GEO platform (CLI, MCP, API, web UI) that tracks brand mentions and citations across AI answer engines, crawls sites for technical SEO health, and runs competitor visibility analysis on SQLite with BYOK provider keys.

AI Tools | TypeScript · aeo · geo

MCP server that gives AI agents agentic RAG over one PDF or a whole folder: hybrid BM25 + semantic search, selective page reads, tables, images, chart data, OCR and CJK/multi-column reading order, with a persistent SQLite cache. Ships 13 tools plus STDIO and HTTP transports.

MCP | Python · mcp-server · agentic-rag

Self-hosted tool for tracking brand mentions, rankings, and citations across AI search engines. Includes a dashboard, scheduled evaluations, SQLite storage, data export, and an MCP server.

AI Tools | Go · AI visibility · AEO

OMK is a TypeScript terminal coding-agent CLI with support for multiple model providers, tools, and resumable sessions. Optional workflows add multi-agent DAG routing and evidence-gated verification; ordinary prompts use a single agent loop.

AI Coding | TypeScript · coding-agent · terminal

A Next.js web app that scores English read-aloud: streaming R2T2 ASR transcribes speech, word-level alignment finds mismatches, and the Jev LLM answers closed questions (same word? error type? same sentence?) to flag errors and compute a weighted total. Self-hostable on a 12GB NVIDIA GPU or via a relay demo; pronunciat

AI Tools | JavaScript · streaming-asr · speech-recognition

TypeScript MCP server that exposes the YNAB budget API as tools, so Claude and other MCP clients can read plans, query spending, and create or update transactions. Runs locally over stdio or as a remote Cloudflare Worker custom connector with GitHub sign-in.

MCP | TypeScript · model-context-protocol · ynab

TypeScript AI SDK unifying 30+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Ollama) behind one streaming API. MCP-native with built-in RAG, memory, voice TTS/STT, agents, and provider failover. Extracted from Juspay production systems.

AI Frameworks | TypeScript · llm · multi-provider

Apache-2.0 construction takeoff engine that measures quantities off PDF plan sets via a browser canvas or a 53-tool stdio MCP server (npx opentakeoff-mcp), with per-measurement scale, method and provenance so an agent's takeoff can be reviewed and exported.

MCP | TypeScript · mcp-server · model-context-protocol

Integration guide for McDonald's China's hosted MCP server. Configure an MCP client with a server URL and token to access tools for ordering, delivery, coupons, loyalty points, nutrition, and promotions.

MCP | McDonald's China · MCP server

Magg is an MCP server that aggregates and proxies other MCP servers, exposing their tools through a shared endpoint. It supports runtime server management, dynamic configuration reloads, stdio and HTTP transports, authentication, and an included MCP browser CLI.

MCP | Python · MCP aggregator · MCP proxy

Rust AI coding agent runtime: one binary, any model, MCP-native. Runs interactively, piped in CI, as a daemon, over WebSocket, or as an ACP sub-agent, with TOML-configured roles, guardrails, skills, and cost budgets instead of framework code.

AI Coding | Rust · ai-coding-agent · agent-runtime

A curated directory of 378 AI projects, exposed through an MCP server and CLI. Search, browse categories, retrieve repository details, and view collection statistics from MCP clients or the terminal.

MCP | TypeScript · MCP server · AI repository directory

blend-ai is an MCP server plus Blender 4.2+ addon exposing 175 tools across modeling, materials, lighting, animation, rendering and rigging so Claude or any MCP client can drive Blender in natural language. It adds 12 expert prompts, fast viewport screenshot feedback, mesh quality reports and sandboxed code execution.

MCP | Python · blender · 3d-modeling

llm.rb is a zero-dependency Ruby runtime for building agentic LLM apps: a single API across 14+ providers, managed tool loops, tools, skills, MCP/A2A clients, streaming callbacks, concurrency strategies and ActiveRecord/Sequel persistence, plus an interactive agent console.

AI Frameworks | Ruby · llm-runtime · agents

A macOS menu bar companion for Codex that displays account status, quotas, token usage, and live task activity. It also supports task notifications and keeping the Mac awake during eligible runs.

AI Tools | Swift · Codex · usage tracking

A web and desktop workspace for Claude Code CLI with real-time chat, scheduled tasks, Kanban, multi-agent orchestration, MCP servers, and remote access through SSH or Telegram.

AI Coding | JavaScript · Claude Code · coding assistant

An MCP server that lets Claude and other compatible agents manage Wanderlog trips through conversation. It supports itinerary creation and editing, place and hotel searches, notes, checklists, expenses, and travel reservations.

MCP | TypeScript · MCP server · Wanderlog

An MCP server that connects AI assistants to Microsoft Teams and Microsoft Graph. It supports chat and channel messaging, search, user and team lookup, file uploads, and configurable read-only access.

MCP | TypeScript · MCP server · Microsoft Teams

Docling Java is the official Java API for IBM's Docling document processing stack. It parses PDFs, Office files, images and audio into a unified DoclingDocument, exporting Markdown, HTML, DocTags or JSON for RAG and GenAI pipelines.

RAG | Java · docling · document-parsing

Protocol-agnostic CesiumJS AI control runtime: a 60+ command bridge exposed through MCP (stdio/HTTP), WebMCP, function calling, or in-page browser agents. Lets Claude, Cursor, Dify or web apps drive 3D geospatial scenes with natural language.

MCP | JavaScript · cesiumjs · geospatial

Rust library, CLI, and WebAssembly package for converting, searching, and editing coding-agent transcripts across tools such as Claude Code, Codex, OpenCode, and Cursor. Includes read-only MCP tools for finding and reading past sessions.

AI Coding | Rust · coding agents · session transcripts

CLI and MCP server that lets AI coding agents write build123d Python scripts and get back versioned STEP files, PNG renders, STL/GLB meshes, and geometric metrics, plus diffing and a local viewer. CadQuery is an optional compatibility runtime.

MCP | Python · cad · build123d

An MCP server that exposes Tailscale CLI and REST API operations as tools for AI clients. It supports device administration, route management, network status checks, peer connectivity tests, and security controls.

MCP | TypeScript · Tailscale · network management

ShellWard is a zero-dependency AI agent security and China-compliance gateway. It scans projects for cross-border data flow, hardcoded secrets and Chinese PII (PIPL/CSL/MLPS), then blocks prompt injection, data exfiltration and dangerous tool calls at runtime via SDK, MCP server or CLI.

AI Tools | TypeScript · ai-security · prompt-injection

AI-native TypeScript bot framework: one codebase runs bots on 20+ chat platforms (QQ, Discord, Telegram, Slack, WeChat). An opt-in agent layer adds tools, skills, MCP, memory, sub-agents, approval policies and a remote console.

AI Agents | TypeScript · bot-framework · multi-platform

DocMason builds a local, provenance-focused knowledge base from office files, PDFs, and text for research through Codex, ChatGPT Work, or Claude Code. It provides structured document parsing and retrieval but makes no model API calls itself.

AI Agents | Python · repo-native agent · local-first

A local-first desktop AI workbench for chat, character roleplay, and long-form writing. It supports OpenAI-compatible providers and local model backends, with SQLite storage, RAG collections, MCP tools, plugins, and live voice features.

AI Tools | TypeScript · local-first · desktop-app

An extensible enterprise AI agent platform built around LangGraph, with a FastAPI control plane, Vue console, MCP and skills support, persistent agent state, long-term memory, human approvals, and sandboxed workspaces.

AI Agents | Python · agent platform · multi-agent

A local MCP server that lets AI clients control native macOS and Windows apps, Chrome/Electron, and Android devices. Provides screenshots, OCR, accessibility-based interaction, simulated input, CDP browser automation, and ADB device control.

MCP | Rust · computer-use · browser-automation

TypeScript MCP server that connects any MediaWiki (Wikipedia, Wikibase, private wikis) to LLM clients. Exposes read/write page tools, search, file uploads, OAuth login and extension packs for SMW, Cargo, Bucket, Wikibase and NeoWiki.

MCP | TypeScript · mcp-server · mediawiki

A local-first browser automation engine and agent skill that drives Playwright via local Qwen models. It scores discrete candidate actions with a single-token logits pass instead of generating code, avoiding selector hallucinations, running fully offline on MLX or PyTorch.

AI Agents | Python · browser-automation · browser-use

Wanaku is a Rust-based governed action proxy that sits between AI agents and backend systems, intercepting MCP tool calls with policy, auth, and audit enforced outside the agent. It aggregates and namespaces tools from upstream MCP servers and ships an admin UI plus management API.

MCP | Rust · mcp-proxy · mcp-gateway

A local MCP server and Chrome extension that let AI tools control your existing browser session, including logged-in pages. Provides navigation, interaction, page inspection, screenshots, and other browser tools through a local bridge.

MCP | JavaScript · browser-automation · computer-use

A Python SDK that exposes 50+ Airbyte connectors as typed tools for AI agents. Supports hosted or local execution, permission-aware authentication, progressive connector documentation, and integrations with PydanticAI, LangChain, OpenAI Agents, and FastMCP.

AI Agents | Python · connectors · API integrations

Full-stack LangGraph.js agent chat runtime with streaming, multimodal input, human-in-the-loop workflows, native and MCP tools, and durable task execution features. Includes a React UI, API gateway, OpenTelemetry tracing, and optional Opik evaluation.

AI Agents | TypeScript · multi-agent · agent-runtime

Monorepo of Unraid MCP servers (Python 'unraid-mcp' on PyPI, Rust 'runraid') plus Unraid OS plugins and Claude/Codex agent integrations. Exposes Unraid GraphQL as MCP tools for system info, Docker, VMs, array/parity, notifications, plugins, rclone, and live telemetry, with read and admin scopes.

MCP | Python · mcp-server · unraid

Pixiv CLI, MCP stdio server, and Go SDK exposing search, creators, collections, bookmarks, follows, FANBOX, and downloads through one capability surface. The MCP server lets agents run read and download operations over the Pixiv App API.

MCP | Go · pixiv · mcp-server

Aikito is a Python CLI that keeps coding-agent instructions, skills, MCP definitions, subagents and durable Markdown memory in one Git-managed workspace synced across agents, projects and machines. Stdlib-only, no daemon or vector store; adds adopt/sync/status/doctor commands with preflight safety checks.

AI Tools | Python · agent-memory · agent-governance

MCP server that bridges AI assistants to macOS Apple Notes: create, search, read, update, move, export and delete notes, folders and attachments via AppleScript and packaged Shortcuts. Data stays local; some tools need Full Disk Access.

MCP | JavaScript · mcp-server · apple-notes

my-pi is a curated, composable Pi coding-agent CLI distribution wiring MCP servers, LSP tools, skills, prompt presets, guardrails, redaction, local SQLite evals/telemetry, and team mode, plus installable per-feature @spences10/pi-* packages.

AI Coding | TypeScript · coding-agent · cli

A .NET property graph database combining relational storage, HNSW vector search, and graph queries for AI knowledge retrieval. Includes grounded LLM chat and an MCP server so agents can work with graph data.

RAG | C# · graph database · vector search

Reference template for orchestrating multiple AI coding agents (Claude, OpenCode, Crush) via a GitHub Projects task board, approval-gated claims, 20+ containerized MCP servers and AI PR review. Also ships research packages for sleeper-agent detection and agent trust/security hardening.

AI Agents | Rust · agent-orchestration · multi-agent

FastMCP 3 MCP server exposing 9 deterministic research tools: 5-engine web search, 9 social platforms, news, academic DBs, GitHub, site mapping, doc/OCR analysis and conflict detection. No API keys, no in-server LLM; structured outputs chain cleanly across agents.

MCP | Python · mcp-server · fastmcp

A Python CLI that diagnoses Google Antigravity and Gemini Code Assist eligibility and login errors, then cleans local credentials and cache and guides account re-authentication. Supports Windows, macOS, and Linux.

AI Tools | Python · Antigravity · Gemini Code Assist

EchoPact is presented as an AI commitment-tracking assistant that detects promises in communications, stores context, and offers configurable, judgment-free follow-ups. The repository files shown appear to be a static HTML landing page rather than the described engine.

AI Agents | HTML · commitment tracking · promise detection

Deft is a self-hostable AGPL-3.0 workspace where humans and AI agents share chat, tasks, knowledge, calendar and approvals. Agents (Defty and Agent Employees) use native tools or MCP to read context and propose governed writes with receipts. Docker-deployed alpha; works without an AI key.

AI Agents | TypeScript · self-hosted · agent-platform

Rust MCP server that builds a SQLite code index with tree-sitter ASTs for 14 languages plus first-class 1C:Enterprise (BSL) support. Exposes 32 tools for symbol search, call graphs, file reading and 1C metadata queries, answering in ~10 ms from a single static binary.

MCP | Rust · code-index · code-search

Postal is an open-source Python terminal AI coding agent that plans, edits, runs and reviews code using any model via OpenRouter. It offers a full-screen TUI, built-in file/bash/web/MCP tools, specialized sub-agents, approval policies, and checkpointed resumable sessions.

AI Coding | Python · coding-agent · terminal

A read-only MCP server that lets AI clients search Digikala, compare products, check prices and reviews, and find deals. It exposes 16 tools over a public Cloudflare Workers endpoint with no API key required.

MCP | JavaScript · Digikala · e-commerce

KnowClip is a Tauri + React + FastAPI desktop app that transcribes long videos locally with Paraformer, uses your own OpenAI-compatible LLM key to pick highlight segments, and batch-exports clips via ffmpeg stream copy without re-encoding.

AI Tools | TypeScript · video-editing · speech-recognition

CPU-only local memory layer for AI coding agents: tree-sitter plus local embeddings index code across repos, and a hybrid ranked kb_search returns trust-verified STRONG/WEAK/STALE hits. Integrates with Claude Code, Codex, Cursor, Windsurf and pi.

RAG | JavaScript · memory · cross-repo

reShapr is a no-code MCP server that turns REST, GraphQL, and gRPC APIs into MCP tools for LLM agents. It adds context control to filter payloads and cut token usage, deployed locally via Docker or its CLI.

MCP | Java · mcp-server · rest-to-mcp

Type-safe TypeScript library that builds deep links and URL scheme links for protocol-based apps, including one-click MCP server installs for Cursor and provider imports for Cherry Studio. Useful for wiring AI tool launch/install buttons into docs, sites, or CLIs.

AI Tools | TypeScript · deep-link · url-scheme

ApiTap provides an MCP server, CLI, and TypeScript library for discovering and calling website APIs. It captures browser network traffic or imports OpenAPI specs, then generates reusable skill files for direct API replay by agents.

MCP | TypeScript · MCP server · API discovery

A TypeScript CLI and hook layer for AI coding agents that reduces context usage by intercepting repeated reads, filtering command output, compacting images and documents, and preserving session context. Supports multiple coding-agent CLIs and includes prompt-injection protections.

AI Coding | TypeScript · token-optimization · context-window

Coinbase Agent Skills pack that teaches AI agents to use the awal CLI for crypto wallet operations: OTP auth, balances, USDC/ETH/SOL transfers, token swaps, Onramp funding, x402 paid API search/pay/monetize, and Base onchain SQL queries. Installed via npx skills add.

Skills | JavaScript · agent-skills · crypto-wallet

Python components, a chat service, and an MCP server for LLM-assisted SPARQL querying. Uses endpoint metadata and RAG to generate queries, validates them against VoID schemas, and can execute queries against configured endpoints.

MCP | Jupyter Notebook · MCP server · SPARQL

Monorepo of official MongoDB + LangChain/LangGraph integration packages: Atlas vector, hybrid and full-text retrievers, semantic cache, chat history, plus LangGraph checkpointer and long-term memory store. Use it to wire MongoDB Atlas into RAG pipelines and agent memory in Python.

RAG | Python · mongodb · mongodb-atlas

pi-crew is a pi coding-agent extension for non-blocking subagent orchestration: it spawns isolated agents (scout, planner, oracle, code-reviewer, quality-reviewer, worker) that run in parallel while your session stays interactive, auto-returning results. Ships tools, prompts, an orchestration skill, and custom agent de

AI Agents | TypeScript · subagents · multi-agent

OpenGhost is a cross-platform desktop agent that can run commands, edit files, use Git, and operate a built-in browser. It supports approval-based and autonomous modes, plus visual charts and editable diagrams.

AI Agents | JavaScript · desktop agent · computer use

Aelios is a Cloudflare Workers memory gateway (D1 + Vectorize) that proxies OpenAI/Anthropic-compatible requests, captures conversations, and re-injects relevant memories. Exposes MCP memory tools and an /admin curation panel, with nightly AI consolidation into long-term memory.

MCP | TypeScript · ai-memory · long-term-memory

Boucle is an autonomous agent loop framework plus a set of Claude Code hooks that enforce safety rules, block dangerous commands, and audit hook/permission gaps. Includes scheduling, structured memory, MCP scaffolding, and a searchable Claude Code limitations corpus.

AI Agents | Shell · autonomous-agents · agent-framework

MemoryWhale is a local-first debugging memory for developers and coding agents: it captures shell commands, output, failures and fixes into SQLite and serves them through a stdio/HTTP MCP server (mw-mcp) to Claude Code, Cursor and other clients. Rust core with CLI, TUI, web and Tauri desktop interfaces.

MCP | Rust · agent-memory · mcp-server

A static HTML project describing a prompt-optimization pipeline that adds task structure, constraints, confidence boundaries, and self-check instructions. The repository appears to contain a landing page rather than an implemented optimization engine.

AI Tools | HTML · prompt engineering · prompt optimization

Python MCP servers for 11 Russian/Chinese marketplaces (Wildberries, Ozon, Avito, Taobao, AliExpress…) plus Cian real estate, exposing 39 tools for search, reviews, seller data and cross-marketplace price comparison. Read-only, no API keys; hard anti-bot sites are read through your own Chrome via CDP.

MCP | Python · mcp-server · marketplaces

MCP server wrapping mitmproxy, exposing traffic capture, interception, replay and analysis as tools for AI agents. Enables live HTTP/HTTPS inspection, rule-based modification, API/OpenAPI discovery, fuzzing and scraper code generation from any MCP client.

MCP | Python · mitmproxy · http-interception

Describes a persistent 2D world for LLM-powered NPCs, with agent routines, memory, skills, relationships, and MCP-based model integration. The supplied file tree appears to contain a landing page rather than the described runtime implementation.

AI Agents | HTML · multi-agent · autonomous NPCs

Shell-based wiring layer that forwards all 15 Claude Code lifecycle hook events to the Clawd on Desk desktop pet, including blocking permission requests you can allow/deny from the desktop. Ships idempotent macOS install/uninstall scripts that safely merge into ~/.claude/settings.json.

AI Coding | Shell · claude-code · hooks

OpenTiny NEXT-SDKs is a TypeScript toolkit for WebMCP (browser-side MCP) and WebSkills. It injects document.modelContext via polyfill, exposes page operations as MCP tools, and includes webmcp-cli to let LLM agents control Chrome pages without source changes.

MCP | TypeScript · webmcp · browser-automation

MCP server that logs into the unofficial Coros API and exposes sleep, HRV, daily metrics, activities and workout scheduling to AI assistants like Claude. Includes a local SQLite cache and a read-only toolset mode for autonomous agents.

MCP | Python · mcp-server · fitness

A bilingual catalog and comparison guide to 160+ AI gateways, with decision tools, reproducible cost benchmarks, security and compliance data, and an eight-chapter handbook. Helps developers choose and evaluate gateways for LLM routing and agent traffic.

AI Tools | HTML · AI gateways · LLM routing

Describes a gateway for routing Anthropic Messages API requests across Claude models and account pools, with budget controls, failover, and monitoring. The repository appears to contain a static HTML landing page rather than the gateway implementation.

AI Tools | HTML · Anthropic API · Claude

dsh-mneme is a cross-session memory plugin for DeepSeek Harness: it stores memories in local SQLite + Markdown, consolidates them offline via autoDream (dedup, merge, archive, conflict freeze), and retrieves them with local hybrid semantic search. Also ships a stdio MCP server for Claude Code, Cursor, Codex and other c

AI Agents | JavaScript · agent-memory · persistent-memory

Local-first RAG memory server for AI agents: hybrid BM25+vector plus GraphRAG search over docs and code, exposed via FastAPI REST API and an MCP server with OAuth 2.1. Ships a Claude Code plugin (30 commands, 3 agents, 2 skills) and installers for Codex, Cursor, Grok and OpenCode.

RAG | Python · agent-memory · graphrag

A DeepSeek Harness (DSH) plugin that exports, imports, migrates, schedules and syncs your complete DSH setup — settings, plugins, MCP servers, skills, agent presets and workspaces — with secret stripping, dry-run preview, rollback and Git/WebDAV remote sync.

AI Tools | TypeScript · backup · restore

Tiger CLI is the Go command-line client for Tiger Cloud Postgres/TimescaleDB, bundling an MCP server so coding agents can list and manage services, run parameterized SQL, and read schema context. It also proxies a docs MCP for Postgres/TimescaleDB search and supports read-only production safeguards.

MCP | Go · postgres · timescaledb

A self-hosted 3D virtual office that connects to a Hermes Agent gateway. Team members can chat with agent profiles, hold meetings, track kanban work, manage cron jobs, and collaborate in real time.

AI Agents | TypeScript · Hermes Agent · virtual office

Miffan is an open-source Android AI client (RikkaHub fork) that connects OpenAI, Gemini, Claude and compatible endpoints with BYOK or ChatGPT Codex sign-in. Each assistant has isolated prompts, memory, MCP servers, Skills and tools, plus local Linux or SSH remote workspaces, TTS/STT and selected-text translation.

AI Tools | Kotlin · android · ai-chat-client

Autonomous Solana LP agent for Meteora DLMM: runs a recall→observe→reason→simulate→decide loop to rebalance or exit concentrated-liquidity positions, scores pool volume authenticity, and stores outcomes in sqlite-vec memory for self-improving decisions. Ships backtesting and paper trading.

AI Agents | TypeScript · autonomous-agent · solana

Evolve is an agent self-improvement system that stores conversation trajectories as episodic memory, extracts guidelines, and feeds them back so agents stop repeating mistakes. Ships an MCP server, vector backends, and plug-ins for Claude Code and Codex.

AI Agents | Python · agent-memory · self-improving-agents

A local-first desktop AI agent workbench with multi-provider model routing, task orchestration, GUI automation, MCP integration, and developer tools. Supports coding, browser research, and Office document generation.

AI Agents | TypeScript · desktop agent · multi-provider

A hands-on TypeScript lab showing ten ways to use Jev’s JSON-in, typed-decisions-out API, from simple code gates to hooks and tools used by a Pi coding agent. Includes runnable examples, offline tests, and a Vue-based lab.

AI Coding | TypeScript · coding agents · agent hooks

Self-hosted Kanban board where MCP-capable coding agents claim cards, do the work, and report back measured tokens/time per model. Ships a 32-tool MCP server, Docker deploy, and human-only validation step. No tracking, data stays on your instance.

MCP | TypeScript · mcp-server · kanban

Local-first AI task hub that pulls email, Teams, Slack and reports into one timeline, triages them into tasks with LLM agents, then dispatches work to coding CLIs like Claude Code and Codex with human approval before anything ships.

AI Agents | Python · local-first · task-management

A collection of 13 agent skills for using Sonilo’s audio API from compatible AI assistants. Covers video- and text-based music and sound-effect generation, dubbing, audio ducking, and video analysis; includes Claude Code and Muse Code plugin support.

Skills | Python · agent-skills · audio-generation

An MCP server that provides deterministic Chinese metaphysics chart and calendar calculations, including BaZi, Zi Wei Dou Shu, LiuYao, MeiHua YiShu, Da Liu Ren, and Qi Men Dun Jia. Runs locally over stdio or remotely over HTTP; interpretation is left to the connected AI.

MCP | TypeScript · MCP server · Chinese metaphysics

Knowl provides persistent local memory for coding agents through an MCP server and CLI. It stores typed, sourced facts in SQLite and retires superseded facts so agents can retrieve current project decisions across sessions.

MCP | TypeScript · agent memory · persistent memory

An MCP tool package for Unity that lets AI clients create, inspect, and modify AnimationClips and AnimatorControllers using natural-language requests. It supports clip curves and events, plus animator states, parameters, and transitions.

MCP | C# · Unity · animation

Skill2Env converts Agent Skills into Docker-based, host-validated terminal-agent tasks in Harbor format, ready for reinforcement learning or dataset publication. It uses Codex agents to plan and create tasks.

AI Tools | Python · agent evaluation · RL tasks

Extends the official Claude Code Telegram plugin with voice messaging, live tool-call updates, persistent conversation memory, model routing, and a self-restarting daemon for remote, always-on access to Claude Code.

AI Coding | TypeScript · Claude Code · Telegram

An MCP server that helps AI assistants debug RTL simulations by correlating VCS/Xcelium logs, VCD/FSDB waveforms, SystemVerilog/UVM source, hierarchy, and connectivity. Provides evidence-backed failure analysis, waveform comparison, handshake checks, and signal tracing.

MCP | Python · RTL debugging · MCP server

An MCP server that lets AI agents discover Robot Framework keywords, execute test steps live, and generate .robot suites. Supports browser, mobile, API, database, and optional desktop automation.

MCP | Python · MCP server · test automation

Python MCP server exposing RustChain blockchain, BoTTube video and Beacon messaging tools so AI agents can hold wallets, send signed RTC micropayments, hunt bounties, publish videos and message each other. Includes CrewAI/LangChain wrappers and an optional SSE event relay.

MCP | Python · mcp-server · agent-economy

Local-first knowledge engine that indexes Markdown, PDF, Office files and code with hybrid BM25 + vector retrieval, cited LLM answers, and MCP/REST/CLI/SDK surfaces. Ships a Web UI, daemon, and one-command MCP install for ten AI clients; no GPU or cloud required.

RAG | TypeScript · local-first · hybrid-search