Aevia
Expanding life cycle assessment and thinking through generative AI
Aevia is an assistant for life cycle assessment. It searches the LCA literature and LCA databases, builds LCA models — product systems — and runs impact assessments on them. Its interface is made for interrogating what comes back, so you arrive at the meaning rather than at a column of numbers.
It works alongside the software you already use: connect your own openLCA, or plug Aevia into your Claude, ChatGPT or other assistant account and drive it from there.
New accounts start with 500 free credits and a month of the full product — enough to do real work before you decide. No payment details needed.
Help me compare the environmental impacts of three different types of typical swiss houses. First search the web for information about typical swiss houses, then search the literature, then model the houses, then assess their impacts, and then compare them and state your conclusions.
How it works
From a question to something you understand.
It follows the shape an assessment already has — find the data, model the system, run the numbers, work out what they mean — without forcing you down a compliance workflow. Aevia is as useful for an exploratory comparison or a sanity check as it is for a full ISO 14040 study.
Search LCA literature and databases
Ask in plain language. Aevia searches peer-reviewed LCA journals for method and context, and the unit processes in your database for data — thousands of datasets, in the descriptors they were published under, British spellings and market for … conventions included.
Build product systems to model what you want to investigate
State the functional unit and the system boundary; Aevia assembles the product system, from a bill of quantities or as an explicit network of linked unit processes. You see the model before anything is calculated, and you can edit it — add a member, rewire a link, change an amount — with the same validation either way.
Assess the environmental impacts of your models
A full LCIA on a real engine: classification and characterisation across every category the chosen method defines, using the characterisation factors the engine resolves rather than the ones stored in the method definition — so unit conversion, regionalisation and direction sign are the engine's, not a reconstruction of them.
Gain understanding
The phase that decides whether an assessment is worth anything. Contribution analysis by member or by elementary flow, sensitivity on any driver or parameter, comparison across product systems — then a Word report carrying the goal and scope, the method, the data provenance and the figures.
Grounded in the literature
Half of an assessment is an argument from the literature.
Allocation choices, method selection, the defensibility of a proxy dataset — these get settled in papers and standards, not in a database column. Aevia searches a curated library semantically, returns the passage rather than the whole document, and cites what it used, so a sentence in your report can be traced back to a page.
The library currently indexes four journals:
- The International Journal of Life Cycle Assessment
- Journal of Cleaner Production
- Journal of Industrial Ecology
- Sustainability
Only what we are entitled to read. Aevia indexes abstracts and bibliographic records across all of these journals, and full text only for open-access articles. Everything else is searchable by its abstract and citation, and links out to the publisher for the rest — so the assistant can point you to a paper it may not quote, which is the honest version of a literature search.
- Search is on every plan, including the free one.
- Live web search and page fetch, for the guidance note that is in no library yet.
- On Connect, add your own library — PCRs, client reports, internal method notes — searchable alongside the rest and private to you.
Connects with your stack
Aevia plugs into the tools you already pay for.
It is an interface and an orchestrator, not another silo. Two connections matter today, and neither asks you to move anything.
Your LCA software
A small connector opens a private tunnel from your own openLCA to Aevia. The assistant browses and calculates through it, so every solve runs on your hardware against the databases you already have open — and because it is your CPU under your licence, we never meter it.
Aevia works on your installation and the databases you are licensed for — ecoinvent included.
The datasets stay in your openLCA. What Aevia keeps is the shape of your work — which unit processes a system links to, by identifier, and the results you calculated. The inventory behind those identifiers is read from your engine each time it is needed rather than copied into ours, so there is no licensed database here for us to host or redistribute, and your licence stays between you and your licensor.
Your assistant subscription
Aevia's LCA tools are exposed over MCP, so you can drive them from Claude, ChatGPT or another MCP-capable client using the assistant account you already have. That is usually the cheapest way to run real volume: a consumer subscription buys a great deal more usage per dollar than metered API access, and we would rather tell you so than let you find out later.
Or work inside Aevia and let us supply the assistant, metered in credits. Most people do both — the connector when they are already deep in a conversation elsewhere, Aevia's own interface when they want the workspace, the panels and the report in front of them.
Tunneling your own openLCA is on Connect and above; the MCP connector is on Bridge. Both are included free for your first month, so you can try them before choosing.
Traceability
Every number remembers where it came from.
The hard question about an assessment is never asked on the day you finish it. It comes six months later, from a client or a reviewer, and it is always some version of why is this figure what it is?
So nothing here is overwritten. Every product system is versioned and immutable: editing writes a new version, and an assessment stays pinned to the exact version it was calculated from. The chain from a figure in your report back to the model, the method and the datasets behind it stays intact.
- One name for one thing. A product system is s1, its assessment a2 — the same handle in every conversation and everywhere in the interface, so you and the assistant are never discussing two different objects by the same name.
- Change announces itself. Edit a system and every assessment computed from the previous version is flagged as out of date — instead of quietly becoming wrong while still looking finished.
- Drift is detected, not guessed. If the copy in your openLCA moves out of step with the copy here, Aevia says so and offers you the resolutions rather than silently choosing one.
- Even the assistant is accounted for. Each conversation reports the credits it spent, down to the individual tool call — alongside the energy and water its own model usage consumed.
Any language
LCA does not only happen in English.
Ask in Spanish, Portuguese, German or French and the whole conversation follows you there — the reasoning, the explanation of a method choice, the prose of a report. The one thing that stays put is the data: a process descriptor keeps the exact wording its database published, in the language it published it, because a translated descriptor is no longer traceable to the dataset it names.
Plans
Two plans. Start on the free one.
Free comes with enough credit for a real evaluation, and lends you the paid capabilities for your first month so the evaluation is of the whole product. Connect is for working practitioners — your own openLCA, linked process networks, reports and no limits. Bridge adds the MCP connector, for driving Aevia from the assistant you already pay for.
What a credit is
The unit your assistant usage is metered in — the model tokens, the searches, the embeddings behind a conversation. How far a credit goes depends on which model you put to work, which is why every conversation reports what it spent.
They are pre-paid
Always. There is no overage billing and no automatic top-up, so a month can never end with you owing money you did not choose to spend.
Running out is not a lockout
At zero the assistant pauses. Your workspaces, product systems, assessments and reports stay open and readable, and a top-up starts the conversation again.
See what Aevia does, on curated public databases. For trying it properly, teaching, and studying.
Sign in- Full LCA tooling on the BAFU Swiss and ELCD databases
- Product systems from a bill of quantities, assessed and compared
- Contribution and sensitivity analysis
- Literature search and web search
- Versioned workspaces — 10 workspaces, 50 chats
- Your own openLCA and the MCP connector, free for your first month
- Linked product systems — explicit process networks
- Word reports and export
500 credits, granted once — a gift, not a monthly allowance. Enough to evaluate this properly rather than enough to get a taste, and yours to spend at whatever pace suits.
Aevia as the interface to the openLCA and data licences you already have. For working practitioners.
Sign in- Your own openLCA, tunneled — your engine, your licences, never metered
- Linked product systems — model an explicit network of unit processes, not just a bill of quantities
- Word (.docx) reports and data export
- Upload your own documents into the knowledge base
- Unlimited workspaces, chats and saved objects
- Every assistant model, including the premium tier
- Assistant usage included each week, then credits at cost
- MCP connector — driving the tools from Claude or ChatGPT
Billed monthly, cancel any time. Credit top-ups are always pre-paid and never automatic.
Combine the assistant account you already pay for with Aevia's LCA tools. For people who would rather work inside Claude or ChatGPT.
Sign in- Everything in Connect
- MCP connector — drive Aevia's LCA tools from Claude, ChatGPT or another MCP client
- Runs on your assistant subscription, so that work spends none of your credits
Usually the cheapest way to run real volume: a consumer assistant subscription buys a great deal more usage per dollar than metered API access, and we would rather tell you so than let you find out later.
Whichever you pick, the account is the same one: every account starts free, and upgrading is a switch in your billing settings that adds capabilities rather than replacing them. You can move between them without losing any work.
Questions
Straight answers
Do I need openLCA to use this?
Not to start. The free plan runs against curated public databases that we host, so you can build systems and run real assessments without installing anything. Connecting your own openLCA is a Connect feature — and it is one of the things your first month includes, so you can point Aevia at your own engine and data before deciding whether it is worth paying for.
Can I use ecoinvent?
If you hold an ecoinvent licence and have it open in your openLCA, Aevia works against it the same way it works against any other database — the tunnel forwards requests to your own engine and does not care which data is loaded. We do not supply, host or redistribute ecoinvent today, and your licence terms with them continue to govern your use of the data. A plan that includes a commercial database hosted by us is the obvious next rung of this ladder and the product is built for it; we will say so plainly when it is real rather than promise it now.
Can my team work on the same assessments?
Not yet — an account is one person today, and everything you build lives in your workspaces. Shared workspaces and version-controlled product systems, with the kind of history a modeller expects when several people edit the same system, are what we are building toward; openLCA's own collaboration server is the natural way in. We would rather show you that working than put a date on it.
What can you see of my data?
Calculations on your own engine run on your machine. What Aevia stores, in your own workspace, is the systems and assessments you save — process identifiers, the link structure between them, the names needed to display them, and the numbers your calculations produced. It does not pull the underlying datasets out of your database, and nothing in your workspace is shared with other users or sold to anyone.
Is this a compliance or EPD tool?
No, and deliberately not. Aevia is an assistant for someone who knows what they are doing — it does not issue verified declarations, it is not a certification pipeline, and it does not replace a critical review. It is built to make an expert faster and better-sourced, and you remain the author of the assessment.
Which assistant models does it use?
Several, from several providers, routed per task — a cheap model for routine work and a stronger one where it matters. Connect includes the premium tier. We publish what each conversation cost, so the routing is visible rather than something you have to trust.
What happens when I run out of credits?
The assistant pauses and everything else keeps working: your workspaces, product systems, assessments and reports stay open and readable, and you can still export them. You top up to start chatting again. Nothing is ever charged automatically.
Is the free credit a trial that expires?
No. It is granted once when you verify your email and it is not a countdown — there is no fourteen-day clock, and no card to cancel before. When it is spent, you decide whether to top up.
Why meter usage at all?
Because a conversation with a capable model has a real cost, and it varies enormously with what you ask for. Metering it is what lets the free plan be genuinely useful instead of tightly rationed, and it means you can see exactly what a piece of work cost you rather than guessing against an opaque quota.
Can I cancel?
Any time, and your work stays yours to read and export. A subscription runs to the end of the period you have paid for and does not renew after that. See the refund policy for how part-months and unused credits are handled.
Who takes the payment?
Paddle, acting as merchant of record. Card details never reach us — we receive a transaction reference and your subscription status, and your statement will show Paddle rather than Aevia.
Try it on something you already know the answer to.
That is the honest test of an assessment tool, and the fastest way to find out whether this one is any good. A new account starts with enough credit to do it properly.