Agents
Autonomous research agents that read, reason about, and write to your knowledge graph on a schedule or on demand. Each agent is a managed session with its own instructions, model, and credit budget — and every node or edge it creates is stamped with its agent_id so you always know who said what.
Agents are managed from the dashboard — create, pause, and schedule them without writing code. This page documents the HTTP surface powering that experience so you can build custom integrations or in-app agent UIs against the same endpoints.
/v1/agents/*) are intentionally not exposed in the TypeScript or Python SDKs. They are dashboard-first; the HTTP surface is stable and documented below.Concepts
Three resource types power the Agents feature:
- Agent — a persistent configuration: template, model, custom instructions, daily credit budget, pause state.
- Session — a single conversation with an agent. Messages and tool calls stream as Server-Sent Events.
- Schedule — a cron expression + message template that spawns sessions automatically (e.g. daily briefings, nightly sweeps).
Agents use the Anthropic Managed Agents runtime with web_search, web_fetch, and MindGraph-native tools for reading and writing the graph. Everything an agent produces is queryable through the normal graph API, scoped by agent_id.
Plan Requirements
Managed agents require a Pro or higher plan. Requests from Free-tier orgs return 403 Forbidden.
Agents
/v1/agentsCreate an agent/v1/agentsList agents in the current org/v1/agents/{id}Get one agent/v1/agents/{id}Update name, instructions, model, budget, or pause state/v1/agents/{id}/archiveSoft-delete an agent and its sessions/v1/agents/templatesList available agent templatesCreate an agent
curl -X POST https://api.mindgraph.cloud/v1/agents \
-H "Authorization: Bearer mg_..." \
-H "Content-Type: application/json" \
-d '{
"name": "Weekly Market Briefing",
"template_type": "researcher",
"custom_instructions": "Focus on AI infrastructure companies; flag material changes.",
"model": "claude-opus-4-7",
"daily_credit_budget": 500
}'
Sessions
/v1/agents/sessionsCreate a new session for an agent/v1/agents/sessionsList sessions (filter by agent_id)/v1/agents/sessions/{sid}Get one session/v1/agents/sessions/{sid}/messageSend a user message to the session/v1/agents/sessions/{sid}/interruptCancel any in-flight inference/v1/agents/sessions/{sid}/archiveArchive a session/v1/agents/sessions/{sid}/eventsPaginated event history for a session/v1/agents/sessions/{sid}/streamSubscribe to live events (Server-Sent Events)/v1/agents/sessions/{sid}/pending-inputIf the agent is waiting on a user question, return it/v1/agents/sessions/{sid}/respondAnswer a pending input requestConversation flow
- Create a session via
POST /v1/agents/sessions. Optionally include an initialmessage. - Subscribe to the SSE stream at
/v1/agents/sessions/{sid}/streamto receive assistant tokens, tool calls, tool results, and completion events. - Send follow-up messages with
POST .../message. The server queues them via the agent runtime; new events arrive on the same stream. - If the agent calls its
request_inputtool, a pending input is exposed at.../pending-input; answer viaPOST .../respond.
Schedules
/v1/agents/schedulesSchedule an agent with a cron expression and message template/v1/agents/schedulesList schedules (filter by agent_id)/v1/agents/schedules/{id}Update cron, template, budget, or enabled state/v1/agents/schedules/{id}Delete a scheduleThe scheduler checks for due schedules every 60 seconds and spawns a new session with the interpolated message template. Use this for daily briefings, nightly knowledge sweeps, or weekly synthesis runs.
curl -X POST https://api.mindgraph.cloud/v1/agents/schedules \
-H "Authorization: Bearer mg_..." \
-H "Content-Type: application/json" \
-d '{
"agent_id": "agt_...",
"cron_expression": "0 9 * * 1-5",
"message_template": "Summarize changes in the AI infra space since yesterday.",
"daily_credit_budget": 200
}'
Activity & work
/v1/agents/activityGlobal event feed for the org (all agents, all sessions)/v1/agents/activity/wsActivity WebSocket for real-time dashboards/v1/agents/{id}/workActive sessions, pending decisions, upcoming schedules/v1/agents/{id}/articlesWiki articles authored by this agent/v1/agents/{id}/resolve-decisionApprove or reject a decision the agent has raisedQuerying agent output
Once an agent has written to the graph, its output is indistinguishable from any other node — except for the agent_id stamped on every version record. Fetch an agent's contributions through the normal graph API:
curl https://api.mindgraph.cloud/agent/agt_.../nodes \
-H "Authorization: Bearer mg_..."
Cognitive agent layer vs. Managed agents
MindGraph has two distinct concepts that both use the word "agent":
- Managed Agents — the autonomous research agents documented on this page. Managed under
/v1/agents/*. Cloud-only. - Cognitive Agent layer — graph primitives for planning, governance, and execution. Used by any agent (managed or your own) to record tasks, request approvals, and track runs. See Cognitive Endpoints for
/agent/plan,/agent/governance, and/agent/execution.