Agents
Built-in Synap AI, external agents, MCP, skills, and governance model.
Synap supports two complementary agent layers:
- Built-in intelligence running with your pod (orchestrator + specialists).
- External agents connected through open protocols.
All mutations remain governed by permissions and proposal review.
Connection protocols
| Protocol | Best for | Endpoint |
|---|---|---|
| Hub Protocol REST | Full agent workflows, CRUD, memory, channels | /api/hub/* |
| MCP | Claude Desktop, IDE assistants, tool-use flows | /mcp |
| OpenAI-compatible | Reuse existing LLM clients | /v1/chat/completions |
Built-in Synap AI
- Works in channels and branches.
- Can propose structured changes.
- Supports proactive nudges/briefings.
- Uses the same governance model as external agents.
External agents
- OpenClaw and custom agents connect via API keys.
- Scope-limited access per key.
- No silent writes outside allowed policy paths.
Practical paths
- OpenClaw onboarding: OpenClaw
- Skill-driven execution: Skills
- Message-native flows: Channels and agents
- Model/assistant tool interoperability: MCP
Governance
- AI writes pass permission checks.
- Non-auto-approved operations create proposals.
- Full audit trail remains in event history.