Skip to main content

Give your AI long-term memory in 1 command. SQLite-based, no setup, no servers.

Project description

AI-IQ

Give your AI long-term memory in 1 command.

LLMs forget everything. AI-IQ makes them remember.

Install

pip install ai-iq

Quick Start

from ai_iq import Memory

memory = Memory()

# Add memories
memory.add("User prefers dark mode", tags=["preference", "ui"])
memory.add("Redis bug fixed with network_mode: host", category="learning")

# Search (hybrid keyword + semantic)
results = memory.search("redis networking")
for r in results:
    print(f"#{r['id']}: {r['content']}")

# Update and delete
memory.update(1, "User STRONGLY prefers dark mode")
memory.delete(1)

CLI

memory-tool add learning "Docker needs network_mode: host" --project MyApp
memory-tool search "docker networking"
memory-tool dream  # Consolidate duplicates, detect conflicts

Claude Code Plugin

Use AI-IQ directly in Claude Code with auto-capture:

/plugin marketplace add kobie3717/ai-iq
/plugin install ai-iq

See CLAUDE_CODE_PLUGIN.md for details.

Why AI-IQ?

  • Single SQLite file = your AI's brain — No servers, no vector DB, no setup
  • No cloud dependencies — Works offline, owns your data, zero API keys
  • Works with any Python agent — Not locked to Claude, OpenAI, or any vendor
  • Hybrid search — Keyword (FTS5) + semantic (vector) + graph traversal
  • Memories decay naturally — FSRS-6 algorithm like human memory

Advanced Features

See docs/REFERENCE.md for complete documentation:

  • Beliefs & Predictions — Confidence tracking with Bayesian updates
  • Knowledge Graph — Entities, relationships, spreading activation
  • Dream Mode — REM-like consolidation (dedup, conflict detection)
  • Identity Layer — Auto-discovers behavioral traits
  • Narrative Memory — Builds cause-effect stories from causal graph
  • Meta-Learning — Search improves from feedback loops

Example

See examples/chatbot_with_memory.py

Documentation

Complete ReferenceExamplesArchitecture

Requirements

Python 3.8+ and SQLite 3.37+. Optional: pip install ai-iq[full] for semantic search.

License

MIT

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ai_iq-5.7.0.tar.gz (166.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ai_iq-5.7.0-py3-none-any.whl (128.6 kB view details)

Uploaded Python 3

File details

Details for the file ai_iq-5.7.0.tar.gz.

File metadata

  • Download URL: ai_iq-5.7.0.tar.gz
  • Upload date:
  • Size: 166.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for ai_iq-5.7.0.tar.gz
Algorithm Hash digest
SHA256 8b2e90b7883ea6a271443d936a9ff8e3f13b77aca7d4fc9257f6e50cb6380318
MD5 5ebb91c84b87b448e806b83278f33a60
BLAKE2b-256 be8aeb6b1412200c65f0f3cc36c4304bcea5844ba157a2878362204b4fe070da

See more details on using hashes here.

File details

Details for the file ai_iq-5.7.0-py3-none-any.whl.

File metadata

  • Download URL: ai_iq-5.7.0-py3-none-any.whl
  • Upload date:
  • Size: 128.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for ai_iq-5.7.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4ffc4bf690b221ee4f3a30976cba8c9b49625075fb3b35712511248d898b44c6
MD5 490ae418f28c7c5991e9730d2e1038a4
BLAKE2b-256 23e00ea4855d0fd9e28938a15edb55c2330502f251c64a2230f34c8fdda0515b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page