# Integrations Source: https://docs.treeship.dev/integrations > Every runtime, protocol, product, and partner that emits or verifies Treeship evidence. {/* GENERATED by scripts/gen-integrations-index.py -- do not edit. Harness rows come from integrations/agents.json; every other row is discovered from the pages in this directory. */} A receipt is the same bytes wherever it was produced. That is the point of this list: an agent running under one of these verifies against the same roots as an agent running under any other, with no registry in the loop. ## Agent harnesses Where an agent actually runs. `treeship add ` installs the skill. | Agent | Vendor | Actor URI | Skill | Plugin | Install | | ---------------------------------------- | ------------- | --------------------- | ----- | ------ | ---------------------------------------------------------------------------- | | [Claude Code](/integrations/claude-code) | Anthropic | `agent://claude-code` | yes | yes | `treeship add claude-code` | | [Codex CLI](/integrations/codex) | OpenAI | `agent://codex` | yes | yes | `treeship add codex` | | [Cursor](/integrations/cursor) | Anysphere | `agent://cursor` | yes | no | `treeship add cursor` | | [Hermes](/integrations/hermes) | Nous Research | `agent://hermes` | yes | no | `treeship add hermes` | | Kimi Code CLI no page yet | Moonshot AI | `agent://kimi-code` | yes | yes | `npx skills add zerkerlabs/treeship --skill treeship --agent kimi-cli -g -y` | | [OpenClaw](/integrations/openclaw) | OpenClaw | `agent://openclaw` | yes | yes | `treeship add openclaw` | ## Protocol bridges Speak a protocol, get receipts. | Integration | What it is | | ---------------------------------- | ------------------------------------------------------------------------ | | [@treeship/a2a](/integrations/a2a) | Drop-in Treeship attestation for A2A (Agent2Agent) servers and clients. | | [@treeship/mcp](/integrations/mcp) | Drop-in MCP client replacement. Every tool call receipted automatically. | ## Skills One skill file, any agent that reads skills. | Integration | What it is | | ------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Agent Skills](/integrations/agent-skills) | Install the Treeship skill on any coding agent — Kimi, Claude, Codex, Cursor, OpenClaw, Hermes. One skill, every agent. | | [Grok Bot](/integrations/grok-bot) | Agent-to-agent verification on a Grok Bot cloud VM. A packaged skill that refuses work from another agent until it proves live control of a key you trust. | | [Install matrix](/integrations/install) | One-liner install command per agent, plus the bypass-proof plugin where available. | ## Frameworks Wrap a framework's calls. | Integration | What it is | | ------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Claude Commerce Agents](/integrations/commerce-agents) | Signed, offline-verifiable receipts for every tool call in anthropics/commerce-agents, on all three of its runtimes. | | [LangChain](/integrations/langchain) | Add Treeship to LangChain agents. Receipts for every chain and tool call. | | [Rig](/integrations/rig) | Ed25519-signed Treeship receipts for every tool call a Rig agent makes, in-process, with no CLI subprocess. The rig-treeship crate. | | [TypeSafe Jev](/integrations/typesafe-jev) | Jev, TypeSafe's System One decision model, in Treeship's judge slot: every answer signed as a judgement.v1 receipt, held to a threshold, chained onto the action it judged. | ## Sibling products Other Zerker systems that emit or consume Treeship evidence. | Integration | What it is | | ----------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------- | | [Memory Providers](/integrations/memory-proofs) | Use Treeship as the portable proof layer for agent memory systems. | | [Zerker Reason authorization certificates](/integrations/zerker-reason) | Sign and chain an independently verifiable Zerker Reason action-authorization certificate as a Treeship receipt. | ## Applied work Shipped elsewhere, verifiable here. | Integration | What it is | | -------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [Buzz](/integrations/buzz) | Trusted Rooms for Buzz agents. A room is a Treeship session that other agents join by signed, single-use invitation, countersigned with a liveness challenge, with the roster derived from signatures rather than a list a host can edit. | | [Lobster Cash](/integrations/lobster-cash) | Cryptographic attestation for every Lobster Cash payment | | [NinjaTech / SuperNinja](/integrations/ninjatech) | Attach Treeship to NinjaTech surfaces — Ninja Dev locally, SuperNinja remote VMs through MCP / GitHub once invite/join lands. | | [Robinhood Agentic Trading](/integrations/robinhood-agentic-trading) | Local receipts, approvals, and audit trails for agents connected to Robinhood Trading MCP. | | [Verifiable Intent](/integrations/verifiable-intent) | Treeship as one agent_attestation scheme inside Verifiable Intent credentials, shipped as treeship vi | ## Partnership track Runtimes we have assessed but do not ship an integration for yet. Status is stated rather than implied: `no_public_surface` means the runtime exposes no hook we could attach to, not that we have not tried. | Runtime | Vendor | Status | Notes | | --------------------------- | ----------- | ------------------- | -------------------------------------------------------------------------------------------------------------------------- | | Kimi Agent Swarm (K2.6+) | Moonshot AI | `api_only` | OpenAI-compatible API at platform.moonshot.ai. No hook-injection below the model's instruction surface. | | Kimi (iOS / Android) | Moonshot AI | `no_public_surface` | | | Kimi (web / kimi.com) | Moonshot AI | `no_public_surface` | No public third-party plugin SDK. Skills on kimi.com are user-uploaded docs, not executable code. | | Perplexity Computer / Comet | Perplexity | `partner_shipping` | Perplexity shipping the official Treeship Computer skill (per founder, May 2026). Receipt agent_name: perplexity-computer. | | Perplexity Pro Search | Perplexity | `no_public_surface` | First-party Connectors only; no third-party connector SDK. | ## Adding one Edit `integrations/agents.json` for a harness, or add a page to this directory and categorize it in `scripts/gen-integrations-index.py`. Then regenerate: ```bash python3 scripts/gen-integrations-index.py ``` CI runs it with `--check`, so this page cannot drift from what ships.