NodeBench AI

Entity intelligence for any company, market, or question.

Live: nodebenchai.com
npm: npx nodebench-mcp / npx nodebench-mcp-power / npx nodebench-mcp-admin
GitHub: HomenShum/nodebench-ai

New to this codebase? Read docs/START_HERE.md — it follows one user's question through the code in the order it actually runs, then .tours/ walks the same path inside the live source in VS Code (CodeTour extension). docs/codebase/ has the stack, structure, conventions, integrations, testing and the honest list of known problems. docs/SIMPLIFICATION_REPORT.md records what was measured and removed, with the command for every number.

Recorded from demo/graph-rail/ replaying a committed eval transcript (persona-episode pack, 2026-01-05) through session.observe() — recorded events replayed, not re-verified; every label is a literal fixture substring, edges are traversal history, never evidence. Regenerate: node scripts/record-graph-rail-clip.mjs.

Product

NodeBench is a research and reporting product built around five user-facing surfaces:

• Home = start quickly
• Reports = reusable memory
• Chat = do the work
• Inbox = captures, nudges, alerts, automations, and unassigned review
• Me = operator context and control

Deep research opens in the separate Workspace surface at nodebench.workspace; it is not a sixth tab in the operating app.

The core idea is simple:

users do not just need a chatbot that answers once.

They need a system that can:

• take a question, file, URL, or prior thread
• search and synthesize with sources
• turn the run into a reusable artifact
• watch for meaningful change later
• improve the next run from what it learned

Pending Release Candidate: Runtime-Grounded Control Focus

This candidate is not yet merged or deployed. It narrows the reachable product to controls backed by a real runtime capability and makes unavailable state explicit:

• Agents keeps ask, explicit swarm launch, active work, approvals, sources, traces, receipts, exports, and provenance while removing projected metrics, synthetic fallbacks, duplicate actions, and local-only controls.
• Generated code remains copyable and exportable but never executes inside the signed-in app origin. Runtime cards accept successful structured tool output, not assistant prose, guessed search fields, or incomplete/error states.
• Canonical owner-scoped streaming remains; an unreferenced bearer-stream component and HTTP route were removed instead of retained as a second path.
• Home, Reports, Chat, Inbox, and Me use live runtime data, owner-scoped where private, or honest loading, empty, not-found, and unmeasured states instead of reachable product fixtures. Desktop and mobile now share the same Inbox and Me component trees; duplicate queue/profile renders and their hard-coded plan, usage, connector, and local-draft projections were deleted.
• Pipeline launches and schedules require an authenticated server identity, while guest history, detail, bundle, stream, and evaluation reads require an anonymous-session possession credential. Browser-supplied owner keys are no longer an authority boundary, and trusted cron or MCP work stays on internal contracts.
• Authenticated launches consume durable per-owner admission: four units per ten minutes and thirty per day, with composed runs costing two units. Server input bounds and per-owner schedule caps close the remaining cost-abuse path.
• Fresh pipeline attempts and recurring schedule occurrences are isolated by durable attempt identities and execution-generation fences, so retries can resume the same attempt without stale or overlapping workers rewriting it.
• Research distinguishes sources consulted from citations actually bound in the synthesis. Missing, malformed, or unbound evidence cannot be promoted to a verified claim, and chat no longer injects citation markers into prose.
• Operator telemetry and maintenance are deferred until deliberate disclosure and require server-confirmed operator access.
• Task sessions, traces, steps, evidence, approvals, swarms, and operational history are owner-scoped. The unreachable parallel timeline, kanban, hook, and public orchestrator were removed; due diligence retains only a bounded, owner-checked internal task substrate. Unused public due-diligence, investor, demo, and evaluation entrypoints were internalized or removed, and retained job, branch, memo, and catch-path writes require the exact owner chain. Raw orchestrator writes use internal contracts, MCP document and spreadsheet operations require exact object ownership, and a TRACE completion fails closed unless its receipt persists with an exact output hash.

Release evidence is intentionally pending. The source PR must merge through the required CI gates first; a follow-up evidence-seal PR must then record the canonical squash SHA, exact-revision checks, preview assertions, production deployment revision, and direct production browser verification before this section can be described as shipped.

What Shipped

• five-surface web app across Home, Reports, Chat, Inbox, and Me
• separate deep-work Workspace shell at nodebench.workspace
• typed search and reporting pipeline
• hosted public research MCP for external apps and agents: https://nodebench-mcp-unified.onrender.com?profile=public-research
• Pi-AI pipeline lane on Reports with code-gen, design-gen, research, composed runs, schedules, streaming previews, eval scorecard, and MCP HTTP bridge
• live SSE streaming with saved runtime state
• Convex-backed product state for sessions, reports, entities, nudges, files, and related objects
• shared-context handoff and delegation plumbing
• local and deployed server runtime for search, streaming, voice, and shared context routes
• nodebench-mcp, nodebench-mcp-power, and nodebench-mcp-admin distribution lanes
• builder-facing Oracle, dogfood, eval, replay, and control-plane infrastructure

Live graph rail on a LIVE Convex backend

The rail inside the product UI

The rail lives in the real product page — apps/web/src/features/research/components/EntityGraphRail.tsx, mounted in EntityProfilePage (/#entity/<name>, the grammar digest links emit). It is fed by the SAME reactive queries the page already holds (entityContexts.getEntityContext, relationshipGraph.getEntityGraph, adaptiveEntityQueries.getAdaptiveProfile) — zero new subscriptions. Counts stay undefined and every edge is traversal: research prose measures nothing. Regenerate: node demo/graph-rail-live/record-product-rail.mjs (exits nonzero if the rail is missing, stays under 4 nodes, or fails to grow after the live write). See docs/GRAPH_INTEGRATION.md for the event taxonomy.

The standalone live viewer

No replay file: demo/graph-rail-live/ subscribes to the real domains/knowledge/entityContexts:getEntityContext query on an isolated dev deployment, and the repo's own seed script writes through the real mutation on camera. All edges traversal — research prose is not a measurement. Regenerate: node demo/graph-rail-live/record-live.mjs <dev-deployment-url> (see the script header for the one-time deployment setup).

Live graph rail (recorded events)

demo/graph-rail/ feeds the NodeGraph Live renderer (vendored at vendor/nodegraph-live/, pending npm publish) with real entity-research events from a committed eval transcript (benchmarks/history/archived-2026-q1/persona-episode-eval-pack-20260105-153100.json) — it is a replay of recorded events, not a live agent run: every label is a verbatim string from that fixture, all counts render as unknown because the transcript holds no measured pair counts, and no assertion edges are drawn because no record carries a complete source receipt. node scripts/capture-graph-rail.mjs regenerates the capture and exits nonzero on an empty rail, any console error, or any rendered label that does not appear in the fixture.

Hosted Public Research MCP

NodeBench can be used as a public research memory and tool server from any agent or app without forcing signup before the first useful result.

Use the hosted MCP endpoint:

https://nodebench-mcp-unified.onrender.com?profile=public-research

For Gmail/job-match style integrations, use the smaller profile:

https://nodebench-mcp-unified.onrender.com?profile=gmail-research

Public profiles are anonymous by default, but still metered. Responses include:

x-nodebench-request-id
x-nodebench-profile
x-nodebench-auth-mode
x-nodebench-account-key

Apps should send stable, non-sensitive client headers: