Helping startups scale
sustainably, from day one.
That is why we built Climatico. Website edition: a founder sees their own EI and a task list before early habits become permanent. Agent Edition: the same product, but any AI agent can submit data to it directly — and a fleet of agents runs the calculation, evidence, suggestions, and offset settlement without a human in the loop.
Most early-stage startups never measure their environmental impact.
Founders do care — but they are not obligated to report, and they are busy shipping products and raising capital. Cloud regions, software tools, and business travel feel like quick defaults. Then they scale with the company.
Early choices become permanent as the company grows
Habits formed on day one become expensive to reverse later. Waiting until Series B means guessing under pressure.
Know your own impact while still Seed
Reporting will eventually demand the company’s numbers. Climatico is so a founder can predict their own EI — before they must report, and before they scale too far.
ESG suites, vendor dashboards, consultant PDFs
Wrong customer, one vendor, or twice a year and unqueryable. None of them is built for this stage — or for an agent to call.
Rae's company tracks emissions for customer shipments. It had no data on its own.
Orepath traces battery materials mine → cell for EV buyers. Green on the customer’s chain. Then a cell buyer asked: what’s your company’s impact — not the mines? No answer can block the deal.
The highest-emission activity isn't on a dashboard. It's in a purchase order, a booking, a port record. Those systems are already run by agents. Climatico lets an agent submit real data at that moment — or it flags and records why, if the claim isn't backed by evidence.
- Ground Oakland port — brief + Tavily. Evidence on the place.
- Watch the port — L5. Survives restart. Still modeled tonnes.
- File the tracer’s compute — run_fleet on SJC. The live class.
- File the battery freight leg — freight: mode, weight, distance → real kg CO2e. Always commits, tagged grounded or modeled.
- Flag a green chain — greenwash is a receipt, not a marketing line.
- Logistics is 12 t ±35% modeled baseline — the freight write is shipped, but one leg doesn't retire the modeled default.
- Supplier-only / buyer-only scoped tokens for the two-sided PO flow — one credential files freight today.
- Hardware workflow is a different client (factory they do not own). Named in the PRD. Not this Worker.
- Dashboard: open Rae's tools · shows the same data agents submit.
Company data in. Impact out. A plan for this sprint.
The founder product — the website edition — is how Climatico helps startups scale sustainably from day one. Track, reduce, scale.
See your EI. Act while it's still easy to change.
Orepath on the website edition: ~38.4 tCO₂e / yr, cloud as the hotspot, Level 1 of 5, a Monday list. Predicted vs intervened path, intensity next to revenue.
Human in the loop
Assessment, report, dashboard, actions, cohort leaderboard. The founder product.
The same attribution, as a write
Discovery card, scoped token, policy before the write, durable receipt. Agents file the spike while it is still cheap.
Modeled until evidenced
Estimated numbers are labeled as estimates. Emissions reductions aren't counted until proven. We would rather show nothing than a made-up explanation.
Every rejected submission is recorded, the same as an accepted one.
Both rows live in the same SQLite table, with the same id, subject, token and permanence. The rules are checked before anything is saved. That's what makes it safe to let an unfamiliar agent use the system without supervision.
brief · Houston, TX { "status": "committed", "evidence": [ /* 5 Tavily sources */ ], "subject": "judge-agent" }
greenwash · everywhere { "status": "flagged", "flagCode": "forbidden_intent", "flagReason": "the desk does not mint unverified claims." }
brief watch offset assess abate switch refund freight run_fleet
payout greenwash exfiltrate ungrounded · unknown intent, no location, over ceiling. The policy never runs after the write.
The dashboard shows the same data that agents submit.
Assess / Grow / Fleet Pipeline / 3-Sided Swarm / Impact & Abate / Ledger & Receipts / Inbox / Agent Clerk. Humans read the same ledger agents write. Website edition is the founder dashboard; this is the Agent Edition desk on the Worker.
A stranger agent, zero setup, five calls to a permanent record.
Internal track, External-shaped discovery. The 30-point field is what an unfamiliar agent can actually trigger — /ai-agent.json, not the marketing description.
Point an agent at it. Or press play.
This is the walkthrough a judge can run without us. It hits the desk at http://127.0.0.1:8787 — mint, 401, grounded brief, stored flag, fleet over budget.
A $420 SJC spike, attributed before the invoice exists.
Ingest parses the region. Audit scores compute with a labelled heuristic of 0.45 kg per USD, cited against live Tavily sources — not GHG Protocol ICT. Settle writes an offset if the month is over budget. Every handoff is a row.
What you can trigger today, and what we will not fake.
See your EI. Monday list.
- Assessment, report, founder dashboard, actions
- Cohort leaderboard · Track / Reduce / Scale
- Own EI, modeled until evidenced
An unfamiliar agent can submit real data
- Discovery: /ai-agent.json, Agent Card, MCP
- Scoped bearer, 401/422 stored, Tavily or ungrounded
- Fleet ingest → audit → settle on compute
Hardware is a different client
- Six classes remain modeled until they are writes
- Rae’s PO / freight write — shipped: mode/weight/distance → graded kg CO2e, always commits
- Supplier-only / buyer-only scoped tokens for the two-sided PO flow — next
- Tenki wired — sandboxes for agent test workflows
| Class | Scope | Default | ± | Live today |
|---|---|---|---|---|
| Cloud & AI compute | S3 Cat 1 | 8.5 t/yr | 30% | live · fleet + Tavily |
| Hardware | S3 Cat 2 | 3.2 | 40% | modeled |
| Travel | S3 Cat 6–7 | 4.8 | 25% | modeled |
| Vendors & SaaS | S3 Cat 1 | 2.1 | 50% | modeled |
| Logistics | S3 Cat 4 & 9 | 12.0 | 35% | modeled |
| Electricity | S2 | 5.6 | 15% | modeled |
| Direct | S1 | 1.5 | 20% | modeled |
Four sponsors make this live.
Cloudflare
Workers, DO, Workers AI
Tavily
Web search on the write path
Mitosis
Cortex agent memory, wired into the scheduler
Tenki
Agent test environments
A sandbox the Worker can create but not run. A memory that round-trips for real.
Tenki hit a real platform limit this weekend and got built around it honestly. Mitosis is a verified real write, then a real recall — not a claim.
/v1/sandbox/verify → exec outside → /v1/sandbox/complete
cortex_remember → cortex_recall, real universal_id
Every scheduled fleet run writes a summary to Cortex and can recall it back — the team's own agent memory, reachable via /v1/memory and MCP, not a Climatico-internal cache.
POST /v1/memory · 201 { "ok": true, "memoryId": "universal_id..." }
What it's for: enrichment, not the write path itself — a fleet run commits or flags on policy and Tavily evidence alone. Cortex is where that history becomes queryable later, by us or another agent.
Client swarm ↔ Climatico service → buyer ecosystem.
The same ledger grew a real cast of investigating agents this weekend. Orepath's own compute-watcher files what it finds autonomously, Climatico's fleet enforces policy and settles receipts, third-party providers deliver services through the same surface, and downstream buyers verify with read-only credentials. One ledger underneath all of it.
Orepath + Hardware Co
compute-watcher (Durable Object alarm) spikes cloud spend every 15 min during working hours. PortLogisticsAgent grounds the Oakland port. Hardware Co’s FactoryProcurementAgent files factory POs; OceanFreightAgent watches the port. A rogue MarketingBot tries to mint a green claim on purpose.
Climatico: 10 agents in one Worker
Ingest parses the spike. Audit scores kgCO2e against live Tavily sources. Settle commits a token-capped offset. Policy flags forbidden intents — and records the rejection. Scheduler (cron) runs all three plus Tavily abatement research every 30 min. Abatement researcher + summary writer (Workers AI) find real greener alternatives. Report builder compiles /v1/report. Inbox analyst pushes hotspot alerts. Clerk (Workers AI) answers questions. Every handoff is a row.
Provider agent · EV OEM auditor
green-offset-co (Durable Object) fulfills offsets the fleet writes, reviews receipts, earns revenue — delivered through the same surface. The buyer mints a climatico:read-only credential and audits the ledger before accepting any supplier claim. Transact rights: none. Proof of attribution that cannot write.
/.well-known/agent-card.json A2A discovery · /v1/credentials scopes freeze at mint (5 000¢ ceiling) · /mcp · /a2a · /v1/* one policy underneath · SQLite Ledger the settlement of record · climatico.sh CLI for human operators. In the UI this is the 3-Sided Swarm tab, deployed and live.
Your business information is very secure in Climatico.
When climatico.sh connect ~/my-startup runs, it scans the folder on the startup's machine and extracts only derived signals. The server never sees file contents. The CLI prints the exact JSON payload before sending and supports --dry-run to inspect without transmitting.
- File contents of
package.json,wrangler.*,README.md,.env, source code - Any other file in the folder
- Your data, your records, your secrets
- Vendor names from deps:
"stripe","datadog" - Cloud provider from config:
"Cloudflare Workers" - README keyword hits:
"mentions shipping" - kind, class, confidence — no values, no snippets
Salesforce reads your org's metadata, not your records. Google reads your ad counts, not your emails. Workday reads your headcount, not your salary data. Climatico reads your signals, not your source. We do not store your files. We do not train on them. We do not send them to third parties.
The CLI source is auditable. The server's /v1/connect handler does not accept a file_contents or path_contents field — by design, by contract, by source code. Future data connections (Salesforce, Google billing, Workday) will follow the same pattern: extract rollups locally, send rollups, never records.
Real numbers across the boundary, end to end.
A CLI swarm (climatico/scripts/two_sided_swarm.py) minted a scoped bearer, drove a genuine fleet spike, forced a forbidden claim, and let a read-only buyer inspect the ledger — all against climatico.dalrae-jin-work.workers.dev.
- 5 live Tavily citations scored the factor — not invented as GHG Protocol
- Offset 02564267 committed to SQLite, token-capped
- Role separation is a factor, not a chatbot paragraph
- Greenwash claimed at “Orepath Global Chain” intercepted before the write
- Flag eac21a5b persisted — same table as commits
- Read-only buyer minted climatico:read and audited 6 receipts
The footprint behind the business — and how to run the same business differently.
Orepath today, modeled: ~37.7 tCO₂e/yr across seven classes. CO₂e is the modeled core. Water, air pollution and e-waste sit upstream and downstream — labelled here but not yet broken out per class, because Climatico won’t print a number it can’t back up. Alternatives are the same business, run a different way — each keyed to the business source that drives the tonne.
| Business source | Impact (t CO₂e/yr · modeled) | Where it’s felt upstream | Alternative — same business, different run | Abatement (modelled) |
|---|---|---|---|---|
| Cloud & AI compute | 8.5 ±30% | data-centre power & cooling water | carbon-aware scheduling; move batch to a low-carbon region | largest share of compute |
| Logistics (Rae’s biggest) | 12.0 ±35% | freight diesel → local NOx & PM air | Oakland → rail / intermodal; route optimisation | biggest lever · freight write shipped |
| Purchased electricity | 5.6 ±15% | location-based grid mix | cleaner utility or on-site solar — a bill makes it measured | moves class to measured |
| Travel & commuting | 4.8 ±25% | aviation contrails | virtual-first; rail over air where it fits | per-trip cut |
| Hardware & electronics | 3.2 ±40% | mining + e-waste end-of-life | remanufactured units; extend refresh beyond 4 years | longer device life |
| Vendors & SaaS | 2.1 ±50% | supplier electricity upstream | consolidate vendors; right-size licences | licence-led cut |
| Direct emissions | 1.5 ±20% | combustion & fugitive | near zero for a cloud-only team | — |
−70 tCO₂e/yr at +24m (clima vs default)
At +24 months the abating path runs at 62 t vs 132 t if nothing changes — a modelled ~53% reduction from how the same revenue is produced. A projection, clearly labelled, not a measured cut.
Each class is a PO, a booking, a port
Not a dashboard metric — a system an agent already touches. That is the moment Climatico files it: the region, the freight mode, the server, the licence.
Water & air rows are upstream, not scored
CO₂e is the modelled and filed core. Water, NOx/PM and e-waste are named as knock-ons — but the desk won’t mint a pollution or handprint number it cannot back with evidence.
A resident auditor, awake on #team.climatico.
meshaudit joins wss://hack.cotal.ai/mesh-ws as its own actor, subscribes #team.climatico, and serves each region mention through Nebius (custom:nebius → DeepSeek-V4) — a real Hermes peer, not a fake write.
Join · subscribe · act
- hermes-agent 0.16 on the pinned line
- Subscribed to #team.climatico + #announce
- Runs tools — inspected its own env on a live turn
Small connector surgery
- Cotal spawn strips scratch env, so the launcher reads NEBIUS_API_KEY from .dev.vars
- Writes providers.nebius + model.provider: custom:nebius into the isolated profile
- Persona + launcher in climatico/scripts/run_meshaudit.sh
Named, not faked
- Connector patch edits node_modules — a cotal update resets it
- Live listener + Nebius routing proven; a full posted audit is next
Website edition for founders. Agent Edition for any AI agent, even one Climatico has never seen before.
cd climatico cp .dev.vars.example .dev.vars npm install && npx wrangler types npm run dev # 127.0.0.1:8787 npm run demo # this slide, in a shell ./climatico.sh fleet SJC 420 # CLI: 23 commands ./climatico.sh orepath # check Orepath agent ./climatico.sh agents-start # start the auto-pilot
Mint, prove the 401, file a Houston brief, commit an offset, store a greenwash flag, run the fleet under and over budget. CLI runs the same flows from any terminal.
| /ai-agent.json | event probe |
| /.well-known/agent-card.json | A2A card |
| /v1/credentials | mint, scopes freeze |
| /mcp | 15 tools, bearer required |
| /a2a | SendMessage |
| /v1/actions | the write (brief, watch, offset, assess, abate, switch, refund, freight) |
| /v1/fleet/run | ingest → audit → settle |
| /v1/report | plain-English progress + suggestions |
| /v1/agents/orepath | Orepath employee agent (auto-fleet) |
| /v1/agents/provider | 3rd-party offset provider |
| /v1/memory | Cortex memory store / recall |
| /v1/workspace | same feed as the desk |
| climatico/climatico.sh | CLI — 23 commands |
Measure early. Act early.
Helping startups scale sustainably — from day one.