Starter path · Operational trust first

Install, run, inspect—then replay

“Start free” is for builders who want receipts: trust scores, GhostLog lineage, timelines, and guided missions—not a conceptual tour first. Finish with Recon vs chaos when you want the why behind orchestration, or read the runtime continuity manifesto for the replay-native posture behind it.

Run your first replay in under 5 minutes

Generate local trust receipts, open seeded replay, then spot drift, interventions, and autonomy decisions—labeled honestly as starter/demo workspaces until ingestion is wired.

Run first replay

Activation in ~5 minutes

Keep your runtime. Add receipts.

Compare runtime adapters →
1
Keep your runtime / pick your stack

Recon does not replace your runtime. It wraps replay-safe evidence around the stack you already run.

2
Install @reconai/sdk

Add the SDK, then run the local demo path before wiring production ingestion.

Jump to install →
3
Run first replay

Use the deterministic playbook to see trace, replay, drift, and evidence vocabulary.

Open first replay →
4
Open GhostLog / timeline

These surfaces may be empty until ingestion is wired; seeded replay stays available.

5
Trust Agent summary

What you'll see in a wired workspace (Starter inspect-only posture):

  • Replay reconstructed from the receipts Recon can see.
  • Starter posture stays inspect-only until you wire authority.
  • Evidence continuity shows where lineage, drift, and checkpoints held.

Step 1 · Install the SDK

npm install @reconai/sdk

TypeScript / Node surface. LangChain adapter (Python): reconai-langchain on GitHub (PyPI when published). Explore version and peer deps on npm.

Step 2 · Run locally

Step 3 · Inspect trust in the product

Step 4 · Why orchestration differs (optional)

Same workflow with and without the trust layer—use this after you have a mental model from installs and replay. Better as mid-funnel conviction than first click.

See Recon vs chaos (narrative)

Need an account or higher limits? Back to pricing · Contact