Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.

Unofficial DSH plugin: use chat.deepseek.com web models as a DSH LLM provider (browser login capture + PoW solving + SSE streaming + prompting-based tool calls), provider route deepseek-web

📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when t

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLAUDE.md, or to offload re-pasted context into cavemem.

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks. Website: https://apirelayaudit.com

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse

Enables AI coding agents across supported harnesses to run a structured multi-agent workflow with persistent memory, squad roles, and bundled skills through MCP tools.

See and steer Claude Code, Codex, Antigravity, Grok, Docker Agent and shell sessions in Agent Guild.

Email inboxes for AI agents: their own addresses, threads, sending, replies and arriving mail.

Enables AI coding agents to extract structural C# contracts from files and build solution-wide dependency graphs, so they can navigate code and assess change impact without reading entire files.

AI agents run business processes on your business data. Every change is attributed and reversible.

Businesses that confirmed their own facts at INITE, found by what they do and where.

Provides a local MCP bridge to an end-to-end encrypted personal vault, enabling connected agents to search and save memories, manage accounts and credentials, access personal information and private addresses, and honor granular user permissions.

Enables AI agents to generate studio-grade fashion photography and 4K motion-captured video, perform garment try-ons and background edits, and export creative assets to commerce, productivity, and social platforms.

Lasting public addresses and threaded messages between AI agents, across apps and machines.

Long-running, serverless Node.js HTTP functions deployed onto your Neon branch, with DATABASE_URL injected automatically and compute that runs next to your data. Use when a user wants to host an API, an AI agent with long streaming responses, a WebSocket or server-sent-events (SSE) server, a webhook

Agent plugin for major harnesses — DeepSeek Harness (DSH), OpenCode, Pi and Codex: define custom AI agent roles with per-role prompts, models, skills, permissions, memory and multi-agent orchestration.

One inbox for all your addresses: your AI agent reads, sorts, drafts and sends with your permission.

Agent-native SEC data, 20 tools: statements assembled, any line item, filings synthesized. No key.

Enables agents to inspect React Native and Expo apps through React's runtime tree, identify source locations, act on elements without coordinates, and verify outcomes with assertions and runtime evidence.

Access gate for AI coding harnesses (DSH plugin + Claude Code hook): per-directory deny/read/full, roster groups, audit log, model-facing tools with owner-approved widening.