Mole: Deep-Research Agent with Enforced Budget and Verified Quotes for Your Terminal
Mole is a deep-research agent that runs in your terminal. It decomposes a question, searches the web, reads sources, extracts claims, checks each claim against the text it came from, and writes an answer with citations. Unlike chat-based agents, it enforces a strict budget, verifies every claim, and keeps your local data private.
Enforced Budget
Every model call is reserved against a budget before it happens and settled after, using a ledger with non-negative constraints in the database schema. The --usd 0.50 flag means the run stops at fifty cents. Measured overshoot across the test corpus is 0%.
Verified Quotes
Every claim carries a quote that appears verbatim in the source page. Claims that don't pass this check are discarded at extraction. Surviving claims can be re-read against their source, and unsupported ones are marked in the report.
Local Data Privacy
Point mole at a CSV or folder, and it analyzes the data without the contents leaving your machine. The model chooses a hypothesis template and column names; mole runs the SQL locally. Only aggregates (counts, means, test results, buckets covering at least five records) are allowed back. mole crossings shows exactly what left your machine.
Installation
Install via script (Linux/macOS):
curl -fsSL https://raw.githubusercontent.com/lajosdeme/mole/main/install.sh | shOr via Homebrew:
brew install lajosdeme/mole/moleArch Linux (AUR): yay -S mole-research-bin or mole-research. Debian/Ubuntu: download the .deb from the releases page. From source (Go 1.25+): go install github.com/lajosdeme/mole/cmd/mole@latest.
Configuration
You need a search provider and a model provider. Keys live in ~/.config/mole/config.json with mode 0600 — never in environment variables. Mole supports most LLMs, including coding agents, subscriptions, and local models.
MCP Support
Mole speaks MCP, so a coding agent can drive it — either by handing mole a question and collecting the answer, or in toolkit mode, where the agent does the reasoning while mole supplies the non-model parts.
It's free and open source, runs as a single static binary with no runtime dependencies.
📖 Read the full source: HN AI Agents
👀 See Also
ComfyUI Skill Enables AI Agents to Queue and Batch Image Renders via Natural Language
A new open-source skill allows OpenClaw agents to construct ComfyUI workflows, submit jobs, and manage renders through natural language commands like 'Make 50 variations of this concept with different seeds' or 'Compare these 4 prompts side by side at 1024x1024'.
Developer Achieves Sub-Second STT/TTS Latency with Local Whisper and Coqui-TTS Servers
A developer has open-sourced local server implementations for Whisper STT and Coqui TTS that achieve ~0.2s speech-to-text and ~250ms text-to-speech latency, enabling conversational AI agents without cloud dependencies.
OpenClaw Setup Assistance Offered by ClawSet
ClawSet provides setup services for OpenClaw, focusing on understanding client needs. The service includes a setup call for $99 and a month of troubleshooting support.
Voxray-AI: Production Go Backend for Real-Time Voice Agent Pipelines
Voxray-AI is a Go backend that chains Whisper → any LLM → TTS into a real-time voice agent pipeline with WebSocket and WebRTC support. It's built for production-grade servers and high-concurrency voice workloads with configurable providers for STT, LLM, and TTS layers.