ain-research 1.2.0

AIN Infinite Research System - Multi-Agent Automated Science DAEMON. Engineered to sit on top of LLMs to autonomously guide research, provide storage, and retrieval functionality. Evolving into a 10x autonomous ecosystem.

AIN Research Daemon Library

Welcome to the AIN Infinite Research Daemon (ain-research), an open-source Python library built by That-Tech-Geek. This library provides the core infrastructure for an Autonomous Intelligence Network (AIN), sitting seamlessly on top of LLMs to guide, automate, and orchestrate open-ended domain research.

What is it?

ain-research is a sophisticated pipeline for automated research ingestion, storage, and retrieval. It allows LLMs and autonomous agents to asynchronously fetch papers from ArXiv, crawl open-source repositories from GitHub, and store them securely into a local SQLite queue before finally syncing them into a hyper-fast, modular knowledge base (the Vault).

Key capabilities include:

• Infinite Research Daemon: Time-boxed, autonomous daemon that fetches domain-specific research using intelligent rate-limiting and rotating APIs.
• LLM Steering Integration: It is engineered to sit on top of LLMs. You can use the CLI or built-in MCP Server to dynamically add new search queries, refine categorizations, and prioritize processing.
• Atomic Concurrency Control: Uses OS-level kernel FileLocks to ensure zero data corruption during heavy concurrent reading/writing by different agents.
• Model Context Protocol (MCP): Directly expose your AIN Second Brain to any MCP-compatible LLM client (like Claude Desktop or other agents), allowing them to queue research, check system health, and compile the wiki on demand.

Use Cases

1. Automated Overnight Crawling Let the daemon run overnight (ain-daemon). It crawls ArXiv and GitHub based on your configured categories (e.g., Quant Finance, LLMs) and stores the results securely. By the time you wake up, your Vault is packed with fresh, tagged Markdown files.

2. LLM-Guided Research If you have a primary agent researching "Agentic Frameworks", the agent can use the MCP server (ain-mcp) to dynamically add "Agentic Frameworks" to the daytime priority ingestion queue. The daemon will immediately fetch relevant papers and repos, syncing them into the Vault for the LLM to read.

3. Hyper-fast Retrieval The core indexing engine (ain compile) resolves thousands of nodes into lightweight Maps of Content (MOCs) and exact tag inversions, enabling LLMs to quickly query specific subjects without context-window bloat.

Installation

pip install ain-research

Quick Start

1. Configure Workspace

By default, the package uses ~/.ain/ as the root workspace. You can override this using the AIN_WORKSPACE environment variable.

2. Start the Daemon

ain-daemon

Runs the overnight crawler. By default, it operates actively between 22:00 and 23:59.

3. Add to Queue via CLI

ain queue add --arxiv 2305.14314

4. Configure Themes & Schedule

ain theme add --name "Quant" --query "cat:q-fin.*" --tags "finance"
ain schedule --start "22:00" --end "23:59:59"

5. Compile the Knowledge Base

ain compile

Generates the Maps of Content (MOCs), Mermaid network graphs, and visualizer data.

6. Launch MCP Server

To allow LLMs to natively hook into the daemon's research capabilities:

ain-mcp

(Configure this in your LLM client's MCP configuration settings).

Author

That-Tech-Geek

10x Evolution Features (v0.2.0+)

ain-research has evolved from an assistive background utility into an autonomous, 10x-scale ecosystem. It incorporates several advanced systems:

1. Self-Verifying Logic Engine

It actively fights hallucinations using a highly deterministic logic system.

• Cross-Examination: It flags anomalies and invalid assumptions by cross-referencing contradictory data points.
• Logic Proofs: Evaluates findings with mathematical and architectural correctness, minimizing the need for human debugging.

2. Multi-Agent Swarm Orchestration

Instead of running as a single synchronous loop, it now operates as a background multi-agent network.

• Division of Labor: Specialized agents concurrently verify, structure, and peer-review incoming research data.
• Continuous Execution: The swarm processes queue items in real-time alongside the daemon's regular horizon scanning.

3. Zero-Friction Abstract Interface (ain intent)

You can bypass manual tool configurations by simply passing high-level intents.

• Command: ain intent "Explore sparse autoencoders in LLMs"
• The system automatically leverages the LLM client to decompose this intent into discrete tasks, builds the search queries, and delegates them to the swarm.

4. Traceable Truth Layer

Decisions are no longer a "black box".

• Deterministic trace logs are saved into truth_logs/.
• Every LLM judgement, verification step, and data modification is recorded to provide full auditability, turning untrusted guessing into enterprise-grade intelligence.

AIN Infinite Research CLI Documentation

The AIN Research Engine provides a powerful Command Line Interface (CLI) for managing the knowledge vault, ingestion queues, autonomous intent decomposition, and agent integrations.

This document details the available commands and their usage.

---

1. ain compile

Description: Compiles the Vault Index and processes tags across all Markdown files in the local AIN vault. It synchronizes and recalibrates the visualizer data, ensuring that the 3D Neural Network Visualizer and the central INDEX.md reflect the most recent insights.

Usage:

ain compile

---

2. ain queue

Description: Manages the ingestion queue for academic papers and external data sources. The queue supports automated processing, retries, and tracking.

ain queue add

Adds a specific ArXiv paper to the ingestion queue by its ID.

Usage:

ain queue add --arxiv <arxiv_id>

Example: ain queue add --arxiv 2307.09288

ain queue list

Lists up to 50 pending items in the ingestion queue, displaying their item type, identifier, and current retry count.

Usage:

ain queue list

---

3. ain theme

Description: Manages the active research themes and categories stored in the system. The daemon monitors these topics/themes for incoming literature on ArXiv.

ain theme list

Lists all currently active themes, their corresponding ArXiv queries, and tags.

Usage:

ain theme list

ain theme add

Adds a new research theme to the system.

Usage:

ain theme add --name "<theme_name>" --query "<arxiv_query>" [--tags "<tag1,tag2>"]

Example: ain theme add --name "LLM Agents" --query "cat:cs.AI AND all:agent" --tags "ai,agents"

ain theme remove

Removes a specific research theme by its name.

Usage:

ain theme remove --name "<theme_name>"

Example: ain theme remove --name "LLM Agents"

---

4. ain schedule

Description: Sets the daily time window during which the AIN Research daemon is allowed to autonomously crawl ArXiv and other data sources for the active themes.

Usage:

ain schedule --start "<start_time>" --end "<end_time>"

Example: ain schedule --start "22:00" --end "23:59:59"

---

5. ain intent

Description: Leverages the local LLM to autonomously decompose a broad research goal into specific, highly-targeted search topics (3 topics by default). It automatically queues these topics for ongoing ArXiv monitoring and processing.

Usage:

ain intent "<research_goal>"

Example: ain intent "Find state-of-the-art methods for algorithmic market making using reinforcement learning"

---

6. ain ui

Description: Launches the local Truth UI web server to visualize the vault connections (ArXiv Scraps -> First Principles) and interact with the AIN Research Engine graphically.

Usage:

ain ui [--port <port_number>]

Example: ain ui (defaults to port 8000) Example: ain ui --port 8080

---

7. ain setup-agents

Description: Bootstraps the integration between the AIN Research Engine and external AI agents (like Claude Code, Cursor, or Codex) via the Model Context Protocol (MCP).

What it does:

1. Creates AGENTS.md: Generates a standard instruction protocol file that guides agents on how to use the AIN MCP server (queue management, compilation triggers, intent decomposition).
2. Cursor/Codex Configuration: Sets up .cursor/mcp.json to register the ain-mcp command as an active MCP server for the IDE.
3. Claude Code Configuration: Generates a claude.json configuration file enabling Claude to interface directly with the daemon.

Usage:

ain setup-agents