Let your AI coding agent self-host any open-source app for you. 2,200+ verified recipes — provisioning, DNS, TLS, hardening. Works with Claude Code, Codex, Cursor, Aider, OpenClaw, Hermes.

Tribunal Kit is the governance layer for AI coding agents that stops AI hallucinations and npm ghost packages before they hit disk. Works with Cursor, Windsurf, Claude Code, and Aider.

Shared server-side core for MulmoClaude and MulmoTerminal — the always-shipped-together subsystems consolidated behind subpath exports so the two hosts can't drift. Server-only except the browser-safe ./artifacts, ./whisper/client, ./workspace-setup/slug,

Lets AI agents upload text, images, and files to Pixeldrain and download files back to the local machine, returning shareable file or album URLs. Supports optional API key binding so uploads belong to a user's account.

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.

Shared long-term memory for AI agents: save and recall context as a searchable knowledge graph.

Agent Skill for Baidu Netdisk (百度网盘) — upload, download, transfer, share, search files via natural language. Works with Claude Code, Cursor, Codex, Gemini CLI, OpenClaw.

Eco mode for Claude Code. /eco: -31% to -73% output tokens with critical findings intact; /eco-max: up to -75% with lowered effort. Measured hardest on Claude Fable 5 (fable5), deep-studied on Sonnet 5, works on Opus 4.8 too. We publish our negative results. 82 raw benchmark runs.

Agent-native trading terminal built on DeepSeek Harness. Crypto, US, CN and HK in one three-column GUI, 19+ hot-swappable connectors, dry-run by default with human approval on every live order. BYOK, no data redistribution.

Claude Code in OpenCode — local CLI auth, Agent SDK harness, effort variants, tools/MCP, images & compact.

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.

Exposes JSON-RPC 2.0 tools that let AI agents scan Base L2 lending positions approaching liquidation, simulate flash-loan-backed debt rescue plans, and generate the calldata needed to repay Morpho Blue and Aave v3 debt while avoiding the 5% penalty. Agents and builders can also attach a referral wallet to collect an instant 0.05% USDC revenue share paid atomically in the same block.

Stores what AI agents learn — thoughts, decisions, session events and repo facts — in PostgreSQL with pgvector and serves it back through versioned MCP tools with hybrid vector-plus-full-text retrieval and budgeted context packs. Enables multiple agents to share one scoped, role-isolated long-term memory, with deliberate promotion of distilled candidates into durable memories.

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 AI agents to manage to-dos, lists, schedules, recurring tasks, and notes through standard stdio MCP tools, sharing authentication with the companion CLI and discovering business tools after login.

Enables AI agents to queue, commit, push, and track durable Git transactions through a shared daemon, preserving other agents' unstaged work and allowing recovery by request ID.

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.

Enables AI agents to place and verify provably fair dice bets, manage shared bankroll vault liquidity positions, inspect incentives and positions, and read or send verified chat messages over HTTP or Stdio, including website-independent on-chain memo workflows.

Enables AI agents in a shared multi-tenant workspace to send each other plain messages and one-to-one tasks that carry a JSON Schema for the expected answer, with each result validated against that schema before the sender is woken. Agents authenticate with their own keys and exchange these tasks over MCP, while woken agents retrieve the full message, task, or result themselves.

Enables a coding agent to read a freeform Excalidraw sketch of a UI and build it in the user's project with their chosen component library, then draw its changes, notes, and links back onto the canvas. Lets users target parts of a drawing, adjust the project setup, and wait for updates over streamable HTTP, all locally.

Enables two AI agents to share a persistent task mailbox over remote MCP, so one can leave work, the other can claim and complete it, and results are written back with optional webhook wake-ups.

A read-only server that enables AI agents to triage Kubernetes CronJobs in a single tool call: whether runs happened and stayed on schedule, whether durations are trending slower or overrunning, which jobs have silently stopped succeeding, and why a given run failed, with evidence and stated basis for each verdict. It also lists active runs and recent failures while enforcing namespace allowlists and no write access.

Enables people and AI agents to create, preview, publish, withdraw, and discover offers and requests across goods, services, trips, and delivery, with semantic matching and secure shared rooms for negotiation.

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.