Status: Pre-alpha. Vision, architecture, and a minimal MCP scaffold are published here. Active development begins after Help Tech's May 1, 2026 go/no-go decision. First real commits (if approved) land the week of May 4.
Alderfi is the first AI-native, open-source personal finance platform. When OpenAI acquired Hiro Finance in April 2026, thousands of privacy-conscious users lost their "AI CFO" with four weeks of notice. This project is the open, self-hosted answer: a conversational financial assistant where AI is the core interface — not an afterthought — built on the Model Context Protocol so it works with Claude, Cursor, your own agents, or our web UI as equal clients.
- AI-native, not AI-bolted-on. Every capability is an MCP tool. Conversation comes first; forms come second (and sometimes not at all).
- Open source, forever. Apache-2.0. We will not relicense the core. If we ever do, you can fork the day before.
- Self-hosted and local-first. SQLite + your hardware by default. Cloud is an option, never a requirement.
- Layered AI. Merchant rules handle the easy 70–80% with zero latency. A local LLM (Llama 3 8B via llama.cpp) handles the ambiguous 15–25%. Cloud LLMs are opt-in for edge cases. Your data only leaves the box if you say so.
- Read-only banking by default. SimpleFIN-first (proven at scale with Actual Budget). Plaid as a premium option for hosted users. Your banking credentials never touch our servers.
Just the scaffold. One MCP tool (list_accounts) returns mock data. This proves the protocol surface is real — no banking connectors, no AI categorization, no persistence yet. Those arrive in Phases 1–3.
npm install
npm run devThen point an MCP client at the server (stdio transport):
npx @modelcontextprotocol/inspector npm run devYou should see one tool, list_accounts, returning three mock accounts.
High-level phases (detailed architecture in ROADMAP.md):
- Phase 1 (weeks 1–2): MCP server + SimpleFIN/CSV connectors, transaction sync, SQLite store.
- Phase 2 (weeks 3–4): Layered categorization (rules → local LLM → cloud opt-in), anomaly detection, spending insights.
- Phase 3 (weeks 5–6): Conversational UI — natural-language budgeting, proactive alerts, chat-first queries.
- Phase 4 (week 7): Public alpha, Show HN / Product Hunt launch.
Development begins in earnest after Help Tech's May 1, 2026 go/no-go decision. First commits land the week of May 4 if approved.
License: Apache-2.0. Why Apache-2.0 over MIT for this project specifically:
- Explicit patent grant. Apache-2.0 §3 grants patent rights from contributors to users — important in a space (personal finance + AI) where future patent claims from banks, LLM providers, or rival commercial forks are a realistic risk. MIT is silent on patents.
- Industry norm for open-source AI. Llama 3, Mistral, Qwen, LangChain, vLLM, LlamaIndex, and most major AI OSS projects use Apache-2.0. Contributors and enterprises recognize and trust it.
- Enterprise-friendly without forcing copyleft. Companies (future hosted customers, contributors from banks) can adopt and contribute without legal review friction — unlike GPL/AGPL — while still getting the patent protection MIT lacks.
- Termination clause on patent litigation. If a contributor sues another user over patents, their license terminates. Meaningful deterrent; MIT offers none.
We considered MIT for simplicity but concluded the AI + fintech intersection makes patent silence too risky. The full license is in LICENSE; required attribution is in NOTICE. Contributors sign off commits per the Developer Certificate of Origin (git commit -s).
We're pre-alpha and iterating fast, but we welcome issues, discussion, and PRs on architecture. Before opening a PR please:
- Open an issue first describing the change — most scope conversations belong there, not in a PR.
- Sign off your commits (
git commit -s) — we use the Developer Certificate of Origin. - Keep PRs focused — one conceptual change per PR, tests included for new behavior.
See CONTRIBUTING.md for the full guide and CODE_OF_CONDUCT.md for community standards.
- Star this repo to follow along.
- Discuss — tell us what you want from an open-source AI finance tool. What would make you actually self-host?
- Hack — the scaffold is deliberately small so you can read it in 10 minutes.