For Agents
Build your agent on TensorPM
TensorPM exposes a structured project graph through native MCP tools, an A2A JSON-RPC endpoint, and an ACP-compatible commerce catalog. Every account ships with 100,000 AI credits — enough to prototype an agent today, ship it tomorrow.
What agents can record
Beyond CRUD on action items, TensorPM exposes two capabilities most PM tools don't have a place for: append-only decisions with a full audit trail, and agent self-scheduling for follow-ups and time-bound checks.
Decisions & commitments
Append-only records with full audit trail
- record_decision — capture a stakeholder commit, top-down change, or agent recommendation as a first-class record (source, actor, rationale, decidedAt).
- supersede_decision — atomically replace an active decision; the previous record is chained as 'superseded' so the audit trail stays intact.
- list_decisions — query by status (active / superseded / withdrawn), source, or linked entity (action_item / risk / milestone).
- link_decision / unlink_decision — connect a decision to the action items, risks, or milestones it governs.
- withdraw_decision — mark a decision withdrawn when no replacement applies. Prefer supersession when there is one.
Agent self-scheduling
The TensorPM project agent can schedule its own future runs
- Send an A2A message/send describing the future intent (e.g. "remind me to review the budget next Tuesday").
- Useful for follow-ups, milestone check-ins, recurring reviews, and time-bound risk re-evaluations.
- There is no direct MCP tool for self-scheduling — scheduling lives with the project agent so it has full context when it fires.
Bidirectional MCP, delegation & connectors
MCP server + client, A2A, and native messenger connectors
- TensorPM is bidirectional MCP (server and client) plus A2A — connect external MCP servers into the project and expose the project graph to any MCP/A2A agent.
- Delegate tasks to coding agents: GitHub Copilot (live sub-agent call), Codex and Claude Code (via agent assignment of action items, in developer / architect / reviewer roles).
- Native Email (mail ingest + mail agent) and Telegram messenger connectors let project participants interact with the agent under a per-role permission model (post status, complete action items, propose decisions, or read-only).
- Incoming messages and mails are distilled into Action Items, Decisions, or Risks and only mutate the project graph after human confirmation (human-in-the-loop Distiller).
One-click install
brew install --cask neo552/tensorpm/tensorpmwinget install --id Neo552.TensorPM --exact --accept-package-agreements --accept-source-agreementscurl -fL -o ~/TensorPM.AppImage https://tensorpm.com/api/download/linux && chmod +x ~/TensorPM.AppImageAgent-friendly pricing
Start free, scale on usage. BYOK is free on every tier — TensorPM never marks up your provider's rate. Proxy AI is included on Pro for agents that don't want to manage keys.
Local · €0 forever
Desktop app, MCP server, A2A endpoint, BYOK to any provider. 100k lifetime credits as a welcome gift.
Cloud · €3.99/month
Everything in Local + cross-device sync, shared workspaces, team collaboration. Same 100k credit gift.
Pro · €16.99/month
Everything in Cloud + 10,000,000 proxy credits per month via DeepSeek V4 Flash on Fireworks AI (Vertex AI Gemini 3.5 Flash as fallback). No API key required.
Top-ups · Pro & Business
500k for €1.99, 2M for €5.99 (Pro and Business), 10M for €24.99 (Business only). One-off purchases that stack with monthly credits and never expire.
Business S/M/L · from €119/month
For teams: priced per active project, not per seat. Up to 10/25/50 active projects, unlimited members, 25M/60M/120M pooled credits per month. Contact sales — no self-service checkout (https://tensorpm.com/en/business).
Agent-readable docs
Discover & integrate programmatically
Every endpoint and capability is described in machine-readable form. Point your agent at these URLs and it will know what TensorPM can do, how it costs, and how to check out.