feed · watching · stats · help with your tokens
openaccountant/wilson
Wilson is a privacy-first AI bookkeeper that imports transactions, categorizes spending, tracks budgets, and generates financial reports locally.
It solves the problem of managing personal finances with AI assistance while ensuring data privacy by keeping all financial data local, targeting users who want an AI bookkeeper without cloud dependency. The application uses a local SQLite database for storage and supports multiple LLM providers, including local Ollama, to keep financial data on the user's machine.
Similar
- JustVugg/colibri
colibri is a C inference engine that runs very large open mixture-of-experts models on the machine you already have.
- deepseek-ai/dsh-superagent-prototype
dsh-superagent is a research prototype for a proactive coding agent that works on a single GitHub repository using DeepSeek Harness.
- anthropics/FlashProve
FlashProve is a research prototype for zero-knowledge proofs of AI inference that allows providers to prove model identity without revealing weights.
- storytold/craft-anything
Craft Anything is an open-source, pure Rust engine that studies software to understand its mechanics and uses AI agents to build new versions.
- vercel-labs/agent-desktop
agent-desktop gives AI agents computer use on macOS, Windows and Linux by reading the OS accessibility tree instead of screenshots.
- govijr/terminal-mac
terminal-mac is a CLI tool that runs a separate macOS desktop in a virtual machine for computer-use agents, viewed and controlled from a terminal.
- Muvon/octomind
Octomind is an open-source coding agent harness that gives an LLM real access to a repository through MCP tools.
- NVIDIA/auto-ontology
An open context layer that turns database metadata into an ontology, so AI agents answer questions about enterprise data with fewer wrong answers.
sources
Claims below include README evidence. A matching quote or worker agreement does not establish that a claim is correct. Category majority among 2 workers. Version 1.
Wilson is a privacy-first AI bookkeeper that imports transactions, categorizes spending, tracks budgets, and generates financial reports locally.
Privacy-first AI bookkeeper — import transactions, categorize spending, track budgets, and generate financial reports.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
It solves the problem of managing personal finances with AI assistance while ensuring data privacy by keeping all financial data local, targeting users who want an AI bookkeeper without cloud dependency.
Privacy-first financial assistant for your terminal.
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
The application uses a local SQLite database for storage and supports multiple LLM providers, including local Ollama, to keep financial data on the user's machine.
All data is stored locally in `~/.openaccountant/data.db` (SQLite).
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Imports bank statements from CSV files, automatically detecting formats from Chase, American Express, and generic sources.
Bank CSV import — Auto-detects Chase, American Express, and generic CSV formats
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Uses AI to classify transactions into 18 spending categories, allowing users to select their preferred LLM provider.
AI categorization — Classifies transactions into 18 spending categories using your choice of LLM
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Detects spending anomalies such as duplicate charges, unusual spikes, and forgotten subscriptions.
Anomaly detection — Flags duplicate charges, unusual spikes, and forgotten subscriptions
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Supports 9 LLM providers including OpenAI, Anthropic, Google, xAI, Moonshot, DeepSeek, OpenRouter, LiteLLM, and local Ollama.
9 LLM providers — OpenAI, Anthropic, Google, xAI, Moonshot, DeepSeek, OpenRouter, LiteLLM, and Ollama (local)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Extensible via Model Context Protocol (MCP) servers, allowing users to add external tools to the agent.
MCP extensibility — Add tools via Model Context Protocol servers
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Provides semantic transaction search in the dashboard that understands meaning rather than just substrings, using on-device embeddings.
Semantic transaction search — The dashboard Transactions search understands meaning, not just substrings
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
The web dashboard maintains a local mirror of transactions, allowing offline browsing, search, and filtering when the server is unreachable.
Offline dashboard transactions — the dashboard keeps a sync-fed local mirror
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Includes multi-step workflows called 'skills' for tasks like subscription audits, which can be extended with custom user-defined skills.
Skills — Multi-step workflows like subscription audits, extensible with custom skills
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Syncs transactions directly from Monarch Money accounts.
Monarch Money sync — Pull transactions directly from your Monarch Money account
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Integrates web search capabilities via Exa, Perplexity, Tavily, or Brave to research merchants and financial questions.
Web search — Research merchants and financial questions (Exa, Perplexity, Tavily, Brave)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Auto-detects Chase, American Express, and generic CSV formats
Auto-detects Chase, American Express, and generic CSV formats
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Classifies transactions into 18 spending categories using your choice of LLM
Classifies transactions into 18 spending categories using your choice of LLM
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Flags duplicate charges, unusual spikes, and forgotten subscriptions
Flags duplicate charges, unusual spikes, and forgotten subscriptions
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Save filtered transactions to CSV or XLSX
Save filtered transactions to CSV or XLSX
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Research merchants and financial questions (Exa, Perplexity, Tavily, Brave)
Research merchants and financial questions (Exa, Perplexity, Tavily, Brave)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Add tools via Model Context Protocol servers
Add tools via Model Context Protocol servers
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Chain tools sequentially or run parallel teams for complex workflows
Chain tools sequentially or run parallel teams for complex workflows
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Multi-step workflows like subscription audits, extensible with custom skills
Multi-step workflows like subscription audits, extensible with custom skills
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
The dashboard Transactions search understands meaning, not just substrings
The dashboard Transactions search understands meaning, not just substrings
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
OpenAI, Anthropic, Google, xAI, Moonshot, DeepSeek, OpenRouter, LiteLLM, and Ollama (local)
OpenAI, Anthropic, Google, xAI, Moonshot, DeepSeek, OpenRouter, LiteLLM, and Ollama (local)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
the dashboard keeps a sync-fed local mirror (wa-sqlite on OPFS, inlined in the single-file build)
the dashboard keeps a sync-fed local mirror (wa-sqlite on OPFS, inlined in the single-file build)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
the heatmap, streak, weekly summary, budget countdown, savings sparkline, category donut, P&L, and budget bars all recompute locally
the heatmap, streak, weekly summary, budget countdown, savings sparkline, category donut, P&L, and budget bars all recompute locally
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Requires either a locally running Ollama instance or an API key for a cloud LLM provider.
An LLM provider: either Ollama running locally **or** an API key for a cloud provider
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: The browser-based transaction mirror is unencrypted at rest, relying on OS-level full-disk encryption for protection.
the browser mirror is **unencrypted at rest**
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: the browser mirror is unencrypted at rest (browser origin storage holds plaintext, unlike the SQLCipher-encrypted CLI database)
the browser mirror is unencrypted at rest (browser origin storage holds plaintext, unlike the SQLCipher-encrypted CLI database)
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Entity assignment (and every other write) stays online-only
Entity assignment (and every other write) stays online-only
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: An MCP tool whose name is already taken by a built-in or another tool is not registered
An MCP tool whose name is already taken by a built-in or another tool is not registered
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: A server could mislabel a tool that writes
A server could mislabel a tool that writes
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
Limitation: Only tools you list there count as read-only
Only tools you list there count as read-only
Quote matched the README or GitHub description at extraction. Same claim and quote from 1 worker(s). Interpretation not reviewed by a maintainer.
ai-ml · cli