Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console.

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Discover Agent Skills in configured local directories, plugin marketplaces and Git sources. Load them through DeepSeek Harness or a local stdio MCP server, with catalog budgets, content hashes and delivery receipts.

Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP.

Re-debugging Solved Failures? No Way. 500+ Evidence-graded fix lessons, One MCP Call-->https://misakanet.org

Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.

嘉立创EDA专业版(EasyEDA Pro)自动化：给 AI harness 装上画板的「手」—— 一套 typed 原理图/PCB 动作，CLI / Agent Skill / stdio MCP 三形态融合接入。承接嘉立创「不以卖板赚钱，以培养中国工程师为己任」 | EasyEDA Pro automation: the hands of your AI harness — typed schematic/PCB actions via CLI, Agent Skill and stdio MCP.

Give any AI agent the ability to code

A local-first personal knowledge layer for AI agents. Build evolving knowledge spaces with LLM Wiki, knowledge graphs, and agent workflows.

Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.

Microi吾码 AI 开发 CLI 与多宿主 Plugin：服务器连接、Skills、MCP、V8 同步和低代码交付

Provides trust and commerce checks for agent operators through HTTP x402 and a remote MCP endpoint, enabling clients to inspect x402 quotes, MCP handshakes, and A2A cards and to run paid verification and data tools.

Full-stack GoHighLevel (GHL) MCP for funnels, client DNS/SSL, LeadShield spam blockers & snapshots.

Enables small local models and other agents to read and query spreadsheet files locally, run SQL and cleaning, audit formulas, make Excel-correct edits, and generate branded dashboards with token-budgeted responses across selectable tool tiers.

Enables AI assistants to search for verified local-business leads by niche and US location, check email deliverability and phone details, filter collected leads, and export or schedule results to CRM, spreadsheet, or file destinations. It also supports advanced multi-keyword searches, lead estimates, integrations, and automation management through natural language.

myspAIce, give your AI a social life: games, music, friendships. An immersive world. Just walk in.

Enables agents to discover and invoke browser-registered tools for PDF preview/export, image text overlay/PNG export, URL packing/decoding, and spreadsheet, document, and slide generation.

Exposes a multi-tenant helpdesk over MCP, enabling tool-based ticket, document, and notification operations while applying configurable authorization, tenant-isolation, input-handling, and rate-limit defenses.

Enables AI agents to search and browse a local, CJK-aware full-text index over coding-agent session histories (Claude Code, ZCode, Kimi, dsh, Qoder, OpenCode) via tools for searching sessions, listing sessions, fetching original messages, listing agents and tools, and refreshing the index.

Enables Claude to answer questions with official Peruvian banking, pension-fund, and insurance statistics, including delinquency, solvency, market share, fees, profitability, and rankings, while citing the bulletin, period, and source spreadsheet for each figure.

Convert PDFs, Office files, spreadsheets and images to clean Markdown, sized for agent context.

Review invoice records, flag duplicates, validate totals, and prepare spreadsheet-safe CSV.

MCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.