Which agent setups we have run.
A setup is tested once we have run it with the VITNA guard and recorded the version and date. Until then it is documented, not yet tested: its config follows the client's own documentation. The config for each is on Connect your agent.
Tested
Run with the guard: a hold was held, approved and denied.
| Setup | Status | Holds |
|---|---|---|
| Claude Code | Tested 2026-10-14, version 2.1.299. Proven:
| Waits for the decision |
VITNA Desktop as the guard's evaluator
Guard mode can send each tool call to VITNA Desktop on your own machine instead of the cloud: the app checks it before the server sees it, and you decide holds in the app. Records are signed by a key on that machine, not by VITNA.
Run on VITNA Desktop 0.8.0 (built from the v0.8.0 release tag, run with a test identifier and its own data folder), guard 0.5.6, 2026-10-13. Proven:
- A hold: a call to a tool the policy holds waited for a person.
- Approve: the approved call ran.
- Deny: the denied call did not run.
- Expiry: a hold nobody answered was blocked.
- The look tool: the agent changed its emoji and colour in the aquarium, and nothing else.
- Retry after approval: the same call, retried after an approval, ran once.
- The agent's own key refused: no key can decide a hold (the decide route answers 403).
Documented
Config known from the client's docs, documented, not yet tested.
| Setup | Status | Holds |
|---|---|---|
| Claude Desktop | documented, not yet tested | Waits for the decision |
| Codex CLI | documented, not yet tested | Waits for the decision |
| Gemini CLI | documented, not yet tested | Waits for the decision |
| Cursor | documented, not yet tested | Held, not run; retry after approval |
| VS Code (Copilot) | documented, not yet tested | Waits for the decision |
| Cline | documented, not yet tested | Waits for the decision |
| Continue | documented, not yet tested | Waits for the decision |
| Zed | documented, not yet tested | Waits for the decision |
| Goose | documented, not yet tested | Waits for the decision |
| Windsurf / Devin Desktop | documented, not yet tested | Held, not run; retry after approval |
| OpenClaw (VITNA plugin) | documented, not yet tested | Waits for the decision |
| OpenClaw (MCP servers) | documented, not yet tested | Waits for the decision |
| OpenAI Agents SDK (Python) | documented, not yet tested | Waits for the decision |
| OpenAI Agents SDK (JS) | documented, not yet tested | Waits for the decision |
| Google ADK (Python) | documented, not yet tested | Waits for the decision |
| LangChain MCP adapters | documented, not yet tested | Held, not run; retry after approval |
| CrewAI | documented, not yet tested | Held, not run; retry after approval |
| AutoGen | documented, not yet tested | Waits for the decision |
| Microsoft Agent Framework (Python) | documented, not yet tested | Held, not run; retry after approval |
| LlamaIndex | documented, not yet tested | Waits for the decision |
| Mastra | documented, not yet tested | Waits for the decision |
| Vercel AI SDK | documented, not yet tested | Waits for the decision |
Not supported
Setups the guard cannot sit in front of, and why.
| Setup | Status | Holds |
|---|---|---|
| n8n (MCP Client Tool) | Its MCP Client Tool connects over SSE and HTTP only, not stdio, so the guard cannot sit in front of it. A remote VITNA gateway is planned. | – |